{"schemaVersion":"1.0","snapshotDate":"2026-07-15","generatedAt":"2026-07-15T22:59:35.409Z","source":{"name":"Hugging Face official benchmark registry","registryUrl":"https://huggingface.co/api/datasets?filter=benchmark:official","documentationUrl":"https://github.com/huggingface/hub-docs/blob/main/docs/hub/datasets-benchmark.md","acquiredFrom":"local July 2026 API snapshot"},"counts":{"atlasBenchmarks":159,"registryBenchmarks":38,"scoredBenchmarks":34,"scoreLinkedAtlasRecords":34,"rawSubmissions":757,"selectedModelBenchmarkPairs":687,"uniqueModels":346},"methodology":{"scoreSelection":"For each exact model ID and benchmark, select the best reported configuration; retain every raw submission in rawScores.","normalization":"Average-rank percentile within each benchmark after exact-model deduplication; 100 is the strongest observed result and ties share a percentile.","benchmarkHealth":"Geometric mean of participation, observed discrimination, dataset freshness, and submission-source quality. Benchmarks need at least three models to aggregate.","aggregation":"Health-weighted mean of within-benchmark percentiles for each use case. Coverage and confidence are reported separately and never folded into the score.","comparability":"Scores compare reported systems, not base-model ability. Tools, prompts, reasoning settings, scaffolds, frame counts, and budgets may differ.","sourceClasses":{"registry-verified":"Submission marked verified by the registry.","benchmark-operator":"Benchmark or official leaderboard result.","independent":"Independent or community evaluator result.","self-reported":"Model-card or submitter-reported result.","unclassified":"Provenance did not match a stronger source class."}},"useCases":[{"id":"reasoning","name":"Reasoning & knowledge","short":"Hard questions, math, factuality, and structured instruction following.","domains":["General Models","Science & Reasoning"]},{"id":"coding","name":"Coding & repository work","short":"Issue resolution, terminal work, CUDA, and long-horizon software engineering.","domains":["Coding & SWE"]},{"id":"agents","name":"Agents & tool use","short":"Tools, browsers, professional workflows, memory, constraints, and end states.","domains":["Agents & Tool Use","Customer Support"]},{"id":"documents","name":"Retrieval & documents","short":"Search, OCR, document parsing, long context, and evidence-grounded answers.","domains":["Retrieval & RAG"]},{"id":"professional","name":"Legal & financial work","short":"Contracts, exams, negotiations, earnings calls, and professional services tasks.","domains":["Legal","Finance"]},{"id":"science-health","name":"Science & healthcare","short":"Clinical workflows, scientific research, expert reasoning, and life-science work.","domains":["Healthcare","Science & Reasoning"]},{"id":"multimodal","name":"Multimodal & voice","short":"Audio, ASR, video, GUI grounding, vision-language reasoning, and robotics.","domains":["Multimodal & Voice"]},{"id":"safety","name":"Safety & security","short":"Refusal reliability, scientific misuse, cyber risk, and policy compliance.","domains":["Safety & Security"]}],"sourceClassCounts":{"unclassified":37,"self-reported":392,"independent":134,"benchmark-operator":194},"benchmarks":[{"id":"LiquidAI/ifstruct-v1.0","atlasSlug":"ifstruct-v1","name":"IFStruct v1.0","domain":"General Models","useCases":["reasoning"],"datasetUrl":"https://huggingface.co/datasets/LiquidAI/ifstruct-v1.0","leaderboardUrl":"https://huggingface.co/api/datasets/LiquidAI/ifstruct-v1.0/leaderboard","lastModified":"2026-07-07T12:32:14.000Z","license":"apache-2.0","submissions":5,"models":5,"health":{"participation":0.388,"discrimination":0.809,"freshness":1,"sourceQuality":0.588,"weight":0.656,"eligibility":"included"}},{"id":"openai/gsm8k","atlasSlug":"gsm8k","name":"GSM8K","domain":"Science & Reasoning","useCases":["reasoning"],"datasetUrl":"https://huggingface.co/datasets/openai/gsm8k","leaderboardUrl":"https://huggingface.co/api/datasets/openai/gsm8k/leaderboard","lastModified":"2026-03-23T10:18:13.000Z","license":["mit"],"submissions":18,"models":18,"health":{"participation":0.638,"discrimination":0.67,"freshness":1,"sourceQuality":0.579,"weight":0.705,"eligibility":"included"}},{"id":"allenai/olmOCR-bench","atlasSlug":"olmocr-bench","name":"olmOCR-bench","domain":"Retrieval & RAG","useCases":["documents"],"datasetUrl":"https://huggingface.co/datasets/allenai/olmOCR-bench","leaderboardUrl":"https://huggingface.co/api/datasets/allenai/olmOCR-bench/leaderboard","lastModified":"2026-02-19T17:28:38.000Z","license":"odc-by","submissions":15,"models":15,"health":{"participation":0.601,"discrimination":0.646,"freshness":1,"sourceQuality":0.525,"weight":0.672,"eligibility":"included"}},{"id":"cais/hle","atlasSlug":"humanity-s-last-exam","name":"Humanity's Last Exam","domain":"Science & Reasoning","useCases":["reasoning","science-health"],"datasetUrl":"https://huggingface.co/datasets/cais/hle","leaderboardUrl":"https://huggingface.co/api/datasets/cais/hle/leaderboard","lastModified":"2026-01-20T22:42:17.000Z","license":"mit","submissions":68,"models":41,"health":{"participation":0.81,"discrimination":0.834,"freshness":1,"sourceQuality":0.565,"weight":0.786,"eligibility":"included"}},{"id":"datacurve/deep-swe","atlasSlug":"deepswe","name":"DeepSWE","domain":"Coding & SWE","useCases":["coding"],"datasetUrl":"https://huggingface.co/datasets/datacurve/deep-swe","leaderboardUrl":"https://huggingface.co/api/datasets/datacurve/deep-swe/leaderboard","lastModified":"2026-06-02T19:31:16.000Z","license":null,"submissions":2,"models":2,"health":{"participation":0.238,"discrimination":0.765,"freshness":1,"sourceQuality":0.55,"weight":0,"eligibility":"insufficient-participation"}},{"id":"TIGER-Lab/MMLU-Pro","atlasSlug":"mmlu-pro","name":"MMLU-Pro","domain":"Science & Reasoning","useCases":["reasoning"],"datasetUrl":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","leaderboardUrl":"https://huggingface.co/api/datasets/TIGER-Lab/MMLU-Pro/leaderboard","lastModified":"2026-05-02T06:26:05.000Z","license":"mit","submissions":140,"models":140,"health":{"participation":1,"discrimination":0.86,"freshness":1,"sourceQuality":0.714,"weight":0.885,"eligibility":"included"}},{"id":"ScaleAI/SWE-bench_Pro","atlasSlug":"swe-bench-pro","name":"SWE-bench Pro","domain":"Coding & SWE","useCases":["coding"],"datasetUrl":"https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro","leaderboardUrl":"https://huggingface.co/api/datasets/ScaleAI/SWE-bench_Pro/leaderboard","lastModified":"2026-02-23T20:54:47.000Z","license":null,"submissions":31,"models":31,"health":{"participation":0.751,"discrimination":0.773,"freshness":1,"sourceQuality":0.62,"weight":0.775,"eligibility":"included"}},{"id":"mercor/apex-agents","atlasSlug":"apex-agents","name":"APEX-Agents","domain":"Agents & Tool Use","useCases":["agents","professional"],"datasetUrl":"https://huggingface.co/datasets/mercor/apex-agents","leaderboardUrl":"https://huggingface.co/api/datasets/mercor/apex-agents/leaderboard","lastModified":"2026-06-11T16:50:00.000Z","license":"cc-by-4.0","submissions":11,"models":11,"health":{"participation":0.538,"discrimination":0.831,"freshness":1,"sourceQuality":0.767,"weight":0.766,"eligibility":"included"}},{"id":"benchflow/skillsbench","atlasSlug":"skillsbench","name":"SkillsBench","domain":"Agents & Tool Use","useCases":["agents"],"datasetUrl":"https://huggingface.co/datasets/benchflow/skillsbench","leaderboardUrl":"https://huggingface.co/api/datasets/benchflow/skillsbench/leaderboard","lastModified":"2026-06-16T21:50:11.000Z","license":"apache-2.0","submissions":8,"models":8,"health":{"participation":0.476,"discrimination":0.74,"freshness":1,"sourceQuality":0.82,"weight":0.733,"eligibility":"included"}},{"id":"Idavidrein/gpqa","atlasSlug":"gpqa-gpqa-diamond","name":"GPQA","domain":"Science & Reasoning","useCases":["reasoning","science-health"],"datasetUrl":"https://huggingface.co/datasets/Idavidrein/gpqa","leaderboardUrl":"https://huggingface.co/api/datasets/Idavidrein/gpqa/leaderboard","lastModified":"2026-03-05T23:06:58.000Z","license":"cc-by-4.0","submissions":98,"models":77,"health":{"participation":0.944,"discrimination":0.76,"freshness":1,"sourceQuality":0.59,"weight":0.807,"eligibility":"included"}},{"id":"SWE-bench/SWE-bench_Verified","atlasSlug":"swe-bench-verified","name":"SWE-bench Verified","domain":"Coding & SWE","useCases":["coding"],"datasetUrl":"https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified","leaderboardUrl":"https://huggingface.co/api/datasets/SWE-bench/SWE-bench_Verified/leaderboard","lastModified":"2026-02-27T20:36:38.000Z","license":null,"submissions":65,"models":49,"health":{"participation":0.848,"discrimination":0.617,"freshness":1,"sourceQuality":0.567,"weight":0.738,"eligibility":"included"}},{"id":"InternScience/ResearchClawBench","atlasSlug":"researchclawbench","name":"ResearchClawBench","domain":"Agents & Tool Use","useCases":["agents","science-health"],"datasetUrl":"https://huggingface.co/datasets/InternScience/ResearchClawBench","leaderboardUrl":"https://huggingface.co/api/datasets/InternScience/ResearchClawBench/leaderboard","lastModified":"2026-07-15T04:48:55.000Z","license":"mit","submissions":7,"models":7,"health":{"participation":0.451,"discrimination":0.743,"freshness":1,"sourceQuality":0.58,"weight":0.664,"eligibility":"included"}},{"id":"llamaindex/ParseBench","atlasSlug":"parsebench","name":"ParseBench","domain":"Retrieval & RAG","useCases":["documents"],"datasetUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","leaderboardUrl":"https://huggingface.co/api/datasets/llamaindex/ParseBench/leaderboard","lastModified":"2026-04-19T01:48:09.000Z","license":"apache-2.0","submissions":18,"models":18,"health":{"participation":0.638,"discrimination":0.806,"freshness":1,"sourceQuality":0.9,"weight":0.825,"eligibility":"included"}},{"id":"nvidia/compute-eval","atlasSlug":"nvidia-computeeval","name":"NVIDIA ComputeEval","domain":"Coding & SWE","useCases":["coding"],"datasetUrl":"https://huggingface.co/datasets/nvidia/compute-eval","leaderboardUrl":"https://huggingface.co/api/datasets/nvidia/compute-eval/leaderboard","lastModified":"2026-04-27T22:53:04.000Z","license":"other","submissions":0,"models":0,"health":{"participation":0,"discrimination":0,"freshness":1,"sourceQuality":0,"weight":0,"eligibility":"insufficient-participation"}},{"id":"MathArena/aime_2026","atlasSlug":"aime-2026","name":"AIME 2026","domain":"Science & Reasoning","useCases":["reasoning"],"datasetUrl":"https://huggingface.co/datasets/MathArena/aime_2026","leaderboardUrl":"https://huggingface.co/api/datasets/MathArena/aime_2026/leaderboard","lastModified":"2026-05-15T17:06:34.000Z","license":"cc-by-nc-sa-4.0","submissions":17,"models":16,"health":{"participation":0.614,"discrimination":0.609,"freshness":1,"sourceQuality":0.725,"weight":0.722,"eligibility":"included"}},{"id":"harborframework/terminal-bench-2.0","atlasSlug":"terminal-bench-2-0","name":"Terminal-Bench 2.0","domain":"Coding & SWE","useCases":["coding","agents"],"datasetUrl":"https://huggingface.co/datasets/harborframework/terminal-bench-2.0","leaderboardUrl":"https://huggingface.co/api/datasets/harborframework/terminal-bench-2.0/leaderboard","lastModified":"2026-04-24T18:37:11.000Z","license":"apache-2.0","submissions":38,"models":37,"health":{"participation":0.788,"discrimination":0.773,"freshness":1,"sourceQuality":0.637,"weight":0.789,"eligibility":"included"}},{"id":"Delores-Lin/MDPBench","atlasSlug":"mdpbench","name":"MDPBench","domain":"Retrieval & RAG","useCases":["documents"],"datasetUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","leaderboardUrl":"https://huggingface.co/api/datasets/Delores-Lin/MDPBench/leaderboard","lastModified":"2026-07-10T02:56:11.000Z","license":"apache-2.0","submissions":12,"models":12,"health":{"participation":0.556,"discrimination":0.716,"freshness":1,"sourceQuality":0.9,"weight":0.774,"eligibility":"included"}},{"id":"ChrisHayduk/nanofold-public","atlasSlug":"nanofold-public","name":"NanoFold Public","domain":"Science & Reasoning","useCases":["science-health"],"datasetUrl":"https://huggingface.co/datasets/ChrisHayduk/nanofold-public","leaderboardUrl":"https://huggingface.co/api/datasets/ChrisHayduk/nanofold-public/leaderboard","lastModified":"2026-06-16T23:28:52.000Z","license":"cc-by-4.0","submissions":0,"models":0,"health":{"participation":0,"discrimination":0,"freshness":1,"sourceQuality":0,"weight":0,"eligibility":"insufficient-participation"}},{"id":"actava/chi-bench","atlasSlug":"chi-bench","name":"χ-Bench","domain":"Healthcare","useCases":["science-health","agents"],"datasetUrl":"https://huggingface.co/datasets/actava/chi-bench","leaderboardUrl":"https://huggingface.co/api/datasets/actava/chi-bench/leaderboard","lastModified":"2026-06-02T21:37:27.000Z","license":"apache-2.0","submissions":3,"models":3,"health":{"participation":0.3,"discrimination":0.72,"freshness":1,"sourceQuality":0.62,"weight":0.605,"eligibility":"included"}},{"id":"meituan-longcat/WBench","atlasSlug":"wbench","name":"WBench","domain":"Multimodal & Voice","useCases":["multimodal"],"datasetUrl":"https://huggingface.co/datasets/meituan-longcat/WBench","leaderboardUrl":"https://huggingface.co/api/datasets/meituan-longcat/WBench/leaderboard","lastModified":"2026-05-29T07:48:58.000Z","license":"mit","submissions":8,"models":8,"health":{"participation":0.476,"discrimination":0.688,"freshness":1,"sourceQuality":0.9,"weight":0.737,"eligibility":"included"}},{"id":"ARTPARK-IISc/Vaani-Benchmark-V1.0","atlasSlug":"vaani-benchmark","name":"Vaani Benchmark","domain":"Multimodal & Voice","useCases":["multimodal"],"datasetUrl":"https://huggingface.co/datasets/ARTPARK-IISc/Vaani-Benchmark-V1.0","leaderboardUrl":"https://huggingface.co/api/datasets/ARTPARK-IISc/Vaani-Benchmark-V1.0/leaderboard","lastModified":"2026-06-29T06:56:12.000Z","license":"cc-by-4.0","submissions":7,"models":7,"health":{"participation":0.451,"discrimination":0.731,"freshness":1,"sourceQuality":0.597,"weight":0.666,"eligibility":"included"}},{"id":"mteb/arguana","atlasSlug":"arguana","name":"ArguAna","domain":"Retrieval & RAG","useCases":["documents"],"datasetUrl":"https://huggingface.co/datasets/mteb/arguana","leaderboardUrl":"https://huggingface.co/api/datasets/mteb/arguana/leaderboard","lastModified":"2026-04-17T15:17:35.000Z","license":"cc-by-sa-4.0","submissions":3,"models":3,"health":{"participation":0.3,"discrimination":0.773,"freshness":1,"sourceQuality":0.513,"weight":0.588,"eligibility":"included"}},{"id":"hf-audio/open-asr-leaderboard","atlasSlug":"open-asr-leaderboard","name":"Open ASR Leaderboard","domain":"Multimodal & Voice","useCases":["multimodal"],"datasetUrl":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard","leaderboardUrl":"https://huggingface.co/api/datasets/hf-audio/open-asr-leaderboard/leaderboard","lastModified":"2026-06-26T13:12:28.000Z","license":null,"submissions":61,"models":61,"health":{"participation":0.894,"discrimination":0.899,"freshness":1,"sourceQuality":0.9,"weight":0.922,"eligibility":"included"}},{"id":"MMMU/MMMU_Pro","atlasSlug":"mmmu-mmmu-pro","name":"MMMU-Pro","domain":"Multimodal & Voice","useCases":["multimodal","reasoning"],"datasetUrl":"https://huggingface.co/datasets/MMMU/MMMU_Pro","leaderboardUrl":"https://huggingface.co/api/datasets/MMMU/MMMU_Pro/leaderboard","lastModified":"2026-07-10T20:36:10.000Z","license":"apache-2.0","submissions":9,"models":9,"health":{"participation":0.499,"discrimination":0.849,"freshness":1,"sourceQuality":0.573,"weight":0.702,"eligibility":"included"}},{"id":"likaixin/ScreenSpot-Pro","atlasSlug":"screenspot-pro","name":"ScreenSpot-Pro","domain":"Multimodal & Voice","useCases":["multimodal","agents"],"datasetUrl":"https://huggingface.co/datasets/likaixin/ScreenSpot-Pro","leaderboardUrl":"https://huggingface.co/api/datasets/likaixin/ScreenSpot-Pro/leaderboard","lastModified":"2026-03-18T12:37:25.000Z","license":"mit","submissions":22,"models":22,"health":{"participation":0.679,"discrimination":0.957,"freshness":1,"sourceQuality":0.856,"weight":0.864,"eligibility":"included"}},{"id":"LEXam-Benchmark/LEXam","atlasSlug":"lexam","name":"LEXam","domain":"Legal","useCases":["professional"],"datasetUrl":"https://huggingface.co/datasets/LEXam-Benchmark/LEXam","leaderboardUrl":"https://huggingface.co/api/datasets/LEXam-Benchmark/LEXam/leaderboard","lastModified":"2026-05-21T14:40:51.000Z","license":"cc-by-4.0","submissions":9,"models":9,"health":{"participation":0.499,"discrimination":0.73,"freshness":1,"sourceQuality":0.9,"weight":0.757,"eligibility":"included"}},{"id":"mercor/ACE","atlasSlug":"ace-benchmark","name":"ACE","domain":"Agents & Tool Use","useCases":["agents"],"datasetUrl":"https://huggingface.co/datasets/mercor/ACE","leaderboardUrl":"https://huggingface.co/api/datasets/mercor/ACE/leaderboard","lastModified":"2026-04-13T16:39:42.000Z","license":"cc-by-4.0","submissions":0,"models":0,"health":{"participation":0,"discrimination":0,"freshness":1,"sourceQuality":0,"weight":0,"eligibility":"insufficient-participation"}},{"id":"mercor/APEX-v1-extended","atlasSlug":"apex-v1-extended","name":"APEX v1 Extended","domain":"Agents & Tool Use","useCases":["agents","professional"],"datasetUrl":"https://huggingface.co/datasets/mercor/APEX-v1-extended","leaderboardUrl":"https://huggingface.co/api/datasets/mercor/APEX-v1-extended/leaderboard","lastModified":"2026-04-22T17:00:31.000Z","license":"cc-by-4.0","submissions":2,"models":2,"health":{"participation":0.238,"discrimination":0.665,"freshness":1,"sourceQuality":0.9,"weight":0,"eligibility":"insufficient-participation"}},{"id":"VLABench/vlabench_primitive_ft_lerobot_video","atlasSlug":"vlabench","name":"VLABench","domain":"Multimodal & Voice","useCases":["multimodal","agents"],"datasetUrl":"https://huggingface.co/datasets/VLABench/vlabench_primitive_ft_lerobot_video","leaderboardUrl":"https://huggingface.co/api/datasets/VLABench/vlabench_primitive_ft_lerobot_video/leaderboard","lastModified":"2026-04-23T12:08:51.000Z","license":"mit","submissions":4,"models":4,"health":{"participation":0.349,"discrimination":0.714,"freshness":1,"sourceQuality":0.9,"weight":0.688,"eligibility":"included"}},{"id":"FutureMa/EvasionBench","atlasSlug":"evasionbench","name":"EvasionBench","domain":"Finance","useCases":["professional"],"datasetUrl":"https://huggingface.co/datasets/FutureMa/EvasionBench","leaderboardUrl":"https://huggingface.co/api/datasets/FutureMa/EvasionBench/leaderboard","lastModified":"2026-02-19T12:49:42.000Z","license":"apache-2.0","submissions":4,"models":4,"health":{"participation":0.349,"discrimination":0.708,"freshness":1,"sourceQuality":0.62,"weight":0.625,"eligibility":"included"}},{"id":"tiiuae/PBench","atlasSlug":"pbench","name":"PBench","domain":"Multimodal & Voice","useCases":["multimodal"],"datasetUrl":"https://huggingface.co/datasets/tiiuae/PBench","leaderboardUrl":"https://huggingface.co/api/datasets/tiiuae/PBench/leaderboard","lastModified":"2026-05-11T14:51:08.000Z","license":null,"submissions":0,"models":0,"health":{"participation":0,"discrimination":0,"freshness":1,"sourceQuality":0,"weight":0,"eligibility":"insufficient-participation"}},{"id":"MathArena/hmmt_feb_2026","atlasSlug":"hmmt-feb-2026","name":"HMMT February 2026","domain":"Science & Reasoning","useCases":["reasoning"],"datasetUrl":"https://huggingface.co/datasets/MathArena/hmmt_feb_2026","leaderboardUrl":"https://huggingface.co/api/datasets/MathArena/hmmt_feb_2026/leaderboard","lastModified":"2026-05-15T17:07:20.000Z","license":"cc-by-nc-sa-4.0","submissions":14,"models":14,"health":{"participation":0.587,"discrimination":0.711,"freshness":1,"sourceQuality":0.75,"weight":0.748,"eligibility":"included"}},{"id":"mteb/BRIGHT","atlasSlug":"bright","name":"BRIGHT","domain":"Retrieval & RAG","useCases":["documents","reasoning"],"datasetUrl":"https://huggingface.co/datasets/mteb/BRIGHT","leaderboardUrl":"https://huggingface.co/api/datasets/mteb/BRIGHT/leaderboard","lastModified":"2026-04-02T16:24:21.000Z","license":"cc-by-4.0","submissions":1,"models":1,"health":{"participation":0.15,"discrimination":0.65,"freshness":1,"sourceQuality":0.46,"weight":0,"eligibility":"insufficient-participation"}},{"id":"collinear-ai/yc-bench","atlasSlug":"yc-bench","name":"YC-Bench","domain":"Agents & Tool Use","useCases":["agents","professional"],"datasetUrl":"https://huggingface.co/datasets/collinear-ai/yc-bench","leaderboardUrl":"https://huggingface.co/api/datasets/collinear-ai/yc-bench/leaderboard","lastModified":"2026-03-23T18:17:49.000Z","license":"apache-2.0","submissions":12,"models":12,"health":{"participation":0.556,"discrimination":0.874,"freshness":1,"sourceQuality":0.582,"weight":0.729,"eligibility":"included"}},{"id":"internlm/WildClawBench","atlasSlug":"wildclawbench","name":"WildClawBench","domain":"Agents & Tool Use","useCases":["agents"],"datasetUrl":"https://huggingface.co/datasets/internlm/WildClawBench","leaderboardUrl":"https://huggingface.co/api/datasets/internlm/WildClawBench/leaderboard","lastModified":"2026-05-15T04:10:55.000Z","license":"mit","submissions":14,"models":13,"health":{"participation":0.572,"discrimination":0.814,"freshness":1,"sourceQuality":0.602,"weight":0.727,"eligibility":"included"}},{"id":"claw-eval/Claw-Eval","atlasSlug":"claw-eval","name":"Claw-Eval","domain":"Agents & Tool Use","useCases":["agents"],"datasetUrl":"https://huggingface.co/datasets/claw-eval/Claw-Eval","leaderboardUrl":"https://huggingface.co/api/datasets/claw-eval/Claw-Eval/leaderboard","lastModified":"2026-05-08T14:44:56.000Z","license":"mit","submissions":19,"models":18,"health":{"participation":0.638,"discrimination":0.648,"freshness":1,"sourceQuality":0.744,"weight":0.745,"eligibility":"included"}},{"id":"MME-Benchmarks/Video-MME-v2","atlasSlug":"video-mme","name":"Video-MME v2","domain":"Multimodal & Voice","useCases":["multimodal"],"datasetUrl":"https://huggingface.co/datasets/MME-Benchmarks/Video-MME-v2","leaderboardUrl":"https://huggingface.co/api/datasets/MME-Benchmarks/Video-MME-v2/leaderboard","lastModified":"2026-06-11T09:26:28.000Z","license":"mit","submissions":7,"models":5,"health":{"participation":0.388,"discrimination":0.502,"freshness":1,"sourceQuality":0.672,"weight":0.602,"eligibility":"included"}},{"id":"crosbylegal/RedlineBench","atlasSlug":"redlinebench","name":"RedlineBench","domain":"Legal","useCases":["professional","agents"],"datasetUrl":"https://huggingface.co/datasets/crosbylegal/RedlineBench","leaderboardUrl":"https://huggingface.co/api/datasets/crosbylegal/RedlineBench/leaderboard","lastModified":"2026-06-18T14:40:28.000Z","license":"cc-by-4.0","submissions":5,"models":5,"health":{"participation":0.388,"discrimination":0.682,"freshness":1,"sourceQuality":0.484,"weight":0.598,"eligibility":"included"}}],"models":[{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","organization":"moonshotai","parameters":1058589420528,"scoreCount":16,"useCases":{"reasoning":{"score":85.4,"coverage":0.774,"confidence":0.599,"confidenceLabel":"moderate","benchmarks":6},"coding":{"score":49.5,"coverage":1,"confidence":0.792,"confidenceLabel":"strong","benchmarks":3},"agents":{"score":29.8,"coverage":0.559,"confidence":0.568,"confidenceLabel":"moderate","benchmarks":6},"documents":{"score":81.8,"coverage":0.271,"confidence":0.117,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":43.3,"coverage":0.43,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":59.6,"coverage":0.789,"confidence":0.386,"confidenceLabel":"directional","benchmarks":3},"multimodal":{"score":58.6,"coverage":0.252,"confidence":0.183,"confidenceLabel":"directional","benchmarks":2}}},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","organization":"Qwen","parameters":403397928944,"scoreCount":14,"useCases":{"reasoning":{"score":84.5,"coverage":0.657,"confidence":0.567,"confidenceLabel":"moderate","benchmarks":5},"coding":{"score":75,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":41.1,"coverage":0.668,"confidence":0.558,"confidenceLabel":"moderate","benchmarks":7},"professional":{"score":24.9,"coverage":0.43,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":66.3,"coverage":0.789,"confidence":0.386,"confidenceLabel":"directional","benchmarks":3},"multimodal":{"score":47.7,"coverage":0.283,"confidence":0.189,"confidenceLabel":"directional","benchmarks":2}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek-V4-Pro","organization":"deepseek-ai","parameters":861608274846,"scoreCount":13,"useCases":{"reasoning":{"score":84.2,"coverage":0.53,"confidence":0.422,"confidenceLabel":"moderate","benchmarks":4},"coding":{"score":83.4,"coverage":1,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":52,"coverage":0.631,"confidence":0.549,"confidenceLabel":"moderate","benchmarks":7},"professional":{"score":54.5,"coverage":0.21,"confidence":0.071,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":56.2,"coverage":1,"confidence":0.588,"confidenceLabel":"moderate","benchmarks":4}}},{"id":"moonshotai/Kimi-K2.6","name":"Kimi-K2.6","organization":"moonshotai","parameters":1058589420528,"scoreCount":13,"useCases":{"reasoning":{"score":97.6,"coverage":0.626,"confidence":0.412,"confidenceLabel":"moderate","benchmarks":5},"coding":{"score":88.2,"coverage":1,"confidence":0.52,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":61.7,"coverage":0.539,"confidence":0.508,"confidenceLabel":"moderate","benchmarks":6},"professional":{"score":45.5,"coverage":0.21,"confidence":0.071,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":80.3,"coverage":1,"confidence":0.555,"confidenceLabel":"moderate","benchmarks":4},"multimodal":{"score":100,"coverage":0.135,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","organization":"zai-org","parameters":753864139008,"scoreCount":12,"useCases":{"reasoning":{"score":66.7,"coverage":0.51,"confidence":0.371,"confidenceLabel":"directional","benchmarks":4},"coding":{"score":90.1,"coverage":0.679,"confidence":0.286,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":84.3,"coverage":0.631,"confidence":0.542,"confidenceLabel":"moderate","benchmarks":7},"professional":{"score":72.7,"coverage":0.21,"confidence":0.071,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":87,"coverage":1,"confidence":0.555,"confidenceLabel":"moderate","benchmarks":4}}},{"id":"zai-org/GLM-5","name":"GLM-5","organization":"zai-org","parameters":753864139008,"scoreCount":11,"useCases":{"reasoning":{"score":80.5,"coverage":0.657,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":5},"coding":{"score":76.6,"coverage":0.663,"confidence":0.389,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":63.7,"coverage":0.381,"confidence":0.448,"confidenceLabel":"moderate","benchmarks":4},"professional":{"score":61.8,"coverage":0.43,"confidence":0.225,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":81.4,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6-27B","organization":"Qwen","parameters":27781427952,"scoreCount":10,"useCases":{"reasoning":{"score":66.8,"coverage":0.774,"confidence":0.51,"confidenceLabel":"moderate","benchmarks":6},"coding":{"score":72.2,"coverage":1,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":58.4,"coverage":0.192,"confidence":0.127,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":66.7,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},"multimodal":{"score":62.5,"coverage":0.135,"confidence":0.053,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6-35B-A3B","organization":"Qwen","parameters":35951822704,"scoreCount":10,"useCases":{"reasoning":{"score":54.2,"coverage":0.774,"confidence":0.51,"confidenceLabel":"moderate","benchmarks":6},"coding":{"score":55.8,"coverage":1,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":69.4,"coverage":0.1,"confidence":0.046,"confidenceLabel":"directional","benchmarks":1},"documents":{"score":17.7,"coverage":0.289,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":49.3,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},"multimodal":{"score":50,"coverage":0.135,"confidence":0.053,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5-27B","organization":"Qwen","parameters":27781427952,"scoreCount":9,"useCases":{"reasoning":{"score":57.4,"coverage":0.774,"confidence":0.629,"confidenceLabel":"moderate","benchmarks":6},"coding":{"score":53.9,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":76.3,"coverage":0.209,"confidence":0.133,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":76.6,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},"multimodal":{"score":69.4,"coverage":0.302,"confidence":0.159,"confidenceLabel":"directional","benchmarks":2}}},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","organization":"XiaomiMiMo","parameters":1023244718976,"scoreCount":9,"useCases":{"reasoning":{"score":66,"coverage":0.53,"confidence":0.422,"confidenceLabel":"moderate","benchmarks":4},"coding":{"score":85.4,"coverage":1,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":78.6,"coverage":0.286,"confidence":0.28,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":50.9,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","organization":"MiniMaxAI","parameters":228703644928,"scoreCount":8,"useCases":{"reasoning":{"score":54.8,"coverage":0.412,"confidence":0.292,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":65.4,"coverage":0.657,"confidence":0.398,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":19,"coverage":0.281,"confidence":0.285,"confidenceLabel":"directional","benchmarks":3},"professional":{"score":24.2,"coverage":0.43,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":44.4,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","name":"NVIDIA-Nemotron-3-Super-120B-A12B-BF16","organization":"nvidia","parameters":123611012096,"scoreCount":8,"useCases":{"reasoning":{"score":51.5,"coverage":0.657,"confidence":0.536,"confidenceLabel":"moderate","benchmarks":5},"coding":{"score":19.8,"coverage":0.663,"confidence":0.282,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":15.7,"coverage":0.194,"confidence":0.155,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"stepfun-ai/Step-3.5-Flash","name":"Step-3.5-Flash","organization":"stepfun-ai","parameters":199384301376,"scoreCount":8,"useCases":{"reasoning":{"score":72,"coverage":0.657,"confidence":0.506,"confidenceLabel":"moderate","benchmarks":5},"coding":{"score":65.2,"coverage":0.663,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":34.7,"coverage":0.192,"confidence":0.118,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":52.8,"coverage":0.557,"confidence":0.172,"confidenceLabel":"directional","benchmarks":2}}},{"id":"tencent/Hy3","name":"Hy3","organization":"tencent","parameters":298786155776,"scoreCount":8,"useCases":{"reasoning":{"score":95.5,"coverage":0.265,"confidence":0.149,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":79.9,"coverage":0.657,"confidence":0.313,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":85,"coverage":0.281,"confidence":0.231,"confidenceLabel":"directional","benchmarks":3},"professional":{"score":70,"coverage":0.22,"confidence":0.068,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":95.5,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","organization":"zai-org","parameters":358337791296,"scoreCount":8,"useCases":{"reasoning":{"score":68.6,"coverage":0.265,"confidence":0.141,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":47.3,"coverage":0.663,"confidence":0.405,"confidenceLabel":"moderate","benchmarks":2},"agents":{"score":22.1,"coverage":0.289,"confidence":0.327,"confidenceLabel":"directional","benchmarks":3},"professional":{"score":38.9,"coverage":0.61,"confidence":0.422,"confidenceLabel":"moderate","benchmarks":3},"science-health":{"score":68.6,"coverage":0.557,"confidence":0.205,"confidenceLabel":"directional","benchmarks":2}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek-V4-Flash","organization":"deepseek-ai","parameters":158069433298,"scoreCount":7,"useCases":{"reasoning":{"score":80.2,"coverage":0.412,"confidence":0.279,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":83.9,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":39.4,"coverage":0.287,"confidence":0.317,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":72.4,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"MiniMaxAI/MiniMax-M2.1","name":"MiniMax-M2.1","organization":"MiniMaxAI","parameters":228703644928,"scoreCount":7,"useCases":{"reasoning":{"score":60.5,"coverage":0.412,"confidence":0.338,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":29.2,"coverage":1,"confidence":0.797,"confidenceLabel":"strong","benchmarks":3},"agents":{"score":16.7,"coverage":0.1,"confidence":0.071,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":33.3,"coverage":0.18,"confidence":0.066,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":38.7,"coverage":0.557,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2}}},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","organization":"MiniMaxAI","parameters":427040140160,"scoreCount":7,"useCases":{"coding":{"score":91.8,"coverage":0.657,"confidence":0.281,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":81.7,"coverage":0.376,"confidence":0.376,"confidenceLabel":"directional","benchmarks":4},"professional":{"score":90.4,"coverage":0.43,"confidence":0.171,"confidenceLabel":"directional","benchmarks":2},"multimodal":{"score":75,"coverage":0.116,"confidence":0.044,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5-122B-A10B","organization":"Qwen","parameters":125086497008,"scoreCount":7,"useCases":{"reasoning":{"score":81.8,"coverage":0.412,"confidence":0.31,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":56.2,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":57.4,"coverage":0.301,"confidence":0.244,"confidenceLabel":"directional","benchmarks":3},"professional":{"score":0,"coverage":0.21,"confidence":0.071,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":74.4,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},"multimodal":{"score":100,"coverage":0.167,"confidence":0.059,"confidenceLabel":"directional","benchmarks":1}}},{"id":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","name":"MiniMax-M3-MXFP4-Mixed-CT-AutoRound","organization":"INCModelSharing","parameters":233489984384,"scoreCount":6,"useCases":{"coding":{"score":91.8,"coverage":0.657,"confidence":0.281,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":89.7,"coverage":0.283,"confidence":0.208,"confidenceLabel":"directional","benchmarks":3},"professional":{"score":90.4,"coverage":0.43,"confidence":0.171,"confidenceLabel":"directional","benchmarks":2},"multimodal":{"score":75,"coverage":0.116,"confidence":0.044,"confidenceLabel":"directional","benchmarks":1}}},{"id":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","name":"MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","organization":"INCModelSharing","parameters":233690524544,"scoreCount":6,"useCases":{"coding":{"score":91.8,"coverage":0.657,"confidence":0.281,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":89.7,"coverage":0.283,"confidence":0.208,"confidenceLabel":"directional","benchmarks":3},"professional":{"score":90.4,"coverage":0.43,"confidence":0.171,"confidenceLabel":"directional","benchmarks":2},"multimodal":{"score":75,"coverage":0.116,"confidence":0.044,"confidenceLabel":"directional","benchmarks":1}}},{"id":"internlm/Intern-S2-Preview","name":"Intern-S2-Preview","organization":"internlm","parameters":36098254656,"scoreCount":6,"useCases":{"reasoning":{"score":72.3,"coverage":0.519,"confidence":0.418,"confidenceLabel":"moderate","benchmarks":4},"coding":{"score":22.9,"coverage":0.321,"confidence":0.109,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":41.7,"coverage":0.092,"confidence":0.047,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":27.5,"coverage":0.275,"confidence":0.076,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":75,"coverage":0.135,"confidence":0.053,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openai/gpt-oss-120b","name":"gpt-oss-120b","organization":"openai","parameters":120412337472,"scoreCount":6,"useCases":{"reasoning":{"score":47.8,"coverage":0.412,"confidence":0.31,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":10.9,"coverage":0.657,"confidence":0.402,"confidenceLabel":"moderate","benchmarks":2},"professional":{"score":75,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":33.2,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"openai/gpt-oss-20b","name":"gpt-oss-20b","organization":"openai","parameters":21511953984,"scoreCount":6,"useCases":{"reasoning":{"score":48.5,"coverage":0.521,"confidence":0.462,"confidenceLabel":"moderate","benchmarks":4},"coding":{"score":14.6,"coverage":0.321,"confidence":0.109,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":25,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":25.3,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","organization":"zai-org","parameters":753329940480,"scoreCount":6,"useCases":{"reasoning":{"score":100,"coverage":0.265,"confidence":0.134,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":96.7,"coverage":0.337,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":76.3,"coverage":0.16,"confidence":0.116,"confidenceLabel":"directional","benchmarks":2},"professional":{"score":50,"coverage":0.172,"confidence":0.06,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":100,"coverage":0.789,"confidence":0.358,"confidenceLabel":"directional","benchmarks":3}}},{"id":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","name":"NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","organization":"exolabs","parameters":120668707840,"scoreCount":5,"useCases":{"reasoning":{"score":60,"coverage":0.412,"confidence":0.25,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":19.8,"coverage":0.663,"confidence":0.282,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":30.6,"coverage":0.1,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","name":"NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","organization":"exolabs","parameters":120668707840,"scoreCount":5,"useCases":{"reasoning":{"score":60,"coverage":0.412,"confidence":0.25,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":19.8,"coverage":0.663,"confidence":0.282,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":30.6,"coverage":0.1,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","name":"NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","organization":"exolabs","parameters":120668707840,"scoreCount":5,"useCases":{"reasoning":{"score":60,"coverage":0.412,"confidence":0.25,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":19.8,"coverage":0.663,"confidence":0.282,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":30.6,"coverage":0.1,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","organization":"MiniMaxAI","parameters":228703644928,"scoreCount":5,"useCases":{"coding":{"score":75.1,"coverage":0.679,"confidence":0.319,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":29.5,"coverage":0.379,"confidence":0.46,"confidenceLabel":"moderate","benchmarks":4}}},{"id":"openpangu/openPangu-2.0-Flash","name":"openPangu-2.0-Flash","organization":"openpangu","parameters":100136311993,"scoreCount":5,"useCases":{"reasoning":{"score":53.3,"coverage":0.254,"confidence":0.146,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":20.8,"coverage":0.321,"confidence":0.109,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":39.6,"coverage":0.186,"confidence":0.125,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":59.2,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","name":"NVIDIA-Nemotron-3-Super-120B-A12B-BF16","organization":"RedHatAI","parameters":123611012096,"scoreCount":5,"useCases":{"reasoning":{"score":60,"coverage":0.412,"confidence":0.25,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":19.8,"coverage":0.663,"confidence":0.282,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":30.6,"coverage":0.1,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","organization":"deepseek-ai","parameters":684531386000,"scoreCount":4,"useCases":{"reasoning":{"score":45,"coverage":0.399,"confidence":0.303,"confidenceLabel":"directional","benchmarks":3},"professional":{"score":62.5,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":21.1,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-4.1-8b","name":"granite-4.1-8b","organization":"ibm-granite","parameters":8791592960,"scoreCount":4,"useCases":{"reasoning":{"score":40.1,"coverage":0.508,"confidence":0.419,"confidenceLabel":"moderate","benchmarks":4},"science-health":{"score":14.5,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inclusionAI/Ring-2.6-1T","name":"Ring-2.6-1T","organization":"inclusionAI","parameters":1025657871744,"scoreCount":4,"useCases":{"reasoning":{"score":84.3,"coverage":0.254,"confidence":0.131,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":59.4,"coverage":0.321,"confidence":0.098,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":64.7,"coverage":0.094,"confidence":0.04,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":88.2,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"MiniMaxAI/MiniMax-M2","name":"MiniMax-M2","organization":"MiniMaxAI","parameters":228703644928,"scoreCount":4,"useCases":{"reasoning":{"score":47,"coverage":0.278,"confidence":0.153,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":24.6,"coverage":0.663,"confidence":0.405,"confidenceLabel":"moderate","benchmarks":2},"agents":{"score":19.4,"coverage":0.1,"confidence":0.071,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":10,"coverage":0.275,"confidence":0.076,"confidenceLabel":"directional","benchmarks":1}}},{"id":"moonshotai/Kimi-K2-Instruct","name":"Kimi-K2-Instruct","organization":"moonshotai","parameters":1026470731056,"scoreCount":4,"useCases":{"reasoning":{"score":75.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1},"coding":{"score":12,"coverage":0.679,"confidence":0.495,"confidenceLabel":"moderate","benchmarks":2},"agents":{"score":16.9,"coverage":0.197,"confidence":0.2,"confidenceLabel":"directional","benchmarks":2},"professional":{"score":20,"coverage":0.22,"confidence":0.106,"confidenceLabel":"directional","benchmarks":1}}},{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi-K2-Thinking","organization":"moonshotai","parameters":1058118284416,"scoreCount":4,"useCases":{"reasoning":{"score":66.5,"coverage":0.265,"confidence":0.149,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":43.4,"coverage":0.663,"confidence":0.405,"confidenceLabel":"moderate","benchmarks":2},"agents":{"score":43.1,"coverage":0.1,"confidence":0.071,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":66.5,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","organization":"nvidia","parameters":560524578816,"scoreCount":4,"useCases":{"reasoning":{"score":79.4,"coverage":0.412,"confidence":0.279,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":45.8,"coverage":0.321,"confidence":0.109,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":70.2,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","organization":"nvidia","parameters":335038821080,"scoreCount":4,"useCases":{"reasoning":{"score":81.6,"coverage":0.412,"confidence":0.279,"confidenceLabel":"directional","benchmarks":3},"coding":{"score":33.3,"coverage":0.321,"confidence":0.109,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":73.6,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"Qwen/Qwen3-30B-A3B-Thinking-2507","name":"Qwen3-30B-A3B-Thinking-2507","organization":"Qwen","parameters":30532122624,"scoreCount":4,"useCases":{"reasoning":{"score":35.3,"coverage":0.526,"confidence":0.598,"confidenceLabel":"moderate","benchmarks":4},"science-health":{"score":30.3,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"tencent/Hy3-preview","name":"Hy3-preview","organization":"tencent","parameters":298786155776,"scoreCount":4,"useCases":{"reasoning":{"score":66.6,"coverage":0.265,"confidence":0.149,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":70.9,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":77.8,"coverage":0.1,"confidence":0.046,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":66.6,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","organization":"XiaomiMiMo","parameters":310775040000,"scoreCount":4,"useCases":{"coding":{"score":76.2,"coverage":0.679,"confidence":0.319,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":57.9,"coverage":0.278,"confidence":0.272,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":33.3,"coverage":0.232,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/North-Mini-Code-1.0","name":"North-Mini-Code-1.0","organization":"CohereLabs","parameters":30484303872,"scoreCount":3,"useCases":{"coding":{"score":30.9,"coverage":1,"confidence":0.46,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":47.2,"coverage":0.1,"confidence":0.036,"confidenceLabel":"directional","benchmarks":1}}},{"id":"datalab-to/chandra-ocr-2","name":"chandra-ocr-2","organization":"datalab-to","parameters":5295564288,"scoreCount":3,"useCases":{"documents":{"score":86.2,"coverage":0.794,"confidence":0.526,"confidenceLabel":"moderate","benchmarks":3}}},{"id":"deepreinforce-ai/Ornith-1.0-35B","name":"Ornith-1.0-35B","organization":"deepreinforce-ai","parameters":664944,"scoreCount":3,"useCases":{"coding":{"score":58.5,"coverage":0.657,"confidence":0.313,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":76.5,"coverage":0.094,"confidence":0.045,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepreinforce-ai/Ornith-1.0-397B","name":"Ornith-1.0-397B","organization":"deepreinforce-ai","parameters":396802360816,"scoreCount":3,"useCases":{"coding":{"score":100,"coverage":0.657,"confidence":0.313,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":100,"coverage":0.094,"confidence":0.045,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepreinforce-ai/Ornith-1.0-9B","name":"Ornith-1.0-9B","organization":"deepreinforce-ai","parameters":1469680,"scoreCount":3,"useCases":{"coding":{"score":26.7,"coverage":0.657,"confidence":0.313,"confidenceLabel":"directional","benchmarks":2},"agents":{"score":58.8,"coverage":0.094,"confidence":0.045,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepseek-ai/DeepSeek-R1","name":"DeepSeek-R1","organization":"deepseek-ai","parameters":684531386000,"scoreCount":3,"useCases":{"reasoning":{"score":59.5,"coverage":0.281,"confidence":0.154,"confidenceLabel":"directional","benchmarks":2},"professional":{"score":100,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":27.6,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-4.1-30b","name":"granite-4.1-30b","organization":"ibm-granite","parameters":28865728512,"scoreCount":3,"useCases":{"reasoning":{"score":53.3,"coverage":0.399,"confidence":0.275,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":15.8,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-4.1-3b","name":"granite-4.1-3b","organization":"ibm-granite","parameters":3402836480,"scoreCount":3,"useCases":{"reasoning":{"score":32.2,"coverage":0.399,"confidence":0.275,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":7.9,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inclusionAI/Ling-2.6-flash","name":"Ling-2.6-flash","organization":"inclusionAI","parameters":107494409216,"scoreCount":3,"useCases":{"reasoning":{"score":0,"coverage":0.245,"confidence":0.129,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":16.7,"coverage":0.321,"confidence":0.098,"confidenceLabel":"directional","benchmarks":1}}},{"id":"JetBrains/Mellum2-12B-A2.5B-Base","name":"Mellum2-12B-A2.5B-Base","organization":"JetBrains","parameters":12149923072,"scoreCount":3,"useCases":{"reasoning":{"score":28.1,"coverage":0.399,"confidence":0.218,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":5.9,"coverage":0.282,"confidence":0.061,"confidenceLabel":"directional","benchmarks":1}}},{"id":"JetBrains/Mellum2-12B-A2.5B-Base-Pretrain","name":"Mellum2-12B-A2.5B-Base-Pretrain","organization":"JetBrains","parameters":12149923072,"scoreCount":3,"useCases":{"reasoning":{"score":28.1,"coverage":0.399,"confidence":0.218,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":5.9,"coverage":0.282,"confidence":0.061,"confidenceLabel":"directional","benchmarks":1}}},{"id":"LGAI-EXAONE/EXAONE-4.5-33B","name":"EXAONE-4.5-33B","organization":"LGAI-EXAONE","parameters":34350097664,"scoreCount":3,"useCases":{"reasoning":{"score":54.6,"coverage":0.402,"confidence":0.276,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":42.8,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"LGAI-EXAONE/K-EXAONE-236B-A23B","name":"K-EXAONE-236B-A23B","organization":"LGAI-EXAONE","parameters":237099669632,"scoreCount":3,"useCases":{"reasoning":{"score":48.6,"coverage":0.412,"confidence":0.279,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":26.8,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2}}},{"id":"lightonai/LightOnOCR-2-1B","name":"LightOnOCR-2-1B","organization":"lightonai","parameters":1005647872,"scoreCount":3,"useCases":{"documents":{"score":47.5,"coverage":0.794,"confidence":0.515,"confidenceLabel":"moderate","benchmarks":3}}},{"id":"MuVeraAI/Laguna-XS.2","name":"Laguna-XS.2","organization":"MuVeraAI","parameters":33442617088,"scoreCount":3,"useCases":{"coding":{"score":26.4,"coverage":1,"confidence":0.52,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":22.2,"coverage":0.1,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1}}},{"id":"opendatalab/MinerU2.5-2509-1.2B","name":"MinerU2.5-2509-1.2B","organization":"opendatalab","parameters":1156026624,"scoreCount":3,"useCases":{"documents":{"score":9.6,"coverage":0.794,"confidence":0.546,"confidenceLabel":"moderate","benchmarks":3}}},{"id":"poolside/Laguna-M.1","name":"Laguna-M.1","organization":"poolside","parameters":225795725568,"scoreCount":3,"useCases":{"coding":{"score":55.8,"coverage":1,"confidence":0.52,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":61.1,"coverage":0.1,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1}}},{"id":"poolside/Laguna-XS-2.1","name":"Laguna-XS-2.1","organization":"poolside","parameters":33442617088,"scoreCount":3,"useCases":{"coding":{"score":43.8,"coverage":1,"confidence":0.52,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":52.8,"coverage":0.1,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1}}},{"id":"poolside/Laguna-XS.2","name":"Laguna-XS.2","organization":"poolside","parameters":33442617088,"scoreCount":3,"useCases":{"coding":{"score":37.3,"coverage":1,"confidence":0.52,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":43.1,"coverage":0.1,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-4B-Thinking-2507","name":"Qwen3-4B-Thinking-2507","organization":"Qwen","parameters":4022468096,"scoreCount":3,"useCases":{"reasoning":{"score":13,"coverage":0.379,"confidence":0.363,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":23.7,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen3-Coder-480B-A35B-Instruct","organization":"Qwen","parameters":480154875392,"scoreCount":3,"useCases":{"coding":{"score":11.1,"coverage":0.679,"confidence":0.495,"confidenceLabel":"moderate","benchmarks":2},"agents":{"score":5.6,"coverage":0.1,"confidence":0.071,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":66.7,"coverage":0.18,"confidence":0.066,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-Coder-Next","name":"Qwen3-Coder-Next","organization":"Qwen","parameters":79674391296,"scoreCount":3,"useCases":{"coding":{"score":38.1,"coverage":1,"confidence":0.606,"confidenceLabel":"moderate","benchmarks":3},"agents":{"score":50,"coverage":0.1,"confidence":0.046,"confidenceLabel":"directional","benchmarks":1}}},{"id":"rednote-hilab/dots.mocr","name":"dots.mocr","organization":"rednote-hilab","parameters":3039179264,"scoreCount":3,"useCases":{"documents":{"score":83,"coverage":0.794,"confidence":0.515,"confidenceLabel":"moderate","benchmarks":3}}},{"id":"skt/A.X-K1","name":"A.X-K1","organization":"skt","parameters":518983059456,"scoreCount":3,"useCases":{"reasoning":{"score":40.1,"coverage":0.412,"confidence":0.25,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":18.5,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"tiiuae/Falcon-OCR","name":"Falcon-OCR","organization":"tiiuae","parameters":269944416,"scoreCount":3,"useCases":{"documents":{"score":42.4,"coverage":0.794,"confidence":0.526,"confidenceLabel":"moderate","benchmarks":3}}},{"id":"zai-org/GLM-4.5-Air","name":"GLM-4.5-Air","organization":"zai-org","parameters":110468824832,"scoreCount":3,"useCases":{"reasoning":{"score":37.4,"coverage":0.412,"confidence":0.366,"confidenceLabel":"directional","benchmarks":3},"science-health":{"score":14.7,"coverage":0.557,"confidence":0.284,"confidenceLabel":"directional","benchmarks":2}}},{"id":"zai-org/GLM-4.6","name":"GLM-4.6","organization":"zai-org","parameters":356785898816,"scoreCount":3,"useCases":{"coding":{"score":4.2,"coverage":0.679,"confidence":0.495,"confidenceLabel":"moderate","benchmarks":2},"agents":{"score":9.2,"coverage":0.197,"confidence":0.2,"confidenceLabel":"directional","benchmarks":2},"professional":{"score":10,"coverage":0.22,"confidence":0.106,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","organization":"zai-org","parameters":31221488576,"scoreCount":3,"useCases":{"reasoning":{"score":25.4,"coverage":0.265,"confidence":0.134,"confidenceLabel":"directional","benchmarks":2},"coding":{"score":2.1,"coverage":0.321,"confidence":0.109,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":25.4,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}}},{"id":"zai-org/GLM-OCR","name":"GLM-OCR","organization":"zai-org","parameters":1325258240,"scoreCount":3,"useCases":{"documents":{"score":13.4,"coverage":0.794,"confidence":0.515,"confidenceLabel":"moderate","benchmarks":3}}},{"id":"baidu/Qianfan-OCR","name":"Qianfan-OCR","organization":"baidu","parameters":4741408256,"scoreCount":2,"useCases":{"documents":{"score":38.7,"coverage":0.524,"confidence":0.254,"confidenceLabel":"directional","benchmarks":2}}},{"id":"datalab-to/surya-ocr-2","name":"surya-ocr-2","organization":"datalab-to","parameters":686154304,"scoreCount":2,"useCases":{"documents":{"score":74.2,"coverage":0.524,"confidence":0.264,"confidenceLabel":"directional","benchmarks":2}}},{"id":"deepseek-ai/DeepSeek-OCR","name":"DeepSeek-OCR","organization":"deepseek-ai","parameters":3336106240,"scoreCount":2,"useCases":{"documents":{"score":11.5,"coverage":0.506,"confidence":0.274,"confidenceLabel":"directional","benchmarks":2}}},{"id":"deepseek-ai/DeepSeek-OCR-2","name":"DeepSeek-OCR-2","organization":"deepseek-ai","parameters":3389119360,"scoreCount":2,"useCases":{"documents":{"score":19.3,"coverage":0.524,"confidence":0.28,"confidenceLabel":"directional","benchmarks":2}}},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek-R1-0528","organization":"deepseek-ai","parameters":684531386000,"scoreCount":2,"useCases":{"reasoning":{"score":66.2,"coverage":0.281,"confidence":0.177,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":39.5,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"infly/Infinity-Parser2-Pro","name":"Infinity-Parser2-Pro","organization":"infly","parameters":35107181936,"scoreCount":2,"useCases":{"documents":{"score":96.8,"coverage":0.524,"confidence":0.254,"confidenceLabel":"directional","benchmarks":2}}},{"id":"InternScience/Agents-A1","name":"Agents-A1","organization":"InternScience","parameters":35107181936,"scoreCount":2,"useCases":{"reasoning":{"score":86.4,"coverage":0.24,"confidence":0.121,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":75,"coverage":0.275,"confidence":0.068,"confidenceLabel":"directional","benchmarks":1}}},{"id":"jdopensource/JoyAI-LLM-Flash","name":"JoyAI-LLM-Flash","organization":"jdopensource","parameters":49286094592,"scoreCount":2,"useCases":{"reasoning":{"score":56.2,"coverage":0.281,"confidence":0.154,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":34.2,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Llama-3.1-405B","name":"Llama-3.1-405B","organization":"meta-llama","parameters":405853388800,"scoreCount":2,"useCases":{"reasoning":{"score":73.8,"coverage":0.265,"confidence":0.175,"confidenceLabel":"directional","benchmarks":2}}},{"id":"meta-llama/Llama-3.2-90B-Vision-Instruct","name":"Llama-3.2-90B-Vision-Instruct","organization":"meta-llama","parameters":88593355323,"scoreCount":2,"useCases":{"reasoning":{"score":47.5,"coverage":0.252,"confidence":0.191,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":17.1,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"microsoft/Phi-3-medium-4k-instruct","name":"Phi-3-medium-4k-instruct","organization":"microsoft","parameters":13960238080,"scoreCount":2,"useCases":{"reasoning":{"score":56.3,"coverage":0.265,"confidence":0.175,"confidenceLabel":"directional","benchmarks":2}}},{"id":"microsoft/Phi-3-mini-4k-instruct","name":"Phi-3-mini-4k-instruct","organization":"microsoft","parameters":3821079552,"scoreCount":2,"useCases":{"reasoning":{"score":33.9,"coverage":0.265,"confidence":0.175,"confidenceLabel":"directional","benchmarks":2}}},{"id":"microsoft/Phi-3.5-mini-instruct","name":"Phi-3.5-mini-instruct","organization":"microsoft","parameters":3821079552,"scoreCount":2,"useCases":{"reasoning":{"score":40.3,"coverage":0.265,"confidence":0.179,"confidenceLabel":"directional","benchmarks":2}}},{"id":"microsoft/phi-4","name":"phi-4","organization":"microsoft","parameters":14659507200,"scoreCount":2,"useCases":{"reasoning":{"score":69.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":12.5,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Ministral-8B-Instruct-2410","name":"Ministral-8B-Instruct-2410","organization":"mistralai","parameters":8019808256,"scoreCount":2,"useCases":{"reasoning":{"score":23.7,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":0,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Voxtral-Mini-3B-2507","name":"Voxtral-Mini-3B-2507","organization":"mistralai","parameters":4676271104,"scoreCount":2,"useCases":{"multimodal":{"score":75.6,"coverage":0.307,"confidence":0.217,"confidenceLabel":"directional","benchmarks":2}}},{"id":"mteb/baseline-bm25s","name":"baseline-bm25s","organization":"mteb","parameters":null,"scoreCount":2,"useCases":{"documents":{"score":50,"coverage":0.206,"confidence":0.052,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openai/whisper-large-v3","name":"whisper-large-v3","organization":"openai","parameters":1543490560,"scoreCount":2,"useCases":{"multimodal":{"score":33.9,"coverage":0.307,"confidence":0.217,"confidenceLabel":"directional","benchmarks":2}}},{"id":"opendatalab/MinerU2.5-Pro-2605-1.2B","name":"MinerU2.5-Pro-2605-1.2B","organization":"opendatalab","parameters":1156026624,"scoreCount":2,"useCases":{"documents":{"score":73.3,"coverage":0.559,"confidence":0.337,"confidenceLabel":"directional","benchmarks":2}}},{"id":"Qwen/Qwen2-7B","name":"Qwen2-7B","organization":"Qwen","parameters":7615616512,"scoreCount":2,"useCases":{"reasoning":{"score":20.4,"coverage":0.265,"confidence":0.175,"confidenceLabel":"directional","benchmarks":2}}},{"id":"Qwen/Qwen2.5-VL-3B-Instruct","name":"Qwen2.5-VL-3B-Instruct","organization":"Qwen","parameters":3754622976,"scoreCount":2,"useCases":{"reasoning":{"score":0,"coverage":0.117,"confidence":0.05,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":14.3,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":7.9,"coverage":0.302,"confidence":0.208,"confidenceLabel":"directional","benchmarks":2}}},{"id":"Qwen/Qwen2.5-VL-72B-Instruct","name":"Qwen2.5-VL-72B-Instruct","organization":"Qwen","parameters":73410777344,"scoreCount":2,"useCases":{"reasoning":{"score":0,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":52.4,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":52.4,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-VL-7B-Instruct","name":"Qwen2.5-VL-7B-Instruct","organization":"Qwen","parameters":8292166656,"scoreCount":2,"useCases":{"reasoning":{"score":12.5,"coverage":0.117,"confidence":0.05,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":19.1,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":16.1,"coverage":0.302,"confidence":0.208,"confidenceLabel":"directional","benchmarks":2}}},{"id":"Qwen/Qwen3-235B-A22B","name":"Qwen3-235B-A22B","organization":"Qwen","parameters":235093634560,"scoreCount":2,"useCases":{"reasoning":{"score":65.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1},"coding":{"score":6.7,"coverage":0.337,"confidence":0.174,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-4B-Instruct-2507","name":"Qwen3-4B-Instruct-2507","organization":"Qwen","parameters":4022468096,"scoreCount":2,"useCases":{"reasoning":{"score":46.4,"coverage":0.281,"confidence":0.154,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":22.4,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen3-VL-8B-Instruct","organization":"Qwen","parameters":8767123696,"scoreCount":2,"useCases":{"documents":{"score":45.4,"coverage":0.559,"confidence":0.337,"confidenceLabel":"directional","benchmarks":2}}},{"id":"rednote-hilab/dots.ocr","name":"dots.ocr","organization":"rednote-hilab","parameters":3039179264,"scoreCount":2,"useCases":{"documents":{"score":55.5,"coverage":0.506,"confidence":0.274,"confidenceLabel":"directional","benchmarks":2}}},{"id":"stepfun-ai/Step-3.7-Flash","name":"Step-3.7-Flash","organization":"stepfun-ai","parameters":201365316160,"scoreCount":2,"useCases":{"reasoning":{"score":80,"coverage":0.131,"confidence":0.052,"confidenceLabel":"directional","benchmarks":1},"coding":{"score":70,"coverage":0.337,"confidence":0.112,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":80,"coverage":0.275,"confidence":0.076,"confidenceLabel":"directional","benchmarks":1}}},{"id":"XiaomiMiMo/MiMo-V2-Flash","name":"MiMo-V2-Flash","organization":"XiaomiMiMo","parameters":309785318400,"scoreCount":2,"useCases":{"reasoning":{"score":43.1,"coverage":0.265,"confidence":0.173,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":43.1,"coverage":0.557,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2}}},{"id":"zai-org/GLM-4.5","name":"GLM-4.5","organization":"zai-org","parameters":358337791296,"scoreCount":2,"useCases":{"reasoning":{"score":48.8,"coverage":0.278,"confidence":0.2,"confidenceLabel":"directional","benchmarks":2},"science-health":{"score":2.5,"coverage":0.275,"confidence":0.1,"confidenceLabel":"directional","benchmarks":1}}},{"id":"01-ai/Yi-1.5-34B-Chat","name":"Yi-1.5-34B-Chat","organization":"01-ai","parameters":34388917248,"scoreCount":1,"useCases":{"reasoning":{"score":45.3,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"01-ai/Yi-1.5-6B-Chat","name":"Yi-1.5-6B-Chat","organization":"01-ai","parameters":6061035520,"scoreCount":1,"useCases":{"reasoning":{"score":25.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"01-ai/Yi-1.5-9B-Chat","name":"Yi-1.5-9B-Chat","organization":"01-ai","parameters":8829407232,"scoreCount":1,"useCases":{"reasoning":{"score":38.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"01-ai/Yi-34B","name":"Yi-34B","organization":"01-ai","parameters":34388917248,"scoreCount":1,"useCases":{"reasoning":{"score":32.4,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"01-ai/Yi-6B","name":"Yi-6B","organization":"01-ai","parameters":6061035520,"scoreCount":1,"useCases":{"reasoning":{"score":10.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"01-ai/Yi-6B-Chat","name":"Yi-6B-Chat","organization":"01-ai","parameters":6061035520,"scoreCount":1,"useCases":{"reasoning":{"score":11.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"abacusai/Llama-3-Smaug-8B","name":"Llama-3-Smaug-8B","organization":"abacusai","parameters":8030261248,"scoreCount":1,"useCases":{"reasoning":{"score":20.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"abr-ai/niagara-19m-batch.en","name":"niagara-19m-batch.en","organization":"abr-ai","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":28.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"abr-ai/niagara-38m-batch.en","name":"niagara-38m-batch.en","organization":"abr-ai","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":36.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ACERobotics/kairos-sensenova-robot-4B-480P","name":"kairos-sensenova-robot-4B-480P","organization":"ACERobotics","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":14.3,"coverage":0.142,"confidence":0.085,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ai21labs/AI21-Jamba-Large-1.5","name":"AI21-Jamba-Large-1.5","organization":"ai21labs","parameters":398555145696,"scoreCount":1,"useCases":{"reasoning":{"score":41.7,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ATH-MaaS/Ovis2.6-80B-A3B","name":"Ovis2.6-80B-A3B","organization":"ATH-MaaS","parameters":80524245992,"scoreCount":1,"useCases":{"reasoning":{"score":25,"coverage":0.117,"confidence":0.05,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":25,"coverage":0.135,"confidence":0.053,"confidenceLabel":"directional","benchmarks":1}}},{"id":"AutoArk-AI/ARK-ASR-0.6B","name":"ARK-ASR-0.6B","organization":"AutoArk-AI","parameters":1299463168,"scoreCount":1,"useCases":{"multimodal":{"score":95,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"AutoArk-AI/ARK-ASR-3B","name":"ARK-ASR-3B","organization":"AutoArk-AI","parameters":4063438848,"scoreCount":1,"useCases":{"multimodal":{"score":100,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"AutoArk-AI/Audio8-ASR-0.1B","name":"Audio8-ASR-0.1B","organization":"AutoArk-AI","parameters":323990528,"scoreCount":1,"useCases":{"multimodal":{"score":72.5,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"baidu/ERNIE-4.5-21B-A3B-Base-PT","name":"ERNIE-4.5-21B-A3B-Base-PT","organization":"baidu","parameters":21825437888,"scoreCount":1,"useCases":{"reasoning":{"score":51.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"baidu/ERNIE-4.5-300B-A47B-Base-PT","name":"ERNIE-4.5-300B-A47B-Base-PT","organization":"baidu","parameters":299484163264,"scoreCount":1,"useCases":{"reasoning":{"score":67.6,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"baidu/ERNIE-4.5-300B-A47B-PT","name":"ERNIE-4.5-300B-A47B-PT","organization":"baidu","parameters":300474051776,"scoreCount":1,"useCases":{"reasoning":{"score":72.7,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"baidu/Unlimited-OCR","name":"Unlimited-OCR","organization":"baidu","parameters":3336106240,"scoreCount":1,"useCases":{"documents":{"score":29.4,"coverage":0.289,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1}}},{"id":"bharatgenai/Shrutam-HindiASR-1.0","name":"Shrutam-HindiASR-1.0","organization":"bharatgenai","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":100,"coverage":0.129,"confidence":0.056,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ByteDance-Seed/Seed-OSS-36B-Base","name":"Seed-OSS-36B-Base","organization":"ByteDance-Seed","parameters":36151104512,"scoreCount":1,"useCases":{"reasoning":{"score":61.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ByteDance-Seed/Seed-OSS-36B-Base-woSyn","name":"Seed-OSS-36B-Base-woSyn","organization":"ByteDance-Seed","parameters":36151104512,"scoreCount":1,"useCases":{"reasoning":{"score":56.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","name":"Seed-OSS-36B-Instruct","organization":"ByteDance-Seed","parameters":36151104512,"scoreCount":1,"useCases":{"reasoning":{"score":80.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ByteDance-Seed/UI-TARS-1.5-7B","name":"UI-TARS-1.5-7B","organization":"ByteDance-Seed","parameters":8292166656,"scoreCount":1,"useCases":{"agents":{"score":66.7,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":66.7,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ByteDance-Seed/UI-TARS-2B-SFT","name":"UI-TARS-2B-SFT","organization":"ByteDance-Seed","parameters":2442359296,"scoreCount":1,"useCases":{"agents":{"score":23.8,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":23.8,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ByteDance-Seed/UI-TARS-72B-SFT","name":"UI-TARS-72B-SFT","organization":"ByteDance-Seed","parameters":73405560320,"scoreCount":1,"useCases":{"agents":{"score":33.3,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":33.3,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ByteDance-Seed/UI-TARS-7B-SFT","name":"UI-TARS-7B-SFT","organization":"ByteDance-Seed","parameters":8291375616,"scoreCount":1,"useCases":{"agents":{"score":28.6,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":28.6,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/aya-expanse-32b","name":"aya-expanse-32b","organization":"CohereLabs","parameters":32296476672,"scoreCount":1,"useCases":{"reasoning":{"score":36.7,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/aya-expanse-8b","name":"aya-expanse-8b","organization":"CohereLabs","parameters":8028033024,"scoreCount":1,"useCases":{"reasoning":{"score":17.3,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/c4ai-command-a-03-2025","name":"c4ai-command-a-03-2025","organization":"CohereLabs","parameters":111057580032,"scoreCount":1,"useCases":{"reasoning":{"score":18.4,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":18.4,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/c4ai-command-r-08-2024","name":"c4ai-command-r-08-2024","organization":"CohereLabs","parameters":32296476672,"scoreCount":1,"useCases":{"reasoning":{"score":3.3,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":3.3,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/c4ai-command-r-plus-08-2024","name":"c4ai-command-r-plus-08-2024","organization":"CohereLabs","parameters":103810674688,"scoreCount":1,"useCases":{"reasoning":{"score":9.2,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":9.2,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/c4ai-command-r-v01","name":"c4ai-command-r-v01","organization":"CohereLabs","parameters":34980831232,"scoreCount":1,"useCases":{"reasoning":{"score":23,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/c4ai-command-r7b-12-2024","name":"c4ai-command-r7b-12-2024","organization":"CohereLabs","parameters":8028033024,"scoreCount":1,"useCases":{"reasoning":{"score":3.3,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":3.3,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"CohereLabs/cohere-transcribe-03-2026","name":"cohere-transcribe-03-2026","organization":"CohereLabs","parameters":2065804048,"scoreCount":1,"useCases":{"multimodal":{"score":96.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"crosbylegal/claude-fable-5","name":"claude-fable-5","organization":"crosbylegal","parameters":null,"scoreCount":1,"useCases":{"agents":{"score":75,"coverage":0.076,"confidence":0.032,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":75,"coverage":0.172,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1}}},{"id":"crosbylegal/claude-opus-4-8","name":"claude-opus-4-8","organization":"crosbylegal","parameters":null,"scoreCount":1,"useCases":{"agents":{"score":0,"coverage":0.076,"confidence":0.032,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":0,"coverage":0.172,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1}}},{"id":"crosbylegal/gemini-3.5-flash","name":"gemini-3.5-flash","organization":"crosbylegal","parameters":null,"scoreCount":1,"useCases":{"agents":{"score":25,"coverage":0.076,"confidence":0.032,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":25,"coverage":0.172,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1}}},{"id":"crosbylegal/gpt-5.5","name":"gpt-5.5","organization":"crosbylegal","parameters":null,"scoreCount":1,"useCases":{"agents":{"score":100,"coverage":0.076,"confidence":0.032,"confidenceLabel":"directional","benchmarks":1},"professional":{"score":100,"coverage":0.172,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1}}},{"id":"datalab-to/chandra","name":"chandra","organization":"datalab-to","parameters":8767123696,"scoreCount":1,"useCases":{"documents":{"score":64.3,"coverage":0.235,"confidence":0.075,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepseek-ai/DeepSeek-Coder-V2-Lite-Base","name":"DeepSeek-Coder-V2-Lite-Base","organization":"deepseek-ai","parameters":15706484224,"scoreCount":1,"useCases":{"reasoning":{"score":18,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct","name":"DeepSeek-Coder-V2-Lite-Instruct","organization":"deepseek-ai","parameters":15706484224,"scoreCount":1,"useCases":{"reasoning":{"score":30.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepseek-ai/deepseek-math-7b-instruct","name":"deepseek-math-7b-instruct","organization":"deepseek-ai","parameters":null,"scoreCount":1,"useCases":{"reasoning":{"score":18.7,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepseek-ai/DeepSeek-V2","name":"DeepSeek-V2","organization":"deepseek-ai","parameters":235741434880,"scoreCount":1,"useCases":{"reasoning":{"score":0,"coverage":0.117,"confidence":0.05,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepseek-ai/DeepSeek-V2-Chat","name":"DeepSeek-V2-Chat","organization":"deepseek-ai","parameters":235741434880,"scoreCount":1,"useCases":{"reasoning":{"score":48.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepseek-ai/DeepSeek-V2.5","name":"DeepSeek-V2.5","organization":"deepseek-ai","parameters":235741434880,"scoreCount":1,"useCases":{"reasoning":{"score":62.6,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek-V3-0324","organization":"deepseek-ai","parameters":684531386000,"scoreCount":1,"useCases":{"reasoning":{"score":77.7,"coverage":0.147,"confidence":0.056,"confidenceLabel":"directional","benchmarks":1}}},{"id":"distil-whisper/distil-large-v3.5","name":"distil-large-v3.5","organization":"distil-whisper","parameters":756405760,"scoreCount":1,"useCases":{"multimodal":{"score":63.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"docling-project/docling-models","name":"docling-models","organization":"docling-project","parameters":null,"scoreCount":1,"useCases":{"documents":{"score":52.9,"coverage":0.289,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1}}},{"id":"EleutherAI/llemma_7b","name":"llemma_7b","organization":"EleutherAI","parameters":null,"scoreCount":1,"useCases":{"reasoning":{"score":9.4,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"espnet/owsm_ctc_v3.1_1B","name":"owsm_ctc_v3.1_1B","organization":"espnet","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":43.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"espnet/owsm_ctc_v4_1B","name":"owsm_ctc_v4_1B","organization":"espnet","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":60,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/cwm","name":"cwm","organization":"facebook","parameters":32581097472,"scoreCount":1,"useCases":{"coding":{"score":0,"coverage":0.321,"confidence":0.117,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/data2vec-audio-base-960h","name":"data2vec-audio-base-960h","organization":"facebook","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":3.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/data2vec-audio-large-960h","name":"data2vec-audio-large-960h","organization":"facebook","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":10,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/hubert-large-ls960-ft","name":"hubert-large-ls960-ft","organization":"facebook","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":13.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/hubert-xlarge-ls960-ft","name":"hubert-xlarge-ls960-ft","organization":"facebook","parameters":962538400,"scoreCount":1,"useCases":{"multimodal":{"score":15,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/mms-1b-all","name":"mms-1b-all","organization":"facebook","parameters":964845850,"scoreCount":1,"useCases":{"multimodal":{"score":16.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/mms-1b-fl102","name":"mms-1b-fl102","organization":"facebook","parameters":964748494,"scoreCount":1,"useCases":{"multimodal":{"score":0,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/omniASR-LLM-1B","name":"omniASR-LLM-1B","organization":"facebook","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":16.7,"coverage":0.129,"confidence":0.056,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/wav2vec2-base-960h","name":"wav2vec2-base-960h","organization":"facebook","parameters":94395552,"scoreCount":1,"useCases":{"multimodal":{"score":1.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/wav2vec2-conformer-rel-pos-large-960h-ft","name":"wav2vec2-conformer-rel-pos-large-960h-ft","organization":"facebook","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":6.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/wav2vec2-conformer-rope-large-960h-ft","name":"wav2vec2-conformer-rope-large-960h-ft","organization":"facebook","parameters":593426112,"scoreCount":1,"useCases":{"multimodal":{"score":8.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/wav2vec2-large-960h","name":"wav2vec2-large-960h","organization":"facebook","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":5,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/wav2vec2-large-960h-lv60-self","name":"wav2vec2-large-960h-lv60-self","organization":"facebook","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":18.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"facebook/wav2vec2-large-robust-ft-libri-960h","name":"wav2vec2-large-robust-ft-libri-960h","organization":"facebook","parameters":315471520,"scoreCount":1,"useCases":{"multimodal":{"score":11.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"FINAL-Bench/Darwin-27B-Opus","name":"Darwin-27B-Opus","organization":"FINAL-Bench","parameters":27781427952,"scoreCount":1,"useCases":{"reasoning":{"score":77.6,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":77.6,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"FINAL-Bench/Darwin-28B-REASON","name":"Darwin-28B-REASON","organization":"FINAL-Bench","parameters":26895998464,"scoreCount":1,"useCases":{"reasoning":{"score":93.4,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":93.4,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"FINAL-Bench/Darwin-31B-Opus","name":"Darwin-31B-Opus","organization":"FINAL-Bench","parameters":32682372656,"scoreCount":1,"useCases":{"reasoning":{"score":71.1,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":71.1,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"FINAL-Bench/Darwin-36B-Opus","name":"Darwin-36B-Opus","organization":"FINAL-Bench","parameters":34660610688,"scoreCount":1,"useCases":{"reasoning":{"score":91.5,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":91.5,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"FINAL-Bench/Darwin-398B-JGOS","name":"Darwin-398B-JGOS","organization":"FINAL-Bench","parameters":403397928944,"scoreCount":1,"useCases":{"reasoning":{"score":98.7,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":98.7,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"FINAL-Bench/Darwin-4B-David","name":"Darwin-4B-David","organization":"FINAL-Bench","parameters":7996156490,"scoreCount":1,"useCases":{"reasoning":{"score":64.5,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":64.5,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"FINAL-Bench/Darwin-60B-DUO","name":"Darwin-60B-DUO","organization":"FINAL-Bench","parameters":null,"scoreCount":1,"useCases":{"reasoning":{"score":89.5,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":89.5,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"FINAL-Bench/Darwin-9B-NEG","name":"Darwin-9B-NEG","organization":"FINAL-Bench","parameters":9653104368,"scoreCount":1,"useCases":{"reasoning":{"score":61.2,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":61.2,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"google/embeddinggemma-300m","name":"embeddinggemma-300m","organization":"google","parameters":302863104,"scoreCount":1,"useCases":{"documents":{"score":100,"coverage":0.206,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1}}},{"id":"google/gemma-2-9b","name":"gemma-2-9b","organization":"google","parameters":9241705984,"scoreCount":1,"useCases":{"reasoning":{"score":36,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"google/gemma-4-12B","name":"gemma-4-12B","organization":"google","parameters":11959730224,"scoreCount":1,"useCases":{"multimodal":{"score":33.3,"coverage":0.129,"confidence":0.056,"confidenceLabel":"directional","benchmarks":1}}},{"id":"GSAI-ML/LLaDA-8B-Instruct","name":"LLaDA-8B-Instruct","organization":"GSAI-ML","parameters":8015581184,"scoreCount":1,"useCases":{"reasoning":{"score":21.6,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"HelpingAI/Dhanishtha-2.0-0126","name":"Dhanishtha-2.0-0126","organization":"HelpingAI","parameters":14768307200,"scoreCount":1,"useCases":{"reasoning":{"score":7.5,"coverage":0.131,"confidence":0.047,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":7.5,"coverage":0.275,"confidence":0.068,"confidenceLabel":"directional","benchmarks":1}}},{"id":"HuggingFaceTB/SmolLM2-1.7B","name":"SmolLM2-1.7B","organization":"HuggingFaceTB","parameters":1711376384,"scoreCount":1,"useCases":{"reasoning":{"score":5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"HuggingFaceTB/SmolLM2-135M","name":"SmolLM2-135M","organization":"HuggingFaceTB","parameters":134515008,"scoreCount":1,"useCases":{"reasoning":{"score":0.7,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"HuggingFaceTB/SmolLM2-360M","name":"SmolLM2-360M","organization":"HuggingFaceTB","parameters":361821120,"scoreCount":1,"useCases":{"reasoning":{"score":1.4,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-3.0-2b-base","name":"granite-3.0-2b-base","organization":"ibm-granite","parameters":2533525504,"scoreCount":1,"useCases":{"reasoning":{"score":6.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-3.0-8b-base","name":"granite-3.0-8b-base","organization":"ibm-granite","parameters":8170835968,"scoreCount":1,"useCases":{"reasoning":{"score":14.4,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-3.1-1b-a400m-base","name":"granite-3.1-1b-a400m-base","organization":"ibm-granite","parameters":1334625280,"scoreCount":1,"useCases":{"reasoning":{"score":2.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-3.1-2b-base","name":"granite-3.1-2b-base","organization":"ibm-granite","parameters":2533525504,"scoreCount":1,"useCases":{"reasoning":{"score":10.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-3.1-3b-a800m-base","name":"granite-3.1-3b-a800m-base","organization":"ibm-granite","parameters":3298788864,"scoreCount":1,"useCases":{"reasoning":{"score":5.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-3.1-8b-base","name":"granite-3.1-8b-base","organization":"ibm-granite","parameters":8170835968,"scoreCount":1,"useCases":{"reasoning":{"score":15.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-4.0-h-tiny","name":"granite-4.0-h-tiny","organization":"ibm-granite","parameters":6939037248,"scoreCount":1,"useCases":{"reasoning":{"score":0,"coverage":0.109,"confidence":0.051,"confidenceLabel":"directional","benchmarks":1}}},{"id":"ibm-granite/granite-vision-4.1-4b","name":"granite-vision-4.1-4b","organization":"ibm-granite","parameters":3997206464,"scoreCount":1,"useCases":{"documents":{"score":5.9,"coverage":0.289,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inclusionAI/Ling-2.6-1T","name":"Ling-2.6-1T","organization":"inclusionAI","parameters":1025657871744,"scoreCount":1,"useCases":{"coding":{"score":50,"coverage":0.321,"confidence":0.098,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inclusionAI/UI-Venus-1.5-2B","name":"UI-Venus-1.5-2B","organization":"inclusionAI","parameters":2438696960,"scoreCount":1,"useCases":{"agents":{"score":61.9,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":61.9,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inclusionAI/UI-Venus-1.5-30B-A3B","name":"UI-Venus-1.5-30B-A3B","organization":"inclusionAI","parameters":31070754032,"scoreCount":1,"useCases":{"agents":{"score":90.5,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":90.5,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inclusionAI/UI-Venus-1.5-8B","name":"UI-Venus-1.5-8B","organization":"inclusionAI","parameters":8767123696,"scoreCount":1,"useCases":{"agents":{"score":85.7,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":85.7,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inclusionAI/UI-Venus-Ground-72B","name":"UI-Venus-Ground-72B","organization":"inclusionAI","parameters":73410777344,"scoreCount":1,"useCases":{"agents":{"score":71.4,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":71.4,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inclusionAI/UI-Venus-Ground-7B","name":"UI-Venus-Ground-7B","organization":"inclusionAI","parameters":8292166656,"scoreCount":1,"useCases":{"agents":{"score":47.6,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":47.6,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"infly/Infinity-Parser-7B","name":"Infinity-Parser-7B","organization":"infly","parameters":8292166656,"scoreCount":1,"useCases":{"documents":{"score":57.1,"coverage":0.235,"confidence":0.056,"confidenceLabel":"directional","benchmarks":1}}},{"id":"infly/Infinity-Parser2-Flash","name":"Infinity-Parser2-Flash","organization":"infly","parameters":2213241664,"scoreCount":1,"useCases":{"documents":{"score":88.2,"coverage":0.289,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1}}},{"id":"inspatio/world","name":"world","organization":"inspatio","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":42.9,"coverage":0.142,"confidence":0.085,"confidenceLabel":"directional","benchmarks":1}}},{"id":"internlm/Intern-S1","name":"Intern-S1","organization":"internlm","parameters":240709856128,"scoreCount":1,"useCases":{"reasoning":{"score":83.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"internlm/internlm2_5-7b-chat","name":"internlm2_5-7b-chat","organization":"internlm","parameters":7737708544,"scoreCount":1,"useCases":{"reasoning":{"score":35.3,"coverage":0.117,"confidence":0.05,"confidenceLabel":"directional","benchmarks":1}}},{"id":"internlm/internlm2-chat-20b","name":"internlm2-chat-20b","organization":"internlm","parameters":19861149696,"scoreCount":1,"useCases":{"reasoning":{"score":5.9,"coverage":0.117,"confidence":0.05,"confidenceLabel":"directional","benchmarks":1}}},{"id":"internlm/internlm2-math-plus-20b","name":"internlm2-math-plus-20b","organization":"internlm","parameters":19861149696,"scoreCount":1,"useCases":{"reasoning":{"score":22.3,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"internlm/internlm2-math-plus-7b","name":"internlm2-math-plus-7b","organization":"internlm","parameters":7737708544,"scoreCount":1,"useCases":{"reasoning":{"score":16.6,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"internlm/internlm3-8b-instruct","name":"internlm3-8b-instruct","organization":"internlm","parameters":8804241408,"scoreCount":1,"useCases":{"reasoning":{"score":51.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"JetBrains/Mellum2-12B-A2.5B-Instruct","name":"Mellum2-12B-A2.5B-Instruct","organization":"JetBrains","parameters":12149923072,"scoreCount":1,"useCases":{"reasoning":{"score":13.2,"coverage":0.134,"confidence":0.042,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":13.2,"coverage":0.282,"confidence":0.061,"confidenceLabel":"directional","benchmarks":1}}},{"id":"JetBrains/Mellum2-12B-A2.5B-Instruct-SFT","name":"Mellum2-12B-A2.5B-Instruct-SFT","organization":"JetBrains","parameters":12149923072,"scoreCount":1,"useCases":{"reasoning":{"score":10.5,"coverage":0.134,"confidence":0.042,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":10.5,"coverage":0.282,"confidence":0.061,"confidenceLabel":"directional","benchmarks":1}}},{"id":"JetBrains/Mellum2-12B-A2.5B-Thinking","name":"Mellum2-12B-A2.5B-Thinking","organization":"JetBrains","parameters":12149923072,"scoreCount":1,"useCases":{"reasoning":{"score":19.7,"coverage":0.134,"confidence":0.042,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":19.7,"coverage":0.282,"confidence":0.061,"confidenceLabel":"directional","benchmarks":1}}},{"id":"JetBrains/Mellum2-12B-A2.5B-Thinking-SFT","name":"Mellum2-12B-A2.5B-Thinking-SFT","organization":"JetBrains","parameters":12149923072,"scoreCount":1,"useCases":{"reasoning":{"score":11.8,"coverage":0.134,"confidence":0.042,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":11.8,"coverage":0.282,"confidence":0.061,"confidenceLabel":"directional","benchmarks":1}}},{"id":"JGOS-Model/JGOS-31B-Citizen","name":"JGOS-31B-Citizen","organization":"JGOS-Model","parameters":31273086512,"scoreCount":1,"useCases":{"reasoning":{"score":61.2,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":61.2,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"KDEGroup/UI-AGILE-3B","name":"UI-AGILE-3B","organization":"KDEGroup","parameters":3754622976,"scoreCount":1,"useCases":{"agents":{"score":38.1,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":38.1,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"KDLAI/KDL-Frontier-Parser-nano","name":"KDL-Frontier-Parser-nano","organization":"KDLAI","parameters":1156026624,"scoreCount":1,"useCases":{"documents":{"score":100,"coverage":0.289,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1}}},{"id":"kyutai/stt-2.6b-en","name":"stt-2.6b-en","organization":"kyutai","parameters":2617118720,"scoreCount":1,"useCases":{"multimodal":{"score":83.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"lerobot/pi0_base","name":"pi0_base","organization":"lerobot","parameters":3501372176,"scoreCount":1,"useCases":{"agents":{"score":100,"coverage":0.087,"confidence":0.066,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":100,"coverage":0.133,"confidence":0.082,"confidenceLabel":"directional","benchmarks":1}}},{"id":"lerobot/pi05_base","name":"pi05_base","organization":"lerobot","parameters":3616757520,"scoreCount":1,"useCases":{"agents":{"score":66.7,"coverage":0.087,"confidence":0.066,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":66.7,"coverage":0.133,"confidence":0.082,"confidenceLabel":"directional","benchmarks":1}}},{"id":"lerobot/pi0fast-base","name":"pi0fast-base","organization":"lerobot","parameters":2923335408,"scoreCount":1,"useCases":{"agents":{"score":0,"coverage":0.087,"confidence":0.066,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":0,"coverage":0.133,"confidence":0.082,"confidenceLabel":"directional","benchmarks":1}}},{"id":"LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct","name":"EXAONE-3.5-2.4B-Instruct","organization":"LGAI-EXAONE","parameters":2405327360,"scoreCount":1,"useCases":{"reasoning":{"score":25.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"LGAI-EXAONE/EXAONE-3.5-32B-Instruct","name":"EXAONE-3.5-32B-Instruct","organization":"LGAI-EXAONE","parameters":32003200000,"scoreCount":1,"useCases":{"reasoning":{"score":53.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct","name":"EXAONE-3.5-7.8B-Instruct","organization":"LGAI-EXAONE","parameters":7818448896,"scoreCount":1,"useCases":{"reasoning":{"score":38.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"lightonai/LightOnOCR-1B-1025","name":"LightOnOCR-1B-1025","organization":"lightonai","parameters":1161230336,"scoreCount":1,"useCases":{"documents":{"score":21.4,"coverage":0.235,"confidence":0.056,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Lightricks/LTX-2.3","name":"LTX-2.3","organization":"Lightricks","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":57.1,"coverage":0.142,"confidence":0.085,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meituan-longcat/LongCat-Flash-Chat","name":"LongCat-Flash-Chat","organization":"meituan-longcat","parameters":561862880256,"scoreCount":1,"useCases":{"reasoning":{"score":80.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meituan-longcat/LongCat-Flash-Lite","name":"LongCat-Flash-Lite","organization":"meituan-longcat","parameters":69073335552,"scoreCount":1,"useCases":{"reasoning":{"score":71.9,"coverage":0.147,"confidence":0.056,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meituan-longcat/LongCat-Flash-Thinking-2601","name":"LongCat-Flash-Thinking-2601","organization":"meituan-longcat","parameters":561862880256,"scoreCount":1,"useCases":{"reasoning":{"score":42.8,"coverage":0.134,"confidence":0.053,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":42.8,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meituan-longcat/LongCat-Video","name":"LongCat-Video","organization":"meituan-longcat","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":28.6,"coverage":0.142,"confidence":0.085,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Llama-3.1-70B","name":"Llama-3.1-70B","organization":"meta-llama","parameters":70553706496,"scoreCount":1,"useCases":{"reasoning":{"score":46,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Llama-3.1-8B","name":"Llama-3.1-8B","organization":"meta-llama","parameters":8030261248,"scoreCount":1,"useCases":{"reasoning":{"score":20.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Llama-3.2-1B","name":"Llama-3.2-1B","organization":"meta-llama","parameters":1235814400,"scoreCount":1,"useCases":{"reasoning":{"score":2.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Llama-3.2-1B-Instruct","name":"Llama-3.2-1B-Instruct","organization":"meta-llama","parameters":1235814400,"scoreCount":1,"useCases":{"reasoning":{"score":0,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":0,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Llama-3.2-3B","name":"Llama-3.2-3B","organization":"meta-llama","parameters":3212749824,"scoreCount":1,"useCases":{"reasoning":{"score":7.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Meta-Llama-3-70B","name":"Meta-Llama-3-70B","organization":"meta-llama","parameters":70553706496,"scoreCount":1,"useCases":{"reasoning":{"score":46.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Meta-Llama-3-8B","name":"Meta-Llama-3-8B","organization":"meta-llama","parameters":8030261248,"scoreCount":1,"useCases":{"reasoning":{"score":19.4,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"meta-llama/Meta-Llama-3-8B-Instruct","name":"Meta-Llama-3-8B-Instruct","organization":"meta-llama","parameters":8030261248,"scoreCount":1,"useCases":{"reasoning":{"score":28.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"microsoft/Phi-3-medium-128k-instruct","name":"Phi-3-medium-128k-instruct","organization":"microsoft","parameters":13960238080,"scoreCount":1,"useCases":{"reasoning":{"score":44.6,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"microsoft/Phi-3-mini-128k-instruct","name":"Phi-3-mini-128k-instruct","organization":"microsoft","parameters":3821079552,"scoreCount":1,"useCases":{"reasoning":{"score":34.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"microsoft/Phi-4-mini-instruct","name":"Phi-4-mini-instruct","organization":"microsoft","parameters":3836021760,"scoreCount":1,"useCases":{"reasoning":{"score":47.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"microsoft/Phi-4-multimodal-instruct","name":"Phi-4-multimodal-instruct","organization":"microsoft","parameters":5574460384,"scoreCount":1,"useCases":{"multimodal":{"score":90,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"microsoft/VibeVoice-ASR-HF","name":"VibeVoice-ASR-HF","organization":"microsoft","parameters":8330325888,"scoreCount":1,"useCases":{"multimodal":{"score":51.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"MiniMaxAI/MiniMax-M1-40k","name":"MiniMax-M1-40k","organization":"MiniMaxAI","parameters":456089655296,"scoreCount":1,"useCases":{"reasoning":{"score":77,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"MiniMaxAI/MiniMax-Text-01","name":"MiniMax-Text-01","organization":"MiniMaxAI","parameters":456089655296,"scoreCount":1,"useCases":{"reasoning":{"score":71.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistral-community/Mistral-7B-v0.2","name":"Mistral-7B-v0.2","organization":"mistral-community","parameters":7241732096,"scoreCount":1,"useCases":{"reasoning":{"score":13,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mathstral-7B-v0.1","name":"Mathstral-7B-v0.1","organization":"mistralai","parameters":7248023552,"scoreCount":1,"useCases":{"reasoning":{"score":31.7,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mistral-7B-Instruct-v0.2","name":"Mistral-7B-Instruct-v0.2","organization":"mistralai","parameters":7241732096,"scoreCount":1,"useCases":{"reasoning":{"score":13.7,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mistral-Large-Instruct-2407","name":"Mistral-Large-Instruct-2407","organization":"mistralai","parameters":122610069504,"scoreCount":1,"useCases":{"reasoning":{"score":63.3,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mistral-Large-Instruct-2411","name":"Mistral-Large-Instruct-2411","organization":"mistralai","parameters":122610069504,"scoreCount":1,"useCases":{"reasoning":{"score":64.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mistral-Medium-3.5-128B","name":"Mistral-Medium-3.5-128B","organization":"mistralai","parameters":127704211408,"scoreCount":1,"useCases":{"coding":{"score":79.2,"coverage":0.321,"confidence":0.109,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mistral-Nemo-Base-2407","name":"Mistral-Nemo-Base-2407","organization":"mistralai","parameters":12247782400,"scoreCount":1,"useCases":{"reasoning":{"score":26.6,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mistral-Small-24B-Base-2501","name":"Mistral-Small-24B-Base-2501","organization":"mistralai","parameters":23572403200,"scoreCount":1,"useCases":{"reasoning":{"score":48.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral-Small-4-119B-2603","organization":"mistralai","parameters":119401317952,"scoreCount":1,"useCases":{"reasoning":{"score":26.3,"coverage":0.134,"confidence":0.053,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":26.3,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mistral-Small-Instruct-2409","name":"Mistral-Small-Instruct-2409","organization":"mistralai","parameters":22247282688,"scoreCount":1,"useCases":{"reasoning":{"score":41,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"mistralai/Mixtral-8x7B-v0.1","name":"Mixtral-8x7B-v0.1","organization":"mistralai","parameters":46702792704,"scoreCount":1,"useCases":{"reasoning":{"score":29.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"Kimi-K2-Instruct-0905","organization":"moonshotai","parameters":1026470735448,"scoreCount":1,"useCases":{"professional":{"score":0,"coverage":0.18,"confidence":0.066,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Multilingual-Multimodal-NLP/IndustrialCoder","name":"IndustrialCoder","organization":"Multilingual-Multimodal-NLP","parameters":31992714240,"scoreCount":1,"useCases":{"coding":{"score":68.8,"coverage":0.321,"confidence":0.087,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Muse-research/Muse-2-350M","name":"Muse-2-350M","organization":"Muse-research","parameters":354980864,"scoreCount":1,"useCases":{"reasoning":{"score":1.3,"coverage":0.134,"confidence":0.048,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":1.3,"coverage":0.282,"confidence":0.069,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nex-agi/Nex-N2-Pro","name":"Nex-N2-Pro","organization":"nex-agi","parameters":396802360816,"scoreCount":1,"useCases":{"agents":{"score":91.7,"coverage":0.092,"confidence":0.035,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/canary-180m-flash","name":"canary-180m-flash","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":68.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/canary-1b","name":"canary-1b","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":80,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/canary-1b-flash","name":"canary-1b-flash","organization":"nvidia","parameters":811049984,"scoreCount":1,"useCases":{"multimodal":{"score":85,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/canary-1b-v2","name":"canary-1b-v2","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":65,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/GR00T-N1-2B","name":"GR00T-N1-2B","organization":"nvidia","parameters":2190019826,"scoreCount":1,"useCases":{"agents":{"score":33.3,"coverage":0.087,"confidence":0.066,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":33.3,"coverage":0.133,"confidence":0.082,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/Nemotron-Cascade-2-30B-A3B","name":"Nemotron-Cascade-2-30B-A3B","organization":"nvidia","parameters":31577937344,"scoreCount":1,"useCases":{"reasoning":{"score":36.8,"coverage":0.134,"confidence":0.053,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":36.8,"coverage":0.282,"confidence":0.077,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/Nemotron-H-56B-Base-8K","name":"Nemotron-H-56B-Base-8K","organization":"nvidia","parameters":56324350464,"scoreCount":1,"useCases":{"reasoning":{"score":56.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/Nemotron-Terminal-14B","name":"Nemotron-Terminal-14B","organization":"nvidia","parameters":14768307200,"scoreCount":1,"useCases":{"coding":{"score":2.8,"coverage":0.343,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":2.8,"coverage":0.1,"confidence":0.049,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/Nemotron-Terminal-32B","name":"Nemotron-Terminal-32B","organization":"nvidia","parameters":32762123264,"scoreCount":1,"useCases":{"coding":{"score":11.1,"coverage":0.343,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":11.1,"coverage":0.1,"confidence":0.049,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/Nemotron-Terminal-8B","name":"Nemotron-Terminal-8B","organization":"nvidia","parameters":8190735360,"scoreCount":1,"useCases":{"coding":{"score":0,"coverage":0.343,"confidence":0.121,"confidenceLabel":"directional","benchmarks":1},"agents":{"score":0,"coverage":0.1,"confidence":0.049,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16","name":"NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16","organization":"nvidia","parameters":31577937344,"scoreCount":1,"useCases":{"reasoning":{"score":61.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","name":"NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","organization":"nvidia","parameters":31577937344,"scoreCount":1,"useCases":{"reasoning":{"score":50,"coverage":0.109,"confidence":0.051,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","name":"NVIDIA-Nemotron-3-Super-120B-A12B-FP8","organization":"nvidia","parameters":123611012096,"scoreCount":1,"useCases":{"reasoning":{"score":38.2,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":38.2,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/parakeet-ctc-0.6b","name":"parakeet-ctc-0.6b","organization":"nvidia","parameters":608848897,"scoreCount":1,"useCases":{"multimodal":{"score":53.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/parakeet-ctc-1.1b","name":"parakeet-ctc-1.1b","organization":"nvidia","parameters":1062626305,"scoreCount":1,"useCases":{"multimodal":{"score":61.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/parakeet-rnnt-0.6b","name":"parakeet-rnnt-0.6b","organization":"nvidia","parameters":616741377,"scoreCount":1,"useCases":{"multimodal":{"score":55,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/parakeet-rnnt-1.1b","name":"parakeet-rnnt-1.1b","organization":"nvidia","parameters":1070518785,"scoreCount":1,"useCases":{"multimodal":{"score":66.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/parakeet-tdt_ctc-110m","name":"parakeet-tdt_ctc-110m","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":56.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/parakeet-tdt-0.6b-v2","name":"parakeet-tdt-0.6b-v2","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":88.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/parakeet-tdt-0.6b-v3","name":"parakeet-tdt-0.6b-v3","organization":"nvidia","parameters":627057286,"scoreCount":1,"useCases":{"multimodal":{"score":86.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/parakeet-tdt-1.1b","name":"parakeet-tdt-1.1b","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":75,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/stt_en_conformer_ctc_large","name":"stt_en_conformer_ctc_large","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":41.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/stt_en_conformer_ctc_small","name":"stt_en_conformer_ctc_small","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":26.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/stt_en_fastconformer_ctc_large","name":"stt_en_fastconformer_ctc_large","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":35,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"nvidia/stt_en_fastconformer_transducer_large","name":"stt_en_fastconformer_transducer_large","organization":"nvidia","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":33.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openai/whisper-base.en","name":"whisper-base.en","organization":"openai","parameters":72593408,"scoreCount":1,"useCases":{"multimodal":{"score":30,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openai/whisper-large","name":"whisper-large","organization":"openai","parameters":1543304960,"scoreCount":1,"useCases":{"multimodal":{"score":46.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openai/whisper-large-v2","name":"whisper-large-v2","organization":"openai","parameters":1543304960,"scoreCount":1,"useCases":{"multimodal":{"score":50,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openai/whisper-medium.en","name":"whisper-medium.en","organization":"openai","parameters":763856896,"scoreCount":1,"useCases":{"multimodal":{"score":45,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openai/whisper-small.en","name":"whisper-small.en","organization":"openai","parameters":241734144,"scoreCount":1,"useCases":{"multimodal":{"score":38.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openai/whisper-tiny.en","name":"whisper-tiny.en","organization":"openai","parameters":37760256,"scoreCount":1,"useCases":{"multimodal":{"score":21.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"openbmb/MiniCPM-V-2","name":"MiniCPM-V-2","organization":"openbmb","parameters":3434965792,"scoreCount":1,"useCases":{"agents":{"score":4.8,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":4.8,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"OpenMOSS-Team/MOSS-Transcribe-preview-2B","name":"MOSS-Transcribe-preview-2B","organization":"OpenMOSS-Team","parameters":2418833792,"scoreCount":1,"useCases":{"multimodal":{"score":98.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"PolarSeeker/OpenSeeker-v2-30B-SFT","name":"OpenSeeker-v2-30B-SFT","organization":"PolarSeeker","parameters":30532122624,"scoreCount":1,"useCases":{"reasoning":{"score":55,"coverage":0.131,"confidence":0.052,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":55,"coverage":0.275,"confidence":0.076,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen-VL","name":"Qwen-VL","organization":"Qwen","parameters":null,"scoreCount":1,"useCases":{"agents":{"score":0,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":0,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen1.5-110B","name":"Qwen1.5-110B","organization":"Qwen","parameters":111209914368,"scoreCount":1,"useCases":{"reasoning":{"score":43.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen1.5-14B-Chat","name":"Qwen1.5-14B-Chat","organization":"Qwen","parameters":14167290880,"scoreCount":1,"useCases":{"reasoning":{"score":24.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen1.5-7B-Chat","name":"Qwen1.5-7B-Chat","organization":"Qwen","parameters":7721324544,"scoreCount":1,"useCases":{"reasoning":{"score":12.2,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2-0.5B","name":"Qwen2-0.5B","organization":"Qwen","parameters":494032768,"scoreCount":1,"useCases":{"reasoning":{"score":4.3,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2-1.5B","name":"Qwen2-1.5B","organization":"Qwen","parameters":1543714304,"scoreCount":1,"useCases":{"reasoning":{"score":7.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2-1.5B-Instruct","name":"Qwen2-1.5B-Instruct","organization":"Qwen","parameters":1543714304,"scoreCount":1,"useCases":{"reasoning":{"score":8.6,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2-72B","name":"Qwen2-72B","organization":"Qwen","parameters":72706203648,"scoreCount":1,"useCases":{"reasoning":{"score":58.8,"coverage":0.117,"confidence":0.05,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-0.5B","name":"Qwen2.5-0.5B","organization":"Qwen","parameters":494032768,"scoreCount":1,"useCases":{"reasoning":{"score":3.6,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-1.5B","name":"Qwen2.5-1.5B","organization":"Qwen","parameters":1543714304,"scoreCount":1,"useCases":{"reasoning":{"score":15.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-14B","name":"Qwen2.5-14B","organization":"Qwen","parameters":14770033664,"scoreCount":1,"useCases":{"reasoning":{"score":59,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-32B","name":"Qwen2.5-32B","organization":"Qwen","parameters":32763876352,"scoreCount":1,"useCases":{"reasoning":{"score":66.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-3B","name":"Qwen2.5-3B","organization":"Qwen","parameters":3085938688,"scoreCount":1,"useCases":{"reasoning":{"score":33.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-72B","name":"Qwen2.5-72B","organization":"Qwen","parameters":72706203648,"scoreCount":1,"useCases":{"reasoning":{"score":69.8,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-7B","name":"Qwen2.5-7B","organization":"Qwen","parameters":7615616512,"scoreCount":1,"useCases":{"reasoning":{"score":35.3,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen2.5-VL-32B-Instruct","organization":"Qwen","parameters":33452718336,"scoreCount":1,"useCases":{"agents":{"score":42.9,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":42.9,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3-235B-A22B-Instruct-2507","organization":"Qwen","parameters":235093634560,"scoreCount":1,"useCases":{"reasoning":{"score":82,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen3-235B-A22B-Thinking-2507","organization":"Qwen","parameters":235093634560,"scoreCount":1,"useCases":{"professional":{"score":87.5,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-30B-A3B-Base","name":"Qwen3-30B-A3B-Base","organization":"Qwen","parameters":30532122624,"scoreCount":1,"useCases":{"reasoning":{"score":58.3,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-32B","name":"Qwen3-32B","organization":"Qwen","parameters":32762123264,"scoreCount":1,"useCases":{"professional":{"score":50,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-ASR-0.6B","name":"Qwen3-ASR-0.6B","organization":"Qwen","parameters":938008576,"scoreCount":1,"useCases":{"multimodal":{"score":81.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-ASR-1.7B","name":"Qwen3-ASR-1.7B","organization":"Qwen","parameters":2349217408,"scoreCount":1,"useCases":{"multimodal":{"score":91.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen3-Next-80B-A3B-Thinking","organization":"Qwen","parameters":81324862720,"scoreCount":1,"useCases":{"professional":{"score":37.5,"coverage":0.218,"confidence":0.105,"confidenceLabel":"directional","benchmarks":1}}},{"id":"robbyant/lingbot-world-fast","name":"lingbot-world-fast","organization":"robbyant","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":100,"coverage":0.142,"confidence":0.085,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Salesforce/GTA1-32B","name":"GTA1-32B","organization":"Salesforce","parameters":33452718336,"scoreCount":1,"useCases":{"agents":{"score":76.2,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":76.2,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Salesforce/GTA1-7B","name":"GTA1-7B","organization":"Salesforce","parameters":8292166656,"scoreCount":1,"useCases":{"agents":{"score":57.1,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":57.1,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"shunyalabs/pingala-v1-universal","name":"pingala-v1-universal","organization":"shunyalabs","parameters":808878080,"scoreCount":1,"useCases":{"multimodal":{"score":66.7,"coverage":0.129,"confidence":0.056,"confidenceLabel":"directional","benchmarks":1}}},{"id":"soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M","name":"Zipformer-cr-ctc-transducer-XL-290M","organization":"soundsgoodai","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":93.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"soundsgoodai/Zipformer-transducer-XL-290M","name":"Zipformer-transducer-XL-290M","organization":"soundsgoodai","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":76.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"speechbrain/asr-conformer-loquacious","name":"asr-conformer-loquacious","organization":"speechbrain","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":40,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"speechbrain/asr-wav2vec2-librispeech","name":"asr-wav2vec2-librispeech","organization":"speechbrain","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":20,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"SPRINGLab/data2vec_aqc","name":"data2vec_aqc","organization":"SPRINGLab","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":50,"coverage":0.129,"confidence":0.041,"confidenceLabel":"directional","benchmarks":1}}},{"id":"Surpem/Supertron-embedding-190M","name":"Supertron-embedding-190M","organization":"Surpem","parameters":130450176,"scoreCount":1,"useCases":{"documents":{"score":0,"coverage":0.206,"confidence":0.052,"confidenceLabel":"directional","benchmarks":1}}},{"id":"tencent/Hunyuan-A13B-Instruct","name":"Hunyuan-A13B-Instruct","organization":"tencent","parameters":80393183232,"scoreCount":1,"useCases":{"reasoning":{"score":64,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"tencent/Hunyuan-GameCraft-1.0","name":"Hunyuan-GameCraft-1.0","organization":"tencent","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":0,"coverage":0.142,"confidence":0.085,"confidenceLabel":"directional","benchmarks":1}}},{"id":"tencent/HunyuanOCR","name":"HunyuanOCR","organization":"tencent","parameters":1119925744,"scoreCount":1,"useCases":{"documents":{"score":50,"coverage":0.271,"confidence":0.117,"confidenceLabel":"directional","benchmarks":1}}},{"id":"tencent/HunyuanVideo-1.5","name":"HunyuanVideo-1.5","organization":"tencent","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":71.4,"coverage":0.142,"confidence":0.085,"confidenceLabel":"directional","benchmarks":1}}},{"id":"tencent/HY-WorldPlay","name":"HY-WorldPlay","organization":"tencent","parameters":null,"scoreCount":1,"useCases":{"multimodal":{"score":85.7,"coverage":0.142,"confidence":0.085,"confidenceLabel":"directional","benchmarks":1}}},{"id":"tencent/Tencent-Hunyuan-Large","name":"Tencent-Hunyuan-Large","organization":"tencent","parameters":null,"scoreCount":1,"useCases":{"reasoning":{"score":55.4,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"TIGER-Lab/MAmmoTH2-7B-Plus","name":"MAmmoTH2-7B-Plus","organization":"TIGER-Lab","parameters":7241732096,"scoreCount":1,"useCases":{"reasoning":{"score":28.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"TIGER-Lab/MAmmoTH2-8B-Plus","name":"MAmmoTH2-8B-Plus","organization":"TIGER-Lab","parameters":8030261248,"scoreCount":1,"useCases":{"reasoning":{"score":33.1,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"TIGER-Lab/MAmmoTH2-8x7B-Plus","name":"MAmmoTH2-8x7B-Plus","organization":"TIGER-Lab","parameters":46702792704,"scoreCount":1,"useCases":{"reasoning":{"score":43.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"UsefulSensors/moonshine-base","name":"moonshine-base","organization":"UsefulSensors","parameters":61513920,"scoreCount":1,"useCases":{"multimodal":{"score":31.7,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"UsefulSensors/moonshine-streaming-medium","name":"moonshine-streaming-medium","organization":"UsefulSensors","parameters":265898112,"scoreCount":1,"useCases":{"multimodal":{"score":78.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"UsefulSensors/moonshine-streaming-small","name":"moonshine-streaming-small","organization":"UsefulSensors","parameters":140135224,"scoreCount":1,"useCases":{"multimodal":{"score":48.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"UsefulSensors/moonshine-streaming-tiny","name":"moonshine-streaming-tiny","organization":"UsefulSensors","parameters":44054720,"scoreCount":1,"useCases":{"multimodal":{"score":25,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"UsefulSensors/moonshine-tiny","name":"moonshine-tiny","organization":"UsefulSensors","parameters":27092736,"scoreCount":1,"useCases":{"multimodal":{"score":23.3,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}},{"id":"XiaomiMiMo/MiMo-7B-Base","name":"MiMo-7B-Base","organization":"XiaomiMiMo","parameters":7833409536,"scoreCount":1,"useCases":{"reasoning":{"score":30.9,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"XiaomiMiMo/MiMo-7B-RL","name":"MiMo-7B-RL","organization":"XiaomiMiMo","parameters":7833409536,"scoreCount":1,"useCases":{"reasoning":{"score":52.5,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/CogAgent","name":"CogAgent","organization":"zai-org","parameters":null,"scoreCount":1,"useCases":{"agents":{"score":9.5,"coverage":0.109,"confidence":0.074,"confidenceLabel":"directional","benchmarks":1},"multimodal":{"score":9.5,"coverage":0.167,"confidence":0.092,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/glm-4-9b","name":"glm-4-9b","organization":"zai-org","parameters":9399951392,"scoreCount":1,"useCases":{"reasoning":{"score":40.3,"coverage":0.147,"confidence":0.073,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/GLM-4.6-FP8","name":"GLM-4.6-FP8","organization":"zai-org","parameters":358458543424,"scoreCount":1,"useCases":{"reasoning":{"score":47.4,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":47.4,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/GLM-4.7-FP8","name":"GLM-4.7-FP8","organization":"zai-org","parameters":358458391872,"scoreCount":1,"useCases":{"reasoning":{"score":84.2,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":84.2,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/GLM-5-FP8","name":"GLM-5-FP8","organization":"zai-org","parameters":753910024032,"scoreCount":1,"useCases":{"reasoning":{"score":67.1,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":67.1,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/GLM-5.1-FP8","name":"GLM-5.1-FP8","organization":"zai-org","parameters":753910024032,"scoreCount":1,"useCases":{"reasoning":{"score":55.9,"coverage":0.134,"confidence":0.07,"confidenceLabel":"directional","benchmarks":1},"science-health":{"score":55.9,"coverage":0.282,"confidence":0.101,"confidenceLabel":"directional","benchmarks":1}}},{"id":"zai-org/GLM-ASR-Nano-2512","name":"GLM-ASR-Nano-2512","organization":"zai-org","parameters":2257843200,"scoreCount":1,"useCases":{"multimodal":{"score":72.5,"coverage":0.178,"confidence":0.095,"confidenceLabel":"directional","benchmarks":1}}}],"rankings":{"reasoning":[{"id":"zai-org/GLM-5.2","name":"GLM-5.2","organization":"zai-org","parameters":753329940480,"score":100,"coverage":0.265,"confidence":0.134,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2.6","name":"Kimi-K2.6","organization":"moonshotai","parameters":1058589420528,"score":97.6,"coverage":0.626,"confidence":0.412,"confidenceLabel":"moderate","benchmarks":5},{"id":"tencent/Hy3","name":"Hy3","organization":"tencent","parameters":298786155776,"score":95.5,"coverage":0.265,"confidence":0.149,"confidenceLabel":"directional","benchmarks":2},{"id":"InternScience/Agents-A1","name":"Agents-A1","organization":"InternScience","parameters":35107181936,"score":86.4,"coverage":0.24,"confidence":0.121,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","organization":"moonshotai","parameters":1058589420528,"score":85.4,"coverage":0.774,"confidence":0.599,"confidenceLabel":"moderate","benchmarks":6},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","organization":"Qwen","parameters":403397928944,"score":84.5,"coverage":0.657,"confidence":0.567,"confidenceLabel":"moderate","benchmarks":5},{"id":"inclusionAI/Ring-2.6-1T","name":"Ring-2.6-1T","organization":"inclusionAI","parameters":1025657871744,"score":84.3,"coverage":0.254,"confidence":0.131,"confidenceLabel":"directional","benchmarks":2},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek-V4-Pro","organization":"deepseek-ai","parameters":861608274846,"score":84.2,"coverage":0.53,"confidence":0.422,"confidenceLabel":"moderate","benchmarks":4},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5-122B-A10B","organization":"Qwen","parameters":125086497008,"score":81.8,"coverage":0.412,"confidence":0.31,"confidenceLabel":"directional","benchmarks":3},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","organization":"nvidia","parameters":335038821080,"score":81.6,"coverage":0.412,"confidence":0.279,"confidenceLabel":"directional","benchmarks":3},{"id":"zai-org/GLM-5","name":"GLM-5","organization":"zai-org","parameters":753864139008,"score":80.5,"coverage":0.657,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":5},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek-V4-Flash","organization":"deepseek-ai","parameters":158069433298,"score":80.2,"coverage":0.412,"confidence":0.279,"confidenceLabel":"directional","benchmarks":3},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","organization":"nvidia","parameters":560524578816,"score":79.4,"coverage":0.412,"confidence":0.279,"confidenceLabel":"directional","benchmarks":3},{"id":"meta-llama/Llama-3.1-405B","name":"Llama-3.1-405B","organization":"meta-llama","parameters":405853388800,"score":73.8,"coverage":0.265,"confidence":0.175,"confidenceLabel":"directional","benchmarks":2},{"id":"internlm/Intern-S2-Preview","name":"Intern-S2-Preview","organization":"internlm","parameters":36098254656,"score":72.3,"coverage":0.519,"confidence":0.418,"confidenceLabel":"moderate","benchmarks":4},{"id":"stepfun-ai/Step-3.5-Flash","name":"Step-3.5-Flash","organization":"stepfun-ai","parameters":199384301376,"score":72,"coverage":0.657,"confidence":0.506,"confidenceLabel":"moderate","benchmarks":5},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","organization":"zai-org","parameters":358337791296,"score":68.6,"coverage":0.265,"confidence":0.141,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6-27B","organization":"Qwen","parameters":27781427952,"score":66.8,"coverage":0.774,"confidence":0.51,"confidenceLabel":"moderate","benchmarks":6},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","organization":"zai-org","parameters":753864139008,"score":66.7,"coverage":0.51,"confidence":0.371,"confidenceLabel":"directional","benchmarks":4},{"id":"tencent/Hy3-preview","name":"Hy3-preview","organization":"tencent","parameters":298786155776,"score":66.6,"coverage":0.265,"confidence":0.149,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi-K2-Thinking","organization":"moonshotai","parameters":1058118284416,"score":66.5,"coverage":0.265,"confidence":0.149,"confidenceLabel":"directional","benchmarks":2},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek-R1-0528","organization":"deepseek-ai","parameters":684531386000,"score":66.2,"coverage":0.281,"confidence":0.177,"confidenceLabel":"directional","benchmarks":2},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","organization":"XiaomiMiMo","parameters":1023244718976,"score":66,"coverage":0.53,"confidence":0.422,"confidenceLabel":"moderate","benchmarks":4},{"id":"MiniMaxAI/MiniMax-M2.1","name":"MiniMax-M2.1","organization":"MiniMaxAI","parameters":228703644928,"score":60.5,"coverage":0.412,"confidence":0.338,"confidenceLabel":"directional","benchmarks":3}],"coding":[{"id":"deepreinforce-ai/Ornith-1.0-397B","name":"Ornith-1.0-397B","organization":"deepreinforce-ai","parameters":396802360816,"score":100,"coverage":0.657,"confidence":0.313,"confidenceLabel":"directional","benchmarks":2},{"id":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","name":"MiniMax-M3-MXFP4-Mixed-CT-AutoRound","organization":"INCModelSharing","parameters":233489984384,"score":91.8,"coverage":0.657,"confidence":0.281,"confidenceLabel":"directional","benchmarks":2},{"id":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","name":"MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","organization":"INCModelSharing","parameters":233690524544,"score":91.8,"coverage":0.657,"confidence":0.281,"confidenceLabel":"directional","benchmarks":2},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","organization":"MiniMaxAI","parameters":427040140160,"score":91.8,"coverage":0.657,"confidence":0.281,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","organization":"zai-org","parameters":753864139008,"score":90.1,"coverage":0.679,"confidence":0.286,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2.6","name":"Kimi-K2.6","organization":"moonshotai","parameters":1058589420528,"score":88.2,"coverage":1,"confidence":0.52,"confidenceLabel":"moderate","benchmarks":3},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","organization":"XiaomiMiMo","parameters":1023244718976,"score":85.4,"coverage":1,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":3},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek-V4-Flash","organization":"deepseek-ai","parameters":158069433298,"score":83.9,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek-V4-Pro","organization":"deepseek-ai","parameters":861608274846,"score":83.4,"coverage":1,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":3},{"id":"tencent/Hy3","name":"Hy3","organization":"tencent","parameters":298786155776,"score":79.9,"coverage":0.657,"confidence":0.313,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-5","name":"GLM-5","organization":"zai-org","parameters":753864139008,"score":76.6,"coverage":0.663,"confidence":0.389,"confidenceLabel":"directional","benchmarks":2},{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","organization":"XiaomiMiMo","parameters":310775040000,"score":76.2,"coverage":0.679,"confidence":0.319,"confidenceLabel":"directional","benchmarks":2},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","organization":"MiniMaxAI","parameters":228703644928,"score":75.1,"coverage":0.679,"confidence":0.319,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","organization":"Qwen","parameters":403397928944,"score":75,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6-27B","organization":"Qwen","parameters":27781427952,"score":72.2,"coverage":1,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":3},{"id":"tencent/Hy3-preview","name":"Hy3-preview","organization":"tencent","parameters":298786155776,"score":70.9,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","organization":"MiniMaxAI","parameters":228703644928,"score":65.4,"coverage":0.657,"confidence":0.398,"confidenceLabel":"directional","benchmarks":2},{"id":"stepfun-ai/Step-3.5-Flash","name":"Step-3.5-Flash","organization":"stepfun-ai","parameters":199384301376,"score":65.2,"coverage":0.663,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2},{"id":"deepreinforce-ai/Ornith-1.0-35B","name":"Ornith-1.0-35B","organization":"deepreinforce-ai","parameters":664944,"score":58.5,"coverage":0.657,"confidence":0.313,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5-122B-A10B","organization":"Qwen","parameters":125086497008,"score":56.2,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6-35B-A3B","organization":"Qwen","parameters":35951822704,"score":55.8,"coverage":1,"confidence":0.58,"confidenceLabel":"moderate","benchmarks":3},{"id":"poolside/Laguna-M.1","name":"Laguna-M.1","organization":"poolside","parameters":225795725568,"score":55.8,"coverage":1,"confidence":0.52,"confidenceLabel":"moderate","benchmarks":3},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5-27B","organization":"Qwen","parameters":27781427952,"score":53.9,"coverage":0.663,"confidence":0.315,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","organization":"moonshotai","parameters":1058589420528,"score":49.5,"coverage":1,"confidence":0.792,"confidenceLabel":"strong","benchmarks":3}],"agents":[{"id":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","name":"MiniMax-M3-MXFP4-Mixed-CT-AutoRound","organization":"INCModelSharing","parameters":233489984384,"score":89.7,"coverage":0.283,"confidence":0.208,"confidenceLabel":"directional","benchmarks":3},{"id":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","name":"MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","organization":"INCModelSharing","parameters":233690524544,"score":89.7,"coverage":0.283,"confidence":0.208,"confidenceLabel":"directional","benchmarks":3},{"id":"tencent/Hy3","name":"Hy3","organization":"tencent","parameters":298786155776,"score":85,"coverage":0.281,"confidence":0.231,"confidenceLabel":"directional","benchmarks":3},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","organization":"zai-org","parameters":753864139008,"score":84.3,"coverage":0.631,"confidence":0.542,"confidenceLabel":"moderate","benchmarks":7},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","organization":"MiniMaxAI","parameters":427040140160,"score":81.7,"coverage":0.376,"confidence":0.376,"confidenceLabel":"directional","benchmarks":4},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","organization":"XiaomiMiMo","parameters":1023244718976,"score":78.6,"coverage":0.286,"confidence":0.28,"confidenceLabel":"directional","benchmarks":3},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5-27B","organization":"Qwen","parameters":27781427952,"score":76.3,"coverage":0.209,"confidence":0.133,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","organization":"zai-org","parameters":753329940480,"score":76.3,"coverage":0.16,"confidence":0.116,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-5","name":"GLM-5","organization":"zai-org","parameters":753864139008,"score":63.7,"coverage":0.381,"confidence":0.448,"confidenceLabel":"moderate","benchmarks":4},{"id":"moonshotai/Kimi-K2.6","name":"Kimi-K2.6","organization":"moonshotai","parameters":1058589420528,"score":61.7,"coverage":0.539,"confidence":0.508,"confidenceLabel":"moderate","benchmarks":6},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6-27B","organization":"Qwen","parameters":27781427952,"score":58.4,"coverage":0.192,"confidence":0.127,"confidenceLabel":"directional","benchmarks":2},{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","organization":"XiaomiMiMo","parameters":310775040000,"score":57.9,"coverage":0.278,"confidence":0.272,"confidenceLabel":"directional","benchmarks":3},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5-122B-A10B","organization":"Qwen","parameters":125086497008,"score":57.4,"coverage":0.301,"confidence":0.244,"confidenceLabel":"directional","benchmarks":3},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek-V4-Pro","organization":"deepseek-ai","parameters":861608274846,"score":52,"coverage":0.631,"confidence":0.549,"confidenceLabel":"moderate","benchmarks":7},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","organization":"Qwen","parameters":403397928944,"score":41.1,"coverage":0.668,"confidence":0.558,"confidenceLabel":"moderate","benchmarks":7},{"id":"openpangu/openPangu-2.0-Flash","name":"openPangu-2.0-Flash","organization":"openpangu","parameters":100136311993,"score":39.6,"coverage":0.186,"confidence":0.125,"confidenceLabel":"directional","benchmarks":2},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek-V4-Flash","organization":"deepseek-ai","parameters":158069433298,"score":39.4,"coverage":0.287,"confidence":0.317,"confidenceLabel":"directional","benchmarks":3},{"id":"stepfun-ai/Step-3.5-Flash","name":"Step-3.5-Flash","organization":"stepfun-ai","parameters":199384301376,"score":34.7,"coverage":0.192,"confidence":0.118,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","organization":"moonshotai","parameters":1058589420528,"score":29.8,"coverage":0.559,"confidence":0.568,"confidenceLabel":"moderate","benchmarks":6},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","organization":"MiniMaxAI","parameters":228703644928,"score":29.5,"coverage":0.379,"confidence":0.46,"confidenceLabel":"moderate","benchmarks":4},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","organization":"zai-org","parameters":358337791296,"score":22.1,"coverage":0.289,"confidence":0.327,"confidenceLabel":"directional","benchmarks":3},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","organization":"MiniMaxAI","parameters":228703644928,"score":19,"coverage":0.281,"confidence":0.285,"confidenceLabel":"directional","benchmarks":3},{"id":"moonshotai/Kimi-K2-Instruct","name":"Kimi-K2-Instruct","organization":"moonshotai","parameters":1026470731056,"score":16.9,"coverage":0.197,"confidence":0.2,"confidenceLabel":"directional","benchmarks":2},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","name":"NVIDIA-Nemotron-3-Super-120B-A12B-BF16","organization":"nvidia","parameters":123611012096,"score":15.7,"coverage":0.194,"confidence":0.155,"confidenceLabel":"directional","benchmarks":2}],"documents":[{"id":"infly/Infinity-Parser2-Pro","name":"Infinity-Parser2-Pro","organization":"infly","parameters":35107181936,"score":96.8,"coverage":0.524,"confidence":0.254,"confidenceLabel":"directional","benchmarks":2},{"id":"datalab-to/chandra-ocr-2","name":"chandra-ocr-2","organization":"datalab-to","parameters":5295564288,"score":86.2,"coverage":0.794,"confidence":0.526,"confidenceLabel":"moderate","benchmarks":3},{"id":"rednote-hilab/dots.mocr","name":"dots.mocr","organization":"rednote-hilab","parameters":3039179264,"score":83,"coverage":0.794,"confidence":0.515,"confidenceLabel":"moderate","benchmarks":3},{"id":"datalab-to/surya-ocr-2","name":"surya-ocr-2","organization":"datalab-to","parameters":686154304,"score":74.2,"coverage":0.524,"confidence":0.264,"confidenceLabel":"directional","benchmarks":2},{"id":"opendatalab/MinerU2.5-Pro-2605-1.2B","name":"MinerU2.5-Pro-2605-1.2B","organization":"opendatalab","parameters":1156026624,"score":73.3,"coverage":0.559,"confidence":0.337,"confidenceLabel":"directional","benchmarks":2},{"id":"rednote-hilab/dots.ocr","name":"dots.ocr","organization":"rednote-hilab","parameters":3039179264,"score":55.5,"coverage":0.506,"confidence":0.274,"confidenceLabel":"directional","benchmarks":2},{"id":"lightonai/LightOnOCR-2-1B","name":"LightOnOCR-2-1B","organization":"lightonai","parameters":1005647872,"score":47.5,"coverage":0.794,"confidence":0.515,"confidenceLabel":"moderate","benchmarks":3},{"id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen3-VL-8B-Instruct","organization":"Qwen","parameters":8767123696,"score":45.4,"coverage":0.559,"confidence":0.337,"confidenceLabel":"directional","benchmarks":2},{"id":"tiiuae/Falcon-OCR","name":"Falcon-OCR","organization":"tiiuae","parameters":269944416,"score":42.4,"coverage":0.794,"confidence":0.526,"confidenceLabel":"moderate","benchmarks":3},{"id":"baidu/Qianfan-OCR","name":"Qianfan-OCR","organization":"baidu","parameters":4741408256,"score":38.7,"coverage":0.524,"confidence":0.254,"confidenceLabel":"directional","benchmarks":2},{"id":"deepseek-ai/DeepSeek-OCR-2","name":"DeepSeek-OCR-2","organization":"deepseek-ai","parameters":3389119360,"score":19.3,"coverage":0.524,"confidence":0.28,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-OCR","name":"GLM-OCR","organization":"zai-org","parameters":1325258240,"score":13.4,"coverage":0.794,"confidence":0.515,"confidenceLabel":"moderate","benchmarks":3},{"id":"deepseek-ai/DeepSeek-OCR","name":"DeepSeek-OCR","organization":"deepseek-ai","parameters":3336106240,"score":11.5,"coverage":0.506,"confidence":0.274,"confidenceLabel":"directional","benchmarks":2},{"id":"opendatalab/MinerU2.5-2509-1.2B","name":"MinerU2.5-2509-1.2B","organization":"opendatalab","parameters":1156026624,"score":9.6,"coverage":0.794,"confidence":0.546,"confidenceLabel":"moderate","benchmarks":3}],"professional":[{"id":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","name":"MiniMax-M3-MXFP4-Mixed-CT-AutoRound","organization":"INCModelSharing","parameters":233489984384,"score":90.4,"coverage":0.43,"confidence":0.171,"confidenceLabel":"directional","benchmarks":2},{"id":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","name":"MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","organization":"INCModelSharing","parameters":233690524544,"score":90.4,"coverage":0.43,"confidence":0.171,"confidenceLabel":"directional","benchmarks":2},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","organization":"MiniMaxAI","parameters":427040140160,"score":90.4,"coverage":0.43,"confidence":0.171,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-5","name":"GLM-5","organization":"zai-org","parameters":753864139008,"score":61.8,"coverage":0.43,"confidence":0.225,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","organization":"moonshotai","parameters":1058589420528,"score":43.3,"coverage":0.43,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","organization":"zai-org","parameters":358337791296,"score":38.9,"coverage":0.61,"confidence":0.422,"confidenceLabel":"moderate","benchmarks":3},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","organization":"Qwen","parameters":403397928944,"score":24.9,"coverage":0.43,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","organization":"MiniMaxAI","parameters":228703644928,"score":24.2,"coverage":0.43,"confidence":0.25,"confidenceLabel":"directional","benchmarks":2}],"science-health":[{"id":"zai-org/GLM-5.2","name":"GLM-5.2","organization":"zai-org","parameters":753329940480,"score":100,"coverage":0.789,"confidence":0.358,"confidenceLabel":"directional","benchmarks":3},{"id":"tencent/Hy3","name":"Hy3","organization":"tencent","parameters":298786155776,"score":95.5,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","organization":"zai-org","parameters":753864139008,"score":87,"coverage":1,"confidence":0.555,"confidenceLabel":"moderate","benchmarks":4},{"id":"zai-org/GLM-5","name":"GLM-5","organization":"zai-org","parameters":753864139008,"score":81.4,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2.6","name":"Kimi-K2.6","organization":"moonshotai","parameters":1058589420528,"score":80.3,"coverage":1,"confidence":0.555,"confidenceLabel":"moderate","benchmarks":4},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5-27B","organization":"Qwen","parameters":27781427952,"score":76.6,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5-122B-A10B","organization":"Qwen","parameters":125086497008,"score":74.4,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","organization":"nvidia","parameters":335038821080,"score":73.6,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek-V4-Flash","organization":"deepseek-ai","parameters":158069433298,"score":72.4,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","organization":"nvidia","parameters":560524578816,"score":70.2,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","organization":"zai-org","parameters":358337791296,"score":68.6,"coverage":0.557,"confidence":0.205,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6-27B","organization":"Qwen","parameters":27781427952,"score":66.7,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"tencent/Hy3-preview","name":"Hy3-preview","organization":"tencent","parameters":298786155776,"score":66.6,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi-K2-Thinking","organization":"moonshotai","parameters":1058118284416,"score":66.5,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","organization":"Qwen","parameters":403397928944,"score":66.3,"coverage":0.789,"confidence":0.386,"confidenceLabel":"directional","benchmarks":3},{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","organization":"moonshotai","parameters":1058589420528,"score":59.6,"coverage":0.789,"confidence":0.386,"confidenceLabel":"directional","benchmarks":3},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek-V4-Pro","organization":"deepseek-ai","parameters":861608274846,"score":56.2,"coverage":1,"confidence":0.588,"confidenceLabel":"moderate","benchmarks":4},{"id":"stepfun-ai/Step-3.5-Flash","name":"Step-3.5-Flash","organization":"stepfun-ai","parameters":199384301376,"score":52.8,"coverage":0.557,"confidence":0.172,"confidenceLabel":"directional","benchmarks":2},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","organization":"XiaomiMiMo","parameters":1023244718976,"score":50.9,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6-35B-A3B","organization":"Qwen","parameters":35951822704,"score":49.3,"coverage":0.557,"confidence":0.216,"confidenceLabel":"directional","benchmarks":2},{"id":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","name":"NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","organization":"exolabs","parameters":120668707840,"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2},{"id":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","name":"NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","organization":"exolabs","parameters":120668707840,"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2},{"id":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","name":"NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","organization":"exolabs","parameters":120668707840,"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","name":"NVIDIA-Nemotron-3-Super-120B-A12B-BF16","organization":"nvidia","parameters":123611012096,"score":45.7,"coverage":0.557,"confidence":0.194,"confidenceLabel":"directional","benchmarks":2}],"multimodal":[{"id":"mistralai/Voxtral-Mini-3B-2507","name":"Voxtral-Mini-3B-2507","organization":"mistralai","parameters":4676271104,"score":75.6,"coverage":0.307,"confidence":0.217,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5-27B","organization":"Qwen","parameters":27781427952,"score":69.4,"coverage":0.302,"confidence":0.159,"confidenceLabel":"directional","benchmarks":2},{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","organization":"moonshotai","parameters":1058589420528,"score":58.6,"coverage":0.252,"confidence":0.183,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","organization":"Qwen","parameters":403397928944,"score":47.7,"coverage":0.283,"confidence":0.189,"confidenceLabel":"directional","benchmarks":2},{"id":"openai/whisper-large-v3","name":"whisper-large-v3","organization":"openai","parameters":1543490560,"score":33.9,"coverage":0.307,"confidence":0.217,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen2.5-VL-7B-Instruct","name":"Qwen2.5-VL-7B-Instruct","organization":"Qwen","parameters":8292166656,"score":16.1,"coverage":0.302,"confidence":0.208,"confidenceLabel":"directional","benchmarks":2},{"id":"Qwen/Qwen2.5-VL-3B-Instruct","name":"Qwen2.5-VL-3B-Instruct","organization":"Qwen","parameters":3754622976,"score":7.9,"coverage":0.302,"confidence":0.208,"confidenceLabel":"directional","benchmarks":2}],"safety":[]},"selectedScores":[{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"InternScience/Agents-A1","value":93.25,"lowerIsBetter":false,"percentile":100,"sourceName":"Agents-A1 eval trace","sourceUrl":"https://huggingface.co/datasets/InternScience/Agents-A1-ifstruct-eval-20260703-041434","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/Agents-A1.yaml","parameters":35107181936},{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"openai/gpt-oss-20b","value":91.95,"lowerIsBetter":false,"percentile":75,"sourceName":"Liquid AI — IFStruct v1.0 blog (gpt-oss-20b)","sourceUrl":"https://www.liquid.ai/blog/ifstruct-v1.0","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/openai-gpt-oss-20b.yaml","parameters":21511953984},{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","value":86.8,"lowerIsBetter":false,"percentile":50,"sourceName":"Liquid AI — IFStruct v1.0 blog (Nemotron-3-Nano-30B-A3B)","sourceUrl":"https://www.liquid.ai/blog/ifstruct-v1.0","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/nvidia-NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.yaml","parameters":31577937344},{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"ibm-granite/granite-4.1-8b","value":68.45,"lowerIsBetter":false,"percentile":25,"sourceName":"Liquid AI — IFStruct v1.0 blog (granite-4.1-8b)","sourceUrl":"https://www.liquid.ai/blog/ifstruct-v1.0","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ibm-granite-granite-4.1-8b.yaml","parameters":8791592960},{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"ibm-granite/granite-4.0-h-tiny","value":38.75,"lowerIsBetter":false,"percentile":0,"sourceName":"Liquid AI — IFStruct v1.0 blog (granite-4.0-h-tiny)","sourceUrl":"https://www.liquid.ai/blog/ifstruct-v1.0","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ibm-granite-granite-4.0-h-tiny.yaml","parameters":6939037248},{"benchmarkId":"openai/gsm8k","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":99.6,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":1023244718976},{"benchmarkId":"openai/gsm8k","modelId":"meta-llama/Llama-3.1-405B","value":96.8,"lowerIsBetter":false,"percentile":94.12,"sourceName":"Model Card","sourceUrl":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"8-shot CoT","filename":".eval_results/gsm8k.yaml","parameters":405853388800},{"benchmarkId":"openai/gsm8k","modelId":"ibm-granite/granite-4.1-30b","value":94.16,"lowerIsBetter":false,"percentile":88.24,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-30b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":28865728512},{"benchmarkId":"openai/gsm8k","modelId":"meta-llama/Llama-3.2-90B-Vision-Instruct","value":93.1008339651,"lowerIsBetter":false,"percentile":82.35,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/41/24/41243885-1629-4ecf-bc92-be4fa346aeba.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":88593355323},{"benchmarkId":"openai/gsm8k","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":92.6,"lowerIsBetter":false,"percentile":76.47,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":861608274846},{"benchmarkId":"openai/gsm8k","modelId":"ibm-granite/granite-4.1-8b","value":92.49,"lowerIsBetter":false,"percentile":70.59,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-8b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":8791592960},{"benchmarkId":"openai/gsm8k","modelId":"microsoft/Phi-3-medium-4k-instruct","value":91,"lowerIsBetter":false,"percentile":64.71,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/microsoft/Phi-3-medium-4k-instruct","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"8-shot CoT","filename":".eval_results/gsm8k.yaml","parameters":13960238080},{"benchmarkId":"openai/gsm8k","modelId":"Qwen/Qwen2-72B","value":89.5,"lowerIsBetter":false,"percentile":58.82,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen2-72B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":72706203648},{"benchmarkId":"openai/gsm8k","modelId":"deepseek-ai/DeepSeek-V3","value":89.3,"lowerIsBetter":false,"percentile":52.94,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":684531386000},{"benchmarkId":"openai/gsm8k","modelId":"ibm-granite/granite-4.1-3b","value":86.88,"lowerIsBetter":false,"percentile":47.06,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-3b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":3402836480},{"benchmarkId":"openai/gsm8k","modelId":"microsoft/Phi-3.5-mini-instruct","value":86.2,"lowerIsBetter":false,"percentile":41.18,"sourceName":"Phi-3 Technical Report","sourceUrl":"https://hf.co/papers/2404.14219","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":3821079552},{"benchmarkId":"openai/gsm8k","modelId":"internlm/internlm2_5-7b-chat","value":86,"lowerIsBetter":false,"percentile":35.29,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/internlm2_5-7b-chat","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"0-shot CoT","filename":".eval_results/gsm8k.yaml","parameters":7737708544},{"benchmarkId":"openai/gsm8k","modelId":"microsoft/Phi-3-mini-4k-instruct","value":85.7,"lowerIsBetter":false,"percentile":29.41,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/microsoft/Phi-3-mini-4k-instruct","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"8-shot CoT","filename":".eval_results/gsm8k.yaml","parameters":3821079552},{"benchmarkId":"openai/gsm8k","modelId":"JetBrains/Mellum2-12B-A2.5B-Base-Pretrain","value":81.73,"lowerIsBetter":false,"percentile":20.59,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval, no-tools, exact match","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"openai/gsm8k","modelId":"JetBrains/Mellum2-12B-A2.5B-Base","value":81.73,"lowerIsBetter":false,"percentile":20.59,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval (pre-YaRN), no-tools, exact match","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"openai/gsm8k","modelId":"Qwen/Qwen2-7B","value":79.9,"lowerIsBetter":false,"percentile":11.76,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen2-7B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"4-shot","filename":".eval_results/gsm8k.yaml","parameters":7615616512},{"benchmarkId":"openai/gsm8k","modelId":"internlm/internlm2-chat-20b","value":79.6,"lowerIsBetter":false,"percentile":5.88,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/internlm2-chat-20b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":19861149696},{"benchmarkId":"openai/gsm8k","modelId":"deepseek-ai/DeepSeek-V2","value":79.2,"lowerIsBetter":false,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":235741434880},{"benchmarkId":"allenai/olmOCR-bench","modelId":"infly/Infinity-Parser2-Pro","value":87.6,"lowerIsBetter":false,"percentile":100,"sourceName":"Infinity Parser technical report","sourceUrl":"https://huggingface.co/papers/2506.03197","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":35107181936},{"benchmarkId":"allenai/olmOCR-bench","modelId":"datalab-to/chandra-ocr-2","value":85.8,"lowerIsBetter":false,"percentile":92.86,"sourceName":"Chandra OCR 2 Model Card","sourceUrl":"https://huggingface.co/datalab-to/chandra-ocr-2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":5295564288},{"benchmarkId":"allenai/olmOCR-bench","modelId":"rednote-hilab/dots.mocr","value":83.9,"lowerIsBetter":false,"percentile":85.71,"sourceName":"dots.mocr technical report","sourceUrl":"https://huggingface.co/papers/2603.13032","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":3039179264},{"benchmarkId":"allenai/olmOCR-bench","modelId":"datalab-to/surya-ocr-2","value":83.3,"lowerIsBetter":false,"percentile":78.57,"sourceName":"Surya OCR 2 Model Card","sourceUrl":"https://huggingface.co/datalab-to/surya-ocr-2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":686154304},{"benchmarkId":"allenai/olmOCR-bench","modelId":"lightonai/LightOnOCR-2-1B","value":83.2,"lowerIsBetter":false,"percentile":71.43,"sourceName":"LightOnOCR technical report","sourceUrl":"https://huggingface.co/papers/2601.14251","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"H&F rewards omission, not transcription thus a model that outputs nothing scores perfectly. Excluded to keep Overall focused on real OCR quality.","filename":".eval_results/olmocrbench.yaml","parameters":1005647872},{"benchmarkId":"allenai/olmOCR-bench","modelId":"datalab-to/chandra","value":83.1,"lowerIsBetter":false,"percentile":64.29,"sourceName":"OlmOCR-Bench Github repository","sourceUrl":"https://github.com/allenai/olmocr/tree/main/olmocr/bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":8767123696},{"benchmarkId":"allenai/olmOCR-bench","modelId":"infly/Infinity-Parser-7B","value":82.5,"lowerIsBetter":false,"percentile":57.14,"sourceName":"Infinity Parser technical report","sourceUrl":"https://huggingface.co/papers/2506.03197","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":8292166656},{"benchmarkId":"allenai/olmOCR-bench","modelId":"tiiuae/Falcon-OCR","value":80.3,"lowerIsBetter":false,"percentile":50,"sourceName":"Falcon-OCR Model Card","sourceUrl":"https://huggingface.co/tiiuae/Falcon-OCR","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"English-subset only","filename":".eval_results/olmocrbench.yaml","parameters":269944416},{"benchmarkId":"allenai/olmOCR-bench","modelId":"baidu/Qianfan-OCR","value":79.8,"lowerIsBetter":false,"percentile":42.86,"sourceName":"Qianfan-OCR technical report","sourceUrl":"https://huggingface.co/papers/2603.13398","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/olm_ocr_bench.yaml","parameters":4741408256},{"benchmarkId":"allenai/olmOCR-bench","modelId":"rednote-hilab/dots.ocr","value":79.1,"lowerIsBetter":false,"percentile":35.71,"sourceName":"dots.ocr technical report","sourceUrl":"https://huggingface.co/papers/2512.02498","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":3039179264},{"benchmarkId":"allenai/olmOCR-bench","modelId":"deepseek-ai/DeepSeek-OCR-2","value":76.3,"lowerIsBetter":false,"percentile":28.57,"sourceName":"Tweet by @staghado","sourceUrl":"https://x.com/staghado/status/2016161372938117205/photo/1","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":3389119360},{"benchmarkId":"allenai/olmOCR-bench","modelId":"lightonai/LightOnOCR-1B-1025","value":76.1,"lowerIsBetter":false,"percentile":21.43,"sourceName":"LightOnOCR technical report","sourceUrl":"https://huggingface.co/papers/2601.14251","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Excluding Headers & Footers category","filename":".eval_results/olmocrbench.yaml","parameters":1161230336},{"benchmarkId":"allenai/olmOCR-bench","modelId":"deepseek-ai/DeepSeek-OCR","value":75.7,"lowerIsBetter":false,"percentile":14.29,"sourceName":"OlmOCR-Bench Github repository","sourceUrl":"https://github.com/allenai/olmocr/tree/main/olmocr/bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":3336106240},{"benchmarkId":"allenai/olmOCR-bench","modelId":"opendatalab/MinerU2.5-2509-1.2B","value":75.2,"lowerIsBetter":false,"percentile":3.57,"sourceName":"MinerU2.5 technical report","sourceUrl":"https://huggingface.co/papers/2509.22186","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":1156026624},{"benchmarkId":"allenai/olmOCR-bench","modelId":"zai-org/GLM-OCR","value":75.2,"lowerIsBetter":false,"percentile":3.57,"sourceName":"GLM-OCR API evaluation","sourceUrl":"https://huggingface.co/zai-org/GLM-OCR","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Excluding Headers & Footers category. Using ZAI API.","filename":".eval_results/olmocrbench.yaml","parameters":1325258240},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5.2","value":54.7,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle.yaml","parameters":753329940480},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2.6","value":54,"lowerIsBetter":false,"percentile":97.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":1058589420528},{"benchmarkId":"cais/hle","modelId":"tencent/Hy3","value":53.2,"lowerIsBetter":false,"percentile":95,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":298786155776},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5.1","value":52.3,"lowerIsBetter":false,"percentile":92.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":753864139008},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5","value":50.4,"lowerIsBetter":false,"percentile":90,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":753864139008},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2.5","value":50.2,"lowerIsBetter":false,"percentile":87.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":1058589420528},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-27B","value":48.5,"lowerIsBetter":false,"percentile":85,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"with tools","filename":".eval_results/hle_with_tools_3.yaml","parameters":27781427952},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-397B-A17B","value":48.3,"lowerIsBetter":false,"percentile":82.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":403397928944},{"benchmarkId":"cais/hle","modelId":"stepfun-ai/Step-3.7-Flash","value":48.1,"lowerIsBetter":false,"percentile":80,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":201365316160},{"benchmarkId":"cais/hle","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":48,"lowerIsBetter":false,"percentile":77.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"with tools","filename":".eval_results/hle.yaml","parameters":1023244718976},{"benchmarkId":"cais/hle","modelId":"InternScience/Agents-A1","value":47.6,"lowerIsBetter":false,"percentile":75,"sourceName":"Agents-A1 model card","sourceUrl":"https://huggingface.co/InternScience/Agents-A1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/Agents-A1.yaml","parameters":35107181936},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-122B-A10B","value":47.5,"lowerIsBetter":false,"percentile":72.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"with tools","filename":".eval_results/hle_with_tools_4.yaml","parameters":125086497008},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2-Thinking","value":44.9,"lowerIsBetter":false,"percentile":70,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":1058118284416},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.7","value":42.8,"lowerIsBetter":false,"percentile":67.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":358337791296},{"benchmarkId":"cais/hle","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":37.7,"lowerIsBetter":false,"percentile":65,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":861608274846},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":37.4,"lowerIsBetter":false,"percentile":61.25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":560524578816},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":37.4,"lowerIsBetter":false,"percentile":61.25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":335038821080},{"benchmarkId":"cais/hle","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":34.8,"lowerIsBetter":false,"percentile":57.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":158069433298},{"benchmarkId":"cais/hle","modelId":"PolarSeeker/OpenSeeker-v2-30B-SFT","value":34.6,"lowerIsBetter":false,"percentile":55,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/PolarSeeker/OpenSeeker-v2-30B-SFT","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":30532122624},{"benchmarkId":"cais/hle","modelId":"tencent/Hy3-preview","value":30,"lowerIsBetter":false,"percentile":52.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3-preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Text-only","filename":".eval_results/hle.yaml","parameters":298786155776},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.6-27B","value":24,"lowerIsBetter":false,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":27781427952},{"benchmarkId":"cais/hle","modelId":"stepfun-ai/Step-3.5-Flash","value":23.1,"lowerIsBetter":false,"percentile":47.5,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Text Only","filename":".eval_results/hle.yaml","parameters":199384301376},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":22.82,"lowerIsBetter":false,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":123611012096},{"benchmarkId":"cais/hle","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":22.82,"lowerIsBetter":false,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":123611012096},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":22.82,"lowerIsBetter":false,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":22.82,"lowerIsBetter":false,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":22.82,"lowerIsBetter":false,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"MiniMaxAI/MiniMax-M2.1","value":22.2,"lowerIsBetter":false,"percentile":32.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":228703644928},{"benchmarkId":"cais/hle","modelId":"XiaomiMiMo/MiMo-V2-Flash","value":22.1,"lowerIsBetter":false,"percentile":30,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":309785318400},{"benchmarkId":"cais/hle","modelId":"internlm/Intern-S2-Preview","value":21.94,"lowerIsBetter":false,"percentile":27.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Text only","filename":".eval_results/hle.yaml","parameters":36098254656},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.6-35B-A3B","value":21.4,"lowerIsBetter":false,"percentile":25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":35951822704},{"benchmarkId":"cais/hle","modelId":"MiniMaxAI/MiniMax-M2.5","value":19.4,"lowerIsBetter":false,"percentile":22.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":228703644928},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-120b","value":19,"lowerIsBetter":false,"percentile":20,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high, With tools","filename":".eval_results/hle_high_with_tools.yaml","parameters":120412337472},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-20b","value":17.3,"lowerIsBetter":false,"percentile":17.5,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high, With tools","filename":".eval_results/hle_high_with_tools.yaml","parameters":21511953984},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.7-Flash","value":14.4,"lowerIsBetter":false,"percentile":15,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":31221488576},{"benchmarkId":"cais/hle","modelId":"LGAI-EXAONE/K-EXAONE-236B-A23B","value":13.6,"lowerIsBetter":false,"percentile":12.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":237099669632},{"benchmarkId":"cais/hle","modelId":"MiniMaxAI/MiniMax-M2","value":12.5,"lowerIsBetter":false,"percentile":10,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":228703644928},{"benchmarkId":"cais/hle","modelId":"HelpingAI/Dhanishtha-2.0-0126","value":9.92,"lowerIsBetter":false,"percentile":7.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/HelpingAI/Dhanishtha-2.0-0126","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":14768307200},{"benchmarkId":"cais/hle","modelId":"skt/A.X-K1","value":8.6,"lowerIsBetter":false,"percentile":5,"sourceName":"A.X K1 model card","sourceUrl":"https://huggingface.co/skt/A.X-K1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Humanity's Last Exam score reported in Thinking Mode.","filename":".eval_results/A.X-K1.yaml","parameters":518983059456},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.5","value":8.32,"lowerIsBetter":false,"percentile":2.5,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/93/cb/93cbdfdf-9ec6-4afb-87f4-d771cf29a378.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":358337791296},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.5-Air","value":8.12,"lowerIsBetter":false,"percentile":0,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/e9/03/e90308ab-e898-4434-aa93-13d131887737.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":110468824832},{"benchmarkId":"datacurve/deep-swe","modelId":"zai-org/GLM-5.2","value":46.2,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/deep-swe.yaml","parameters":753329940480},{"benchmarkId":"datacurve/deep-swe","modelId":"tencent/Hy3","value":28,"lowerIsBetter":false,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/deep-swe.yaml","parameters":298786155776},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-M2.1","value":88,"lowerIsBetter":false,"percentile":99.64,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/dd/c9/ddc99cec-f5d3-4cc4-9cc5-bb534377b5f6.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":228703644928},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/Intern-S2-Preview","value":88,"lowerIsBetter":false,"percentile":99.64,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":36098254656},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.5-397B-A17B","value":87.8,"lowerIsBetter":false,"percentile":98.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":403397928944},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":87.5,"lowerIsBetter":false,"percentile":97.84,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":861608274846},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"moonshotai/Kimi-K2.5","value":87.1,"lowerIsBetter":false,"percentile":97.12,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1058589420528},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":86.8,"lowerIsBetter":false,"percentile":96.04,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":560524578816},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":86.8,"lowerIsBetter":false,"percentile":96.04,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":335038821080},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.5-122B-A10B","value":86.7,"lowerIsBetter":false,"percentile":94.96,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/af/3c/af3c554a-1eb9-4a79-80dd-678c7aebf0aa.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":125086497008},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":86.4,"lowerIsBetter":false,"percentile":94.24,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":158069433298},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.6-27B","value":86.2,"lowerIsBetter":false,"percentile":93.53,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":27781427952},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.5-27B","value":86.1,"lowerIsBetter":false,"percentile":92.81,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/15/df/15df0778-3ca6-4ff9-9b34-41f74dc4ced4.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":27781427952},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"zai-org/GLM-5","value":86,"lowerIsBetter":false,"percentile":92.09,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/76/7d/767d7365-4f30-4ac0-9fc4-e0ade16a161f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":753864139008},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.6-35B-A3B","value":85.2,"lowerIsBetter":false,"percentile":91.37,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":35951822704},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-R1-0528","value":85,"lowerIsBetter":false,"percentile":90.65,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":684531386000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"zai-org/GLM-4.5","value":84.6,"lowerIsBetter":false,"percentile":89.93,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/04/c7/04c77f44-dff1-4cc7-80a1-35f4e9e9237f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":358337791296},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"stepfun-ai/Step-3.5-Flash","value":84.4,"lowerIsBetter":false,"percentile":89.21,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":199384301376},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-R1","value":84,"lowerIsBetter":false,"percentile":88.49,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":684531386000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/K-EXAONE-236B-A23B","value":83.8,"lowerIsBetter":false,"percentile":87.77,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":237099669632},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":83.73,"lowerIsBetter":false,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":123611012096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":83.73,"lowerIsBetter":false,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":123611012096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":83.73,"lowerIsBetter":false,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":120668707840},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":83.73,"lowerIsBetter":false,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":120668707840},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":83.73,"lowerIsBetter":false,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":120668707840},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/Intern-S1","value":83.5,"lowerIsBetter":false,"percentile":83.45,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4a/0a/4a0a0ab9-bb59-411e-a406-f6ac49a1e9f1.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":240709856128},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/EXAONE-4.5-33B","value":83.3,"lowerIsBetter":false,"percentile":82.73,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":34350097664},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-235B-A22B-Instruct-2507","value":83,"lowerIsBetter":false,"percentile":82.01,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/df/98/df9861f7-59cf-4b5e-8988-571481f47d14.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":235093634560},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ByteDance-Seed/Seed-OSS-36B-Instruct","value":82.7,"lowerIsBetter":false,"percentile":80.94,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/1b/40/1b405e01-7137-4189-b5d2-83e0f4004dc9.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":36151104512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meituan-longcat/LongCat-Flash-Chat","value":82.7,"lowerIsBetter":false,"percentile":80.94,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/19/91/1991ed80-048e-428c-a9f7-e32c71bd65ea.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":561862880256},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-M2","value":82,"lowerIsBetter":false,"percentile":79.86,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":228703644928},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"skt/A.X-K1","value":81.5,"lowerIsBetter":false,"percentile":79.14,"sourceName":"A.X K1 model card","sourceUrl":"https://huggingface.co/skt/A.X-K1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"English MMLU-Pro score reported in Thinking Mode.","filename":".eval_results/A.X-K1.yaml","parameters":518983059456},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"zai-org/GLM-4.5-Air","value":81.4,"lowerIsBetter":false,"percentile":78.42,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/07/43/074397da-f5e5-441c-bc45-ac16b599ca7c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":110468824832},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V3-0324","value":81.2,"lowerIsBetter":false,"percentile":77.7,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":684531386000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-M1-40k","value":81.1,"lowerIsBetter":false,"percentile":76.98,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/3b/7b/3b7bfaac-ee52-4508-8ecd-676d82e06c1c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":456089655296},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"jdopensource/JoyAI-LLM-Flash","value":81.02,"lowerIsBetter":false,"percentile":76.26,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/jdopensource/JoyAI-LLM-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":49286094592},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"moonshotai/Kimi-K2-Instruct","value":81,"lowerIsBetter":false,"percentile":75.54,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4a/ae/4aae2732-e24b-42a2-9dc1-a35cd215a8ec.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1026470731056},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-30B-A3B-Thinking-2507","value":80.9,"lowerIsBetter":false,"percentile":74.82,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/46/a3/46a34cab-9475-40a1-ba07-2c0528f6bf5d.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":30532122624},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"openai/gpt-oss-120b","value":80.8,"lowerIsBetter":false,"percentile":74.1,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/e4/8d/e48dbb1a-9e1a-4c99-abbf-cb32942b48e7.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":120412337472},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-M2.5","value":80.1,"lowerIsBetter":false,"percentile":73.38,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/c5/4c/c54c4ee8-ff99-4cda-a81f-a2e3a4347fb8.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":228703644928},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"baidu/ERNIE-4.5-300B-A47B-PT","value":78.4,"lowerIsBetter":false,"percentile":72.66,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/e6/6b/e66bffdc-f3d1-4808-90a4-43f204aa883e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":300474051776},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meituan-longcat/LongCat-Flash-Lite","value":78.29,"lowerIsBetter":false,"percentile":71.94,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":69073335552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-Text-01","value":75.7,"lowerIsBetter":false,"percentile":71.22,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/2a/73/2a734d0f-7fcf-48d0-bea6-ad17cd749ee4.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":456089655296},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"openai/gpt-oss-20b","value":73.6,"lowerIsBetter":false,"percentile":70.5,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ca/ef/caef6dbc-0f07-4491-9009-2b0d26dc9724.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":21511953984},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-72B","value":71.59,"lowerIsBetter":false,"percentile":69.78,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/06/60/06600438-ea9f-4078-8eef-701c59af71a4.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":72706203648},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/phi-4","value":70.4,"lowerIsBetter":false,"percentile":69.06,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/c2/37/c23724de-5d83-4794-abcb-9af3ce249886.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":14659507200},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-4B-Instruct-2507","value":69.6,"lowerIsBetter":false,"percentile":68.35,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":4022468096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"baidu/ERNIE-4.5-300B-A47B-Base-PT","value":69.5,"lowerIsBetter":false,"percentile":67.63,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/bc/f1/bcf18d24-d600-4ed9-ba95-73f8d58569e1.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":299484163264},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-32B","value":69.23,"lowerIsBetter":false,"percentile":66.91,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/da/c5/dac51285-4928-4ac7-b052-510e4705981b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":32763876352},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":68.5,"lowerIsBetter":false,"percentile":66.19,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":1023244718976},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-235B-A22B","value":68.18,"lowerIsBetter":false,"percentile":65.47,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/99/98/99989790-84de-4fd9-af37-1d9c28dd95b3.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":235093634560},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Large-Instruct-2411","value":67.94,"lowerIsBetter":false,"percentile":64.75,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/03/98/03985ef7-288d-4421-9257-ce6b77dcd858.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":122610069504},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"tencent/Hunyuan-A13B-Instruct","value":67.3,"lowerIsBetter":false,"percentile":64.03,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4b/ff/4bffdd42-60c3-41a9-9ef8-e5849e114d9e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":80393183232},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Large-Instruct-2407","value":65.91,"lowerIsBetter":false,"percentile":63.31,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b7/99/b799f854-5a9c-413c-b766-ab127e0cd103.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":122610069504},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V2.5","value":65.83,"lowerIsBetter":false,"percentile":62.59,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/65/c2/65c29cb3-af56-45f1-be1b-751630185a59.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":235741434880},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ByteDance-Seed/Seed-OSS-36B-Base","value":65.1,"lowerIsBetter":false,"percentile":61.51,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/cf/2d/cf2d98c9-1e57-4994-9e49-9a7962a2706d.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":36151104512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16","value":65.1,"lowerIsBetter":false,"percentile":61.51,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/2a/e5/2ae5bb55-f5e3-4aa2-beef-141f450a4562.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":31577937344},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V3","value":64.4,"lowerIsBetter":false,"percentile":60.43,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":684531386000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-4.1-30b","value":64.09,"lowerIsBetter":false,"percentile":59.71,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-30b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":28865728512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-14B","value":63.69,"lowerIsBetter":false,"percentile":58.99,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/cc/7c/cc7c2263-9baf-45fc-b58b-64c15989e358.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":14770033664},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-30B-A3B-Base","value":61.7,"lowerIsBetter":false,"percentile":58.27,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/74/e6/74e614fc-75a5-4f12-b077-cbf525141a9f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":30532122624},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.1-405B","value":61.6,"lowerIsBetter":false,"percentile":57.55,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/50/a3/50a33ec6-cf9b-4acc-9f45-61cd8356207c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":405853388800},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/Nemotron-H-56B-Base-8K","value":60.5,"lowerIsBetter":false,"percentile":56.83,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/8b/b3/8bb31817-e160-4285-a781-272851ae2c41.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":56324350464},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ByteDance-Seed/Seed-OSS-36B-Base-woSyn","value":60.4,"lowerIsBetter":false,"percentile":56.12,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/60/1d/601d782d-660b-4f01-bcae-5c4105223c85.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":36151104512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"tencent/Tencent-Hunyuan-Large","value":60.2,"lowerIsBetter":false,"percentile":55.4,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5c/9f/5c9f18ed-3247-4af2-b44f-2a504735554b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":null},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"JetBrains/Mellum2-12B-A2.5B-Base-Pretrain","value":59.31,"lowerIsBetter":false,"percentile":54.32,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval, no-tools, exact match","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"JetBrains/Mellum2-12B-A2.5B-Base","value":59.31,"lowerIsBetter":false,"percentile":54.32,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval (pre-YaRN), no-tools, exact match","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/EXAONE-3.5-32B-Instruct","value":58.91,"lowerIsBetter":false,"percentile":53.24,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/de/c9/dec9e4cf-cc67-42e1-9474-f8de9048014b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":32003200000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"XiaomiMiMo/MiMo-7B-RL","value":58.6,"lowerIsBetter":false,"percentile":52.52,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/eb/b6/ebb62699-a109-4160-9f12-152a17ac9c5b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7833409536},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/internlm3-8b-instruct","value":57.6,"lowerIsBetter":false,"percentile":51.8,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/46/a7/46a7e0d0-c351-46ac-99f0-98aebcf3fef7.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8804241408},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"baidu/ERNIE-4.5-21B-A3B-Base-PT","value":56.7,"lowerIsBetter":false,"percentile":51.08,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5d/0e/5d0edbf1-b369-43eb-b885-d5a87c818d1f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":21825437888},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-4.1-8b","value":55.99,"lowerIsBetter":false,"percentile":50.36,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-8b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8791592960},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3-medium-4k-instruct","value":55.7,"lowerIsBetter":false,"percentile":49.64,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/63/f9/63f9e7e6-d69f-4522-a81d-7280eacf730c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":13960238080},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V2-Chat","value":54.81,"lowerIsBetter":false,"percentile":48.92,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/a7/68/a768afc2-e0b4-4ea5-ba40-166136c33b3b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":235741434880},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Small-24B-Base-2501","value":54.4,"lowerIsBetter":false,"percentile":48.2,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/d4/89/d489ea6c-1287-43bd-aa64-5193c09331b2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":23572403200},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-4-mini-instruct","value":52.8,"lowerIsBetter":false,"percentile":47.48,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b2/6e/b26e73bc-2a30-4fa4-8223-148df3d82658.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3836021760},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Meta-Llama-3-70B","value":52.78,"lowerIsBetter":false,"percentile":46.76,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/77/50/77508bc1-dc52-4a84-9df1-deb62975c053.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":70553706496},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.1-70B","value":52.47,"lowerIsBetter":false,"percentile":46.04,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/3b/18/3b18649e-fd29-4193-a8c1-6d6d93d1ebd2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":70553706496},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-1.5-34B-Chat","value":52.29,"lowerIsBetter":false,"percentile":45.32,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/67/6f/676f4465-ce78-411a-9f5a-c97b3d2eac4f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":34388917248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3-medium-128k-instruct","value":51.91,"lowerIsBetter":false,"percentile":44.6,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/22/1e/221e4697-1155-4d8d-87df-9778573a3ad7.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":13960238080},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"TIGER-Lab/MAmmoTH2-8x7B-Plus","value":50.4,"lowerIsBetter":false,"percentile":43.88,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/17/d1/17d1bf78-2fbe-414d-b555-6d672f57ddf2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":46702792704},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen1.5-110B","value":49.93,"lowerIsBetter":false,"percentile":43.17,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/33/3e/333e0d9f-7e39-4da3-96cb-0501d2380c03.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":111209914368},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-4.1-3b","value":49.83,"lowerIsBetter":false,"percentile":42.45,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-3b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3402836480},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ai21labs/AI21-Jamba-Large-1.5","value":49.46,"lowerIsBetter":false,"percentile":41.73,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/aa/2b/aa2be737-1a21-4cc9-93f2-83316b7dc0cd.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":398555145696},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Small-Instruct-2409","value":48.4,"lowerIsBetter":false,"percentile":41.01,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/71/31/7131c1f0-8fce-4050-8117-51d9b5e651ca.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":22247282688},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"zai-org/glm-4-9b","value":47.92,"lowerIsBetter":false,"percentile":40.29,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/92/ff/92ff34d6-a9d7-48af-a31e-a72c2367edff.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":9399951392},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3.5-mini-instruct","value":47.87,"lowerIsBetter":false,"percentile":39.57,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/03/b7/03b77a5a-1723-4cab-9d50-1a634bf8b06a.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3821079552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct","value":46.24,"lowerIsBetter":false,"percentile":38.85,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/c6/8f/c68fc694-d6dd-4b2a-a699-e5f737ae550f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7818448896},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-1.5-9B-Chat","value":45.95,"lowerIsBetter":false,"percentile":38.13,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/94/9e/949ec028-f03f-4211-8783-c810af6489a4.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8829407232},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3-mini-4k-instruct","value":45.66,"lowerIsBetter":false,"percentile":37.41,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/05/3a/053a7b11-0d89-4289-bfe4-ed3eca7c4a97.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3821079552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"CohereLabs/aya-expanse-32b","value":45.41,"lowerIsBetter":false,"percentile":36.69,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/12/29/1229c8e0-d21f-43e8-a9c7-3ea0d09408d5.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":32296476672},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"google/gemma-2-9b","value":45.1,"lowerIsBetter":false,"percentile":35.97,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/76/6f/766fb522-5c40-49f9-bcad-bd5496404129.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":9241705984},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-7B","value":45,"lowerIsBetter":false,"percentile":35.25,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/0c/64/0c645bb3-1e9c-4400-a704-f99748356114.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7615616512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3-mini-128k-instruct","value":43.86,"lowerIsBetter":false,"percentile":34.53,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ab/4d/ab4d706d-1629-46ac-8db3-cb6fac6de332.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3821079552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-3B","value":43.73,"lowerIsBetter":false,"percentile":33.81,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ed/3a/ed3af7f3-5881-4ddd-bab1-75ecda64c98e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3085938688},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"TIGER-Lab/MAmmoTH2-8B-Plus","value":43.35,"lowerIsBetter":false,"percentile":33.09,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/1f/96/1f963bf0-4985-4d1f-a322-55865369de75.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-34B","value":43.03,"lowerIsBetter":false,"percentile":32.37,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9d/42/9d42931c-6ec3-48ac-ae0a-cebb9c1f68aa.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":34388917248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mathstral-7B-v0.1","value":42,"lowerIsBetter":false,"percentile":31.65,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b7/6c/b76c036b-b67b-4dd4-9c7f-d1938b83f254.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7248023552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"XiaomiMiMo/MiMo-7B-Base","value":41.9,"lowerIsBetter":false,"percentile":30.94,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/67/a9/67a990d8-bf28-4d9e-94b8-a472bde1efbd.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7833409536},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct","value":41.57,"lowerIsBetter":false,"percentile":30.22,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/0c/0f/0c0f446a-6c2a-47c7-a120-4fafb90f92a3.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":15706484224},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mixtral-8x7B-v0.1","value":41.03,"lowerIsBetter":false,"percentile":29.5,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/2b/dd/2bddced4-34a8-4a1c-b582-90bfe03346f1.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":46702792704},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Meta-Llama-3-8B-Instruct","value":40.98,"lowerIsBetter":false,"percentile":28.78,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/3c/1f/3c1f9257-27aa-4da0-b772-60d62242a72b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"TIGER-Lab/MAmmoTH2-7B-Plus","value":40.85,"lowerIsBetter":false,"percentile":28.06,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/1b/16/1b16feea-1def-49ae-b3da-ee3af193a705.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7241732096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2-7B","value":40.73,"lowerIsBetter":false,"percentile":27.34,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/37/79/3779cfdb-412d-49fa-94d4-5c7ae1af8ac6.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7615616512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Nemo-Base-2407","value":39.77,"lowerIsBetter":false,"percentile":26.62,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/be/91/be919504-16fb-4669-8d9b-3bfdfd2e6364.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":12247782400},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct","value":39.1,"lowerIsBetter":false,"percentile":25.9,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ce/1a/ce1a8a1a-5d16-4403-9e85-bf0f3d72f09f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":2405327360},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-1.5-6B-Chat","value":38.23,"lowerIsBetter":false,"percentile":25.18,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/bd/05/bd056a61-8ede-45b4-823d-093343bdd880.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":6061035520},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen1.5-14B-Chat","value":38.02,"lowerIsBetter":false,"percentile":24.46,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/09/ca/09ca61cf-1158-46e6-aeae-1d68f5dfbc34.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":14167290880},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Ministral-8B-Instruct-2410","value":37.93,"lowerIsBetter":false,"percentile":23.74,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b0/f5/b0f59e78-883f-4c57-b728-b983c859f23f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8019808256},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"CohereLabs/c4ai-command-r-v01","value":37.9,"lowerIsBetter":false,"percentile":23.02,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b3/5f/b35fcd95-c193-4ed0-b50c-bc535af5756f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":34980831232},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/internlm2-math-plus-20b","value":37.1,"lowerIsBetter":false,"percentile":22.3,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/6f/ee/6fee4d03-47d0-4c2e-b449-978442fa002c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":19861149696},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"GSAI-ML/LLaDA-8B-Instruct","value":37,"lowerIsBetter":false,"percentile":21.58,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/67/cc/67cc35fb-ae5a-4632-91da-9346a6b2849e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8015581184},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"abacusai/Llama-3-Smaug-8B","value":36.93,"lowerIsBetter":false,"percentile":20.86,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b0/a9/b0a990c3-c1a2-4a69-abed-e1c2c51d8763.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.1-8B","value":36.6,"lowerIsBetter":false,"percentile":20.14,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/45/ba/45baf8ce-a6cc-412f-a134-2242a4af4c93.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Meta-Llama-3-8B","value":35.36,"lowerIsBetter":false,"percentile":19.42,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ac/75/ac75fe42-62e5-4ea9-a130-1eeacc8e9fb2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/deepseek-math-7b-instruct","value":35.3,"lowerIsBetter":false,"percentile":18.71,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/65/7f/657f147a-6450-42fe-a10d-e626f9000d29.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":null},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-Coder-V2-Lite-Base","value":34.37,"lowerIsBetter":false,"percentile":17.99,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/1a/c8/1ac85691-ef95-4bf5-8618-6bac456e2792.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":15706484224},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"CohereLabs/aya-expanse-8b","value":33.74,"lowerIsBetter":false,"percentile":17.27,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/33/5b/335b15a4-a7fd-4ffc-81db-9d5feed90657.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8028033024},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/internlm2-math-plus-7b","value":33.5,"lowerIsBetter":false,"percentile":16.55,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/37/20/37203543-7ca5-4441-be5c-e4cbd12293c2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7737708544},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.1-8b-base","value":33.08,"lowerIsBetter":false,"percentile":15.83,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5b/c9/5bc90039-eb1c-4772-aa34-1cfb7c2343b6.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8170835968},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-1.5B","value":32.1,"lowerIsBetter":false,"percentile":15.11,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/e1/d5/e1d5921c-130a-44f8-ae14-baed069e565e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1543714304},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.0-8b-base","value":31.03,"lowerIsBetter":false,"percentile":14.39,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/d9/f9/d9f9b73a-5b6d-418b-8f26-f89b4d2b6792.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8170835968},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-7B-Instruct-v0.2","value":30.84,"lowerIsBetter":false,"percentile":13.67,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9d/8d/9d8dc94b-067c-478d-aa99-874b71721fc3.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7241732096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistral-community/Mistral-7B-v0.2","value":30.43,"lowerIsBetter":false,"percentile":12.95,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/93/21/9321cec5-309d-4328-aa2c-709af17cff9c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7241732096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen1.5-7B-Chat","value":29.06,"lowerIsBetter":false,"percentile":12.23,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/db/e1/dbe12346-25db-4fac-9421-5153fc4c661c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7721324544},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-6B-Chat","value":28.84,"lowerIsBetter":false,"percentile":11.51,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/28/1d/281df2d2-60b5-4053-b30e-bba4976c3efd.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":6061035520},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-6B","value":26.51,"lowerIsBetter":false,"percentile":10.79,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/8b/02/8b02ff6f-b3ae-4230-8edd-50c3ffa34592.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":6061035520},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.1-2b-base","value":23.89,"lowerIsBetter":false,"percentile":10.07,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/d4/c0/d4c06d3d-8a53-44e5-9db6-ebffc99390d2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":2533525504},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"EleutherAI/llemma_7b","value":23.45,"lowerIsBetter":false,"percentile":9.35,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/f0/87/f087fc33-d4b9-4939-b3cf-2d3fb9094177.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":null},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2-1.5B-Instruct","value":22.62,"lowerIsBetter":false,"percentile":8.63,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/18/ea/18ea6501-7d93-4ec4-bd82-86991bb5cc68.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1543714304},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2-1.5B","value":22.56,"lowerIsBetter":false,"percentile":7.91,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ff/fc/fffc978a-e6ae-41f2-bded-06bb776ee8b9.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1543714304},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.2-3B","value":22.17,"lowerIsBetter":false,"percentile":7.19,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/91/89/9189a395-7ef2-453e-84e0-259870efc2f7.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3212749824},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.0-2b-base","value":21.72,"lowerIsBetter":false,"percentile":6.47,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/06/7f/067fe2c1-7ba3-4f79-8344-e55e999ae537.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":2533525504},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.1-3b-a800m-base","value":20.39,"lowerIsBetter":false,"percentile":5.76,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/a9/31/a931868f-9ae1-4cd5-a2a7-8ea402101bbe.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3298788864},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"HuggingFaceTB/SmolLM2-1.7B","value":18.31,"lowerIsBetter":false,"percentile":5.04,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/33/c9/33c9180c-621e-40a2-bb6f-02b90ecff1fd.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1711376384},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2-0.5B","value":14.97,"lowerIsBetter":false,"percentile":4.32,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/85/72/8572a257-22bc-45c5-8891-d698ba6fc206.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":494032768},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-0.5B","value":14.92,"lowerIsBetter":false,"percentile":3.6,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5b/03/5b03aafd-e973-4ea4-850c-2ab97c1abb27.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":494032768},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.1-1b-a400m-base","value":12.34,"lowerIsBetter":false,"percentile":2.88,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4a/f2/4af2fd82-845a-4087-83eb-ae9b4b7561d1.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1334625280},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.2-1B","value":11.95,"lowerIsBetter":false,"percentile":2.16,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/d5/a3/d5a3c88a-3fee-40b3-a8c7-8c4cc65baf5f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1235814400},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"HuggingFaceTB/SmolLM2-360M","value":11.38,"lowerIsBetter":false,"percentile":1.44,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/23/ae/23aee40b-5bea-46cf-a87b-8263e12e2d1f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":361821120},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"HuggingFaceTB/SmolLM2-135M","value":10.85,"lowerIsBetter":false,"percentile":0.72,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ac/90/ac90804d-cb99-41cc-b3e7-65ed31484008.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":134515008},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-VL-72B-Instruct","value":0.6494348404255319,"lowerIsBetter":false,"percentile":0,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9c/45/9c455b8c-1153-4c24-9de0-1d506297d805.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":73410777344},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"deepreinforce-ai/Ornith-1.0-397B","value":62.2,"lowerIsBetter":false,"percentile":100,"sourceName":"Ornith-1.0-397B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-397B.yaml","parameters":396802360816},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"zai-org/GLM-5.2","value":62.1,"lowerIsBetter":false,"percentile":96.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":753329940480},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MiniMaxAI/MiniMax-M3","value":59,"lowerIsBetter":false,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Testing logic is aligned with the official evaluation.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":59,"lowerIsBetter":false,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Testing logic is aligned with the official evaluation.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":59,"lowerIsBetter":false,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Testing logic is aligned with the official evaluation.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"moonshotai/Kimi-K2.6","value":58.6,"lowerIsBetter":false,"percentile":83.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":1058589420528},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"zai-org/GLM-5.1","value":58.4,"lowerIsBetter":false,"percentile":80,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"high reasoning","filename":".eval_results/swe_bench_pro.yaml","parameters":753864139008},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"tencent/Hy3","value":57.9,"lowerIsBetter":false,"percentile":76.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":298786155776},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":57.2,"lowerIsBetter":false,"percentile":73.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":1023244718976},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"stepfun-ai/Step-3.7-Flash","value":56.3,"lowerIsBetter":false,"percentile":70,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":201365316160},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MiniMaxAI/MiniMax-M2.7","value":56.2,"lowerIsBetter":false,"percentile":66.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":228703644928},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"XiaomiMiMo/MiMo-V2.5","value":56.1,"lowerIsBetter":false,"percentile":63.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":310775040000},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MiniMaxAI/MiniMax-M2.5","value":55.4,"lowerIsBetter":false,"percentile":58.33,"sourceName":"Model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":228703644928},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":55.4,"lowerIsBetter":false,"percentile":58.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":861608274846},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3.6-27B","value":53.5,"lowerIsBetter":false,"percentile":53.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":27781427952},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"moonshotai/Kimi-K2.5","value":50.7,"lowerIsBetter":false,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":1058589420528},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"deepreinforce-ai/Ornith-1.0-35B","value":50.4,"lowerIsBetter":false,"percentile":46.67,"sourceName":"Ornith-1.0-35B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-35B.yaml","parameters":664944},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3.6-35B-A3B","value":49.5,"lowerIsBetter":false,"percentile":43.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":35951822704},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"poolside/Laguna-M.1","value":49.2,"lowerIsBetter":false,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-M.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":225795725568},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"poolside/Laguna-XS-2.1","value":47.6,"lowerIsBetter":false,"percentile":36.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":33442617088},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"poolside/Laguna-XS.2","value":46.3,"lowerIsBetter":false,"percentile":33.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":33442617088},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MuVeraAI/Laguna-XS.2","value":44.5,"lowerIsBetter":false,"percentile":30,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":33442617088},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3-Coder-Next","value":44.3,"lowerIsBetter":false,"percentile":26.67,"sourceName":"Qwen3-Coder-Next technical report","sourceUrl":"https://huggingface.co/papers/2603.00729","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"SWE-Agent as harness","filename":".eval_results/.eval_results/swe_bench_pro.yaml","parameters":79674391296},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"deepreinforce-ai/Ornith-1.0-9B","value":42.9,"lowerIsBetter":false,"percentile":23.33,"sourceName":"Ornith-1.0-9B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-9B.yaml","parameters":1469680},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"CohereLabs/North-Mini-Code-1.0","value":40.2,"lowerIsBetter":false,"percentile":20,"sourceName":"North Mini Code Model Page","sourceUrl":"https://huggingface.co/CohereLabs/North-Mini-Code-1.0","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/swe-bench-pro.yaml","parameters":30484303872},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct","value":38.7,"lowerIsBetter":false,"percentile":16.67,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":480154875392},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MiniMaxAI/MiniMax-M2.1","value":36.81,"lowerIsBetter":false,"percentile":13.33,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":228703644928},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"moonshotai/Kimi-K2-Instruct","value":27.67,"lowerIsBetter":false,"percentile":10,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":1026470731056},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3-235B-A22B","value":21.41,"lowerIsBetter":false,"percentile":6.67,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":235093634560},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"openai/gpt-oss-120b","value":16.2,"lowerIsBetter":false,"percentile":3.33,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":120412337472},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"zai-org/GLM-4.6","value":9.67,"lowerIsBetter":false,"percentile":0,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":356785898816},{"benchmarkId":"mercor/apex-agents","modelId":"MiniMaxAI/MiniMax-M3","value":27.7,"lowerIsBetter":false,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on the apex-agents benchmark.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"mercor/apex-agents","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":27.7,"lowerIsBetter":false,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on the apex-agents benchmark.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"mercor/apex-agents","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":27.7,"lowerIsBetter":false,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on the apex-agents benchmark.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"mercor/apex-agents","modelId":"tencent/Hy3","value":25.6,"lowerIsBetter":false,"percentile":70,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/apex-agents.yaml","parameters":298786155776},{"benchmarkId":"mercor/apex-agents","modelId":"zai-org/GLM-5","value":17.2,"lowerIsBetter":false,"percentile":60,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: thinking","filename":".eval_results/apex-agents.yaml","parameters":753864139008},{"benchmarkId":"mercor/apex-agents","modelId":"moonshotai/Kimi-K2.5","value":14.4,"lowerIsBetter":false,"percentile":50,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: thinking","filename":".eval_results/apex-agents.yaml","parameters":1058589420528},{"benchmarkId":"mercor/apex-agents","modelId":"Qwen/Qwen3.5-397B-A17B","value":13.6,"lowerIsBetter":false,"percentile":40,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: thinking","filename":".eval_results/apex-agents.yaml","parameters":403397928944},{"benchmarkId":"mercor/apex-agents","modelId":"MiniMaxAI/MiniMax-M2.5","value":6.2,"lowerIsBetter":false,"percentile":30,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: high","filename":".eval_results/apex-agents.yaml","parameters":228703644928},{"benchmarkId":"mercor/apex-agents","modelId":"moonshotai/Kimi-K2-Instruct","value":4.1,"lowerIsBetter":false,"percentile":20,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: thinking","filename":".eval_results/apex-agents.yaml","parameters":1026470731056},{"benchmarkId":"mercor/apex-agents","modelId":"zai-org/GLM-4.6","value":4,"lowerIsBetter":false,"percentile":10,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: high","filename":".eval_results/apex-agents.yaml","parameters":356785898816},{"benchmarkId":"mercor/apex-agents","modelId":"zai-org/GLM-4.7","value":3.1,"lowerIsBetter":false,"percentile":0,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: high","filename":".eval_results/apex-agents.yaml","parameters":358337791296},{"benchmarkId":"benchflow/skillsbench","modelId":"zai-org/GLM-5.1","value":58.4,"lowerIsBetter":false,"percentile":100,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":753864139008},{"benchmarkId":"benchflow/skillsbench","modelId":"tencent/Hy3","value":55.3,"lowerIsBetter":false,"percentile":85.71,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/skillsbench.yaml","parameters":298786155776},{"benchmarkId":"benchflow/skillsbench","modelId":"moonshotai/Kimi-K2.6","value":54,"lowerIsBetter":false,"percentile":71.43,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":1058589420528},{"benchmarkId":"benchflow/skillsbench","modelId":"MiniMaxAI/MiniMax-M3","value":53,"lowerIsBetter":false,"percentile":57.14,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":427040140160},{"benchmarkId":"benchflow/skillsbench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":50.1,"lowerIsBetter":false,"percentile":42.86,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":861608274846},{"benchmarkId":"benchflow/skillsbench","modelId":"Qwen/Qwen3.6-27B","value":48.2,"lowerIsBetter":false,"percentile":28.57,"sourceName":"Qwen3.6-27B model card — Benchmark Results (Language > Coding Agent)","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"SkillsBench Avg5. Evaluated via OpenCode on 78 tasks (self-contained subset, excluding API-dependent tasks); avg of 5 runs. Mapped to the Hub's benchflow/skillsbench task skillsbench_v1_1.","filename":".eval_results/Qwen3.6-27B.yaml","parameters":27781427952},{"benchmarkId":"benchflow/skillsbench","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":44.7,"lowerIsBetter":false,"percentile":14.29,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":158069433298},{"benchmarkId":"benchflow/skillsbench","modelId":"MiniMaxAI/MiniMax-M2.7","value":34.9,"lowerIsBetter":false,"percentile":0,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":228703644928},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5.2","value":91.2,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":753329940480},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-398B-JGOS","value":90.9,"lowerIsBetter":false,"percentile":98.68,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-398B-JGOS","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"greedy decoding (temperature=0), single-sample (no voting / no test-time engine), max_tokens=16384, options shuffled seed=42; hardware: NVIDIA B200 x6 (TP2 x PP3), vLLM bfloat16","filename":".eval_results/gpqa_diamond.yaml","parameters":403397928944},{"benchmarkId":"Idavidrein/gpqa","modelId":"moonshotai/Kimi-K2.6","value":90.5,"lowerIsBetter":false,"percentile":97.37,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":1058589420528},{"benchmarkId":"Idavidrein/gpqa","modelId":"tencent/Hy3","value":90.4,"lowerIsBetter":false,"percentile":96.05,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":298786155776},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":90.1,"lowerIsBetter":false,"percentile":94.74,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":861608274846},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-28B-REASON","value":89.39,"lowerIsBetter":false,"percentile":93.42,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-28B-REASON","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Darwin-DELPHI test-time engine, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":26895998464},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.5-397B-A17B","value":88.4,"lowerIsBetter":false,"percentile":91.45,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":403397928944},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-36B-Opus","value":88.4,"lowerIsBetter":false,"percentile":91.45,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-36B-Opus","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Standard inference, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":34660610688},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-60B-DUO","value":88.38,"lowerIsBetter":false,"percentile":89.47,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-60B-DUO","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"DELPHI cascade system, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":null},{"benchmarkId":"Idavidrein/gpqa","modelId":"inclusionAI/Ring-2.6-1T","value":88.27,"lowerIsBetter":false,"percentile":88.16,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ring-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"xhigh reasoning effort, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":1025657871744},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":88.1,"lowerIsBetter":false,"percentile":86.84,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":158069433298},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":87.9,"lowerIsBetter":false,"percentile":85.53,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"No tools","filename":".eval_results/gpqa.yaml","parameters":335038821080},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.7-FP8","value":87.8787878788,"lowerIsBetter":false,"percentile":84.21,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/97/fa/97faabc6-a7ca-4cad-8d29-307103287d91.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":358458391872},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.6-27B","value":87.8,"lowerIsBetter":false,"percentile":82.89,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":27781427952},{"benchmarkId":"Idavidrein/gpqa","modelId":"moonshotai/Kimi-K2.5","value":87.6,"lowerIsBetter":false,"percentile":81.58,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":1058589420528},{"benchmarkId":"Idavidrein/gpqa","modelId":"tencent/Hy3-preview","value":87.2,"lowerIsBetter":false,"percentile":80.26,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3-preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":298786155776},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":87,"lowerIsBetter":false,"percentile":78.95,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"No tools","filename":".eval_results/gpqa.yaml","parameters":560524578816},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-27B-Opus","value":86.9,"lowerIsBetter":false,"percentile":77.63,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-27B-Opus","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Standard inference, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":27781427952},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.5-122B-A10B","value":86.6,"lowerIsBetter":false,"percentile":76.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_1.yaml","parameters":125086497008},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5.1","value":86.2,"lowerIsBetter":false,"percentile":75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":753864139008},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5","value":86,"lowerIsBetter":false,"percentile":73.03,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":753864139008},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.6-35B-A3B","value":86,"lowerIsBetter":false,"percentile":73.03,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":35951822704},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-31B-Opus","value":85.9,"lowerIsBetter":false,"percentile":71.05,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-31B-Opus","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Standard inference, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":32682372656},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.7","value":85.7,"lowerIsBetter":false,"percentile":69.74,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":358337791296},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.5-27B","value":85.5,"lowerIsBetter":false,"percentile":68.42,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_1.yaml","parameters":27781427952},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5-FP8","value":85.3535353535,"lowerIsBetter":false,"percentile":67.11,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/8a/87/8a87d622-4abb-48a7-8ac3-594e31a85525.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":753910024032},{"benchmarkId":"Idavidrein/gpqa","modelId":"MiniMaxAI/MiniMax-M2.5","value":85.2,"lowerIsBetter":false,"percentile":65.79,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":228703644928},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-4B-David","value":85,"lowerIsBetter":false,"percentile":64.47,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-4B-David","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"4B class Gen-2 evolution, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":7996156490},{"benchmarkId":"Idavidrein/gpqa","modelId":"moonshotai/Kimi-K2-Thinking","value":84.5,"lowerIsBetter":false,"percentile":63.16,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":1058118284416},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-9B-NEG","value":84.34,"lowerIsBetter":false,"percentile":61.18,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-9B-NEG","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"9B class, standard inference, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":9653104368},{"benchmarkId":"Idavidrein/gpqa","modelId":"JGOS-Model/JGOS-31B-Citizen","value":84.34,"lowerIsBetter":false,"percentile":61.18,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/JGOS-Model/JGOS-31B-Citizen","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"maj@8 + DELPHI + near-miss maj@32-64 weighted vote, Pass@1 (167/198)","filename":".eval_results/gpqa_diamond.yaml","parameters":31273086512},{"benchmarkId":"Idavidrein/gpqa","modelId":"openpangu/openPangu-2.0-Flash","value":83.7,"lowerIsBetter":false,"percentile":59.21,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@4, Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"Idavidrein/gpqa","modelId":"stepfun-ai/Step-3.5-Flash","value":83.5,"lowerIsBetter":false,"percentile":57.89,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":199384301376},{"benchmarkId":"Idavidrein/gpqa","modelId":"XiaomiMiMo/MiMo-V2-Flash","value":83.3333333333,"lowerIsBetter":false,"percentile":55.92,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/36/22/3622b785-41c0-4a96-b867-5bde46851587.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":309785318400},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5.1-FP8","value":83.3333333333,"lowerIsBetter":false,"percentile":55.92,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/52/23/522348c0-d242-4517-b97c-4e55c4261882.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":753910024032},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":82.7,"lowerIsBetter":false,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":123611012096},{"benchmarkId":"Idavidrein/gpqa","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":82.7,"lowerIsBetter":false,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":123611012096},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":82.7,"lowerIsBetter":false,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":82.7,"lowerIsBetter":false,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":82.7,"lowerIsBetter":false,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.6-FP8","value":81.3131313131,"lowerIsBetter":false,"percentile":47.37,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/7e/18/7e18ad63-4a0a-4d9d-a4ec-40b683b42981.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":358458543424},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-120b","value":80.9,"lowerIsBetter":false,"percentile":46.05,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high, With tools","filename":".eval_results/gpqa_diamond_high_with_tools.yaml","parameters":120412337472},{"benchmarkId":"Idavidrein/gpqa","modelId":"MiniMaxAI/MiniMax-M2.1","value":80.8080808081,"lowerIsBetter":false,"percentile":44.74,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/08/7b/087b0dc6-3c87-4f40-8458-16f19de92200.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":228703644928},{"benchmarkId":"Idavidrein/gpqa","modelId":"meituan-longcat/LongCat-Flash-Thinking-2601","value":80.5,"lowerIsBetter":false,"percentile":42.76,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":561862880256},{"benchmarkId":"Idavidrein/gpqa","modelId":"LGAI-EXAONE/EXAONE-4.5-33B","value":80.5,"lowerIsBetter":false,"percentile":42.76,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":34350097664},{"benchmarkId":"Idavidrein/gpqa","modelId":"LGAI-EXAONE/K-EXAONE-236B-A23B","value":79.1,"lowerIsBetter":false,"percentile":40.79,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":237099669632},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-R1-0528","value":78.7878787879,"lowerIsBetter":false,"percentile":39.47,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/a1/dd/a1dd2ea2-f092-423e-bc53-04c2fba5948d.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa_diamond.yaml","parameters":684531386000},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","value":77.2727272727,"lowerIsBetter":false,"percentile":38.16,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/bd/1f/bd1fe04f-7d58-4045-be60-7150500d537f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":123611012096},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/Nemotron-Cascade-2-30B-A3B","value":76.1,"lowerIsBetter":false,"percentile":36.84,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":31577937344},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.7-Flash","value":75.2,"lowerIsBetter":false,"percentile":35.53,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":31221488576},{"benchmarkId":"Idavidrein/gpqa","modelId":"jdopensource/JoyAI-LLM-Flash","value":74.43,"lowerIsBetter":false,"percentile":34.21,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/jdopensource/JoyAI-LLM-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":49286094592},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-20b","value":74.2,"lowerIsBetter":false,"percentile":32.89,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high, With tools","filename":".eval_results/gpqa_diamond_high_with_tools.yaml","parameters":21511953984},{"benchmarkId":"Idavidrein/gpqa","modelId":"skt/A.X-K1","value":74,"lowerIsBetter":false,"percentile":31.58,"sourceName":"A.X K1 model card","sourceUrl":"https://huggingface.co/skt/A.X-K1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"GPQA-Diamond score reported in Thinking Mode.","filename":".eval_results/A.X-K1.yaml","parameters":518983059456},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3-30B-A3B-Thinking-2507","value":72.2222222222,"lowerIsBetter":false,"percentile":30.26,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4b/02/4b02c12c-3f7b-45c8-b746-c590860a7a36.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":30532122624},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.5-Air","value":71.7171717172,"lowerIsBetter":false,"percentile":28.95,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9c/77/9c7740fd-9cad-445c-9681-eb576e2a110e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":110468824832},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-R1","value":71.5,"lowerIsBetter":false,"percentile":27.63,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":684531386000},{"benchmarkId":"Idavidrein/gpqa","modelId":"mistralai/Mistral-Small-4-119B-2603","value":71.2,"lowerIsBetter":false,"percentile":26.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"reasoning: high","filename":".eval_results/gpqa_diamond.yaml","parameters":119401317952},{"benchmarkId":"Idavidrein/gpqa","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":66.7,"lowerIsBetter":false,"percentile":25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":1023244718976},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3-4B-Thinking-2507","value":65.8,"lowerIsBetter":false,"percentile":23.68,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":4022468096},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3-4B-Instruct-2507","value":62,"lowerIsBetter":false,"percentile":22.37,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":4022468096},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-V3","value":58.2070707071,"lowerIsBetter":false,"percentile":21.05,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/0a/db/0adbcd9f-38e6-414a-88b1-7bd928d4c72e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa_diamond.yaml","parameters":684531386000},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Thinking","value":57.6,"lowerIsBetter":false,"percentile":19.74,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"post-training eval (SFT + RLVR), with thinking, no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"CohereLabs/c4ai-command-a-03-2025","value":50.5050505051,"lowerIsBetter":false,"percentile":18.42,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b2/77/b27740dc-a017-4738-8dd0-c18973b61d9e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":111057580032},{"benchmarkId":"Idavidrein/gpqa","modelId":"meta-llama/Llama-3.2-90B-Vision-Instruct","value":46.0858585859,"lowerIsBetter":false,"percentile":17.11,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/94/0f/940ff5c0-b932-4c37-9eb5-27cbd4997484.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":88593355323},{"benchmarkId":"Idavidrein/gpqa","modelId":"ibm-granite/granite-4.1-30b","value":45.76,"lowerIsBetter":false,"percentile":15.79,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-30b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":28865728512},{"benchmarkId":"Idavidrein/gpqa","modelId":"ibm-granite/granite-4.1-8b","value":41.96,"lowerIsBetter":false,"percentile":14.47,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-8b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":8791592960},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Instruct","value":40.9,"lowerIsBetter":false,"percentile":13.16,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"post-training eval (SFT + RLVR), no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Thinking-SFT","value":39.9,"lowerIsBetter":false,"percentile":11.84,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"post-training eval (SFT only), with thinking, no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Instruct-SFT","value":38.9,"lowerIsBetter":false,"percentile":10.53,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"post-training eval (SFT only), no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"CohereLabs/c4ai-command-r-plus-08-2024","value":34.3434343434,"lowerIsBetter":false,"percentile":9.21,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/af/03/af03cc06-a493-48b7-a049-61d9b690c8f3.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":103810674688},{"benchmarkId":"Idavidrein/gpqa","modelId":"ibm-granite/granite-4.1-3b","value":31.7,"lowerIsBetter":false,"percentile":7.89,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-3b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":3402836480},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Base-Pretrain","value":31.31,"lowerIsBetter":false,"percentile":5.92,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval, no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Base","value":31.31,"lowerIsBetter":false,"percentile":5.92,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval (pre-YaRN), no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"CohereLabs/c4ai-command-r-08-2024","value":26.7676767677,"lowerIsBetter":false,"percentile":3.29,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9a/17/9a17fcf2-ee22-4a4f-b992-0d07290a56fc.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":32296476672},{"benchmarkId":"Idavidrein/gpqa","modelId":"CohereLabs/c4ai-command-r7b-12-2024","value":26.7676767677,"lowerIsBetter":false,"percentile":3.29,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/69/1d/691d4ef0-94b0-47e2-a7c9-b85f1bdc625b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":8028033024},{"benchmarkId":"Idavidrein/gpqa","modelId":"Muse-research/Muse-2-350M","value":25.79,"lowerIsBetter":false,"percentile":1.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Muse-research/Muse-2-350M","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":354980864},{"benchmarkId":"Idavidrein/gpqa","modelId":"meta-llama/Llama-3.2-1B-Instruct","value":18.6868686869,"lowerIsBetter":false,"percentile":0,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/aa/ad/aaad0db3-7c5b-4834-a1a2-d96624bdd003.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":1235814400},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepreinforce-ai/Ornith-1.0-397B","value":82.4,"lowerIsBetter":false,"percentile":100,"sourceName":"Ornith-1.0-397B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-397B.yaml","parameters":396802360816},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":80.6,"lowerIsBetter":false,"percentile":97.92,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":861608274846},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MiniMaxAI/MiniMax-M3","value":80.5,"lowerIsBetter":false,"percentile":93.75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Each test was run 4 times and the average was taken.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":80.5,"lowerIsBetter":false,"percentile":93.75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Each test was run 4 times and the average was taken.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":80.5,"lowerIsBetter":false,"percentile":93.75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Each test was run 4 times and the average was taken.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"moonshotai/Kimi-K2.6","value":80.2,"lowerIsBetter":false,"percentile":89.58,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":1058589420528},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":79,"lowerIsBetter":false,"percentile":87.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":158069433298},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":78.9,"lowerIsBetter":false,"percentile":85.42,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":1023244718976},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"tencent/Hy3","value":78,"lowerIsBetter":false,"percentile":83.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":298786155776},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"zai-org/GLM-5","value":77.8,"lowerIsBetter":false,"percentile":81.25,"sourceName":"Model card","sourceUrl":"https://huggingface.co/zai-org/GLM-5/","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Z.ai reported number","filename":".eval_results/swe_bench_verified.yaml","parameters":753864139008},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"mistralai/Mistral-Medium-3.5-128B","value":77.6,"lowerIsBetter":false,"percentile":79.17,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":127704211408},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.6-27B","value":77.2,"lowerIsBetter":false,"percentile":77.08,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":27781427952},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.5-397B-A17B","value":76.4,"lowerIsBetter":false,"percentile":75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":403397928944},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MiniMaxAI/MiniMax-M2.5","value":75.8,"lowerIsBetter":false,"percentile":72.92,"sourceName":"SWE-Bench official evaluation","sourceUrl":"https://www.swebench.com/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"high reasoning","filename":".eval_results/swe_bench_verified.yaml","parameters":228703644928},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepreinforce-ai/Ornith-1.0-35B","value":75.6,"lowerIsBetter":false,"percentile":70.83,"sourceName":"Ornith-1.0-35B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-35B.yaml","parameters":664944},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Multilingual-Multimodal-NLP/IndustrialCoder","value":74.8,"lowerIsBetter":false,"percentile":68.75,"sourceName":"IndustrialCoder technical report","sourceUrl":"https://huggingface.co/papers/2603.16790","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":31992714240},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"poolside/Laguna-M.1","value":74.6,"lowerIsBetter":false,"percentile":66.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-M.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":225795725568},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"stepfun-ai/Step-3.5-Flash","value":74.4,"lowerIsBetter":false,"percentile":63.54,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":199384301376},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"tencent/Hy3-preview","value":74.4,"lowerIsBetter":false,"percentile":63.54,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3-preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":298786155776},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MiniMaxAI/MiniMax-M2.1","value":74,"lowerIsBetter":false,"percentile":59.38,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":228703644928},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"inclusionAI/Ring-2.6-1T","value":74,"lowerIsBetter":false,"percentile":59.38,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ring-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"high reasoning effort","filename":".eval_results/swe_bench_verified.yaml","parameters":1025657871744},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"zai-org/GLM-4.7","value":73.8,"lowerIsBetter":false,"percentile":56.25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":358337791296},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.6-35B-A3B","value":73.4,"lowerIsBetter":false,"percentile":54.17,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":35951822704},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.5-27B","value":72.4,"lowerIsBetter":false,"percentile":52.08,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":27781427952},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"inclusionAI/Ling-2.6-1T","value":72.2,"lowerIsBetter":false,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ling-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":1025657871744},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.5-122B-A10B","value":72,"lowerIsBetter":false,"percentile":47.92,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":125086497008},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":71.9,"lowerIsBetter":false,"percentile":45.83,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":560524578816},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"moonshotai/Kimi-K2-Thinking","value":71.3,"lowerIsBetter":false,"percentile":43.75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":1058118284416},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"poolside/Laguna-XS-2.1","value":70.9,"lowerIsBetter":false,"percentile":41.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":33442617088},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"moonshotai/Kimi-K2.5","value":70.8,"lowerIsBetter":false,"percentile":39.58,"sourceName":"SWE-Bench official evaluation","sourceUrl":"https://www.swebench.com/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"high reasoning","filename":".eval_results/swe_bench_verified.yaml","parameters":1058589420528},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3-Coder-Next","value":70.6,"lowerIsBetter":false,"percentile":37.5,"sourceName":"Qwen3-Coder-Next technical report","sourceUrl":"https://huggingface.co/papers/2603.00729","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"SWE-Agent as harness","filename":".eval_results/swe_bench_verified.yaml","parameters":79674391296},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"poolside/Laguna-XS.2","value":69.9,"lowerIsBetter":false,"percentile":35.42,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":33442617088},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":69.7,"lowerIsBetter":false,"percentile":33.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":335038821080},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MiniMaxAI/MiniMax-M2","value":69.4,"lowerIsBetter":false,"percentile":30.21,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":228703644928},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepreinforce-ai/Ornith-1.0-9B","value":69.4,"lowerIsBetter":false,"percentile":30.21,"sourceName":"Ornith-1.0-9B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-9B.yaml","parameters":1469680},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MuVeraAI/Laguna-XS.2","value":68.2,"lowerIsBetter":false,"percentile":27.08,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":33442617088},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"CohereLabs/North-Mini-Code-1.0","value":67.6,"lowerIsBetter":false,"percentile":25,"sourceName":"North Mini Code Model Page","sourceUrl":"https://huggingface.co/CohereLabs/North-Mini-Code-1.0","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/swe-bench-verified.yaml","parameters":30484303872},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"internlm/Intern-S2-Preview","value":64,"lowerIsBetter":false,"percentile":22.92,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":36098254656},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openpangu/openPangu-2.0-Flash","value":63.1,"lowerIsBetter":false,"percentile":20.83,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@3, Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openai/gpt-oss-120b","value":62.4,"lowerIsBetter":false,"percentile":18.75,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high","filename":".eval_results/swe_bench_verified_high.yaml","parameters":120412337472},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"inclusionAI/Ling-2.6-flash","value":61.2,"lowerIsBetter":false,"percentile":16.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ling-2.6-flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":107494409216},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openai/gpt-oss-20b","value":60.7,"lowerIsBetter":false,"percentile":14.58,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high","filename":".eval_results/swe_bench_verified_high.yaml","parameters":21511953984},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":60.47,"lowerIsBetter":false,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":123611012096},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":60.47,"lowerIsBetter":false,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":123611012096},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":60.47,"lowerIsBetter":false,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":60.47,"lowerIsBetter":false,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":60.47,"lowerIsBetter":false,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"zai-org/GLM-4.7-Flash","value":59.2,"lowerIsBetter":false,"percentile":2.08,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":31221488576},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"facebook/cwm","value":53.9,"lowerIsBetter":false,"percentile":0,"sourceName":"CWM technical report","sourceUrl":"https://huggingface.co/papers/2510.02387","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"averaged over 4 runs","filename":".eval_results/swe_bench_verified.yaml","parameters":32581097472},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"zai-org/GLM-5.2","value":20.709230769230768,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":753329940480},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"zai-org/GLM-5.1","value":18.19,"lowerIsBetter":false,"percentile":83.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 40/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":753864139008},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"moonshotai/Kimi-K2.6","value":18,"lowerIsBetter":false,"percentile":66.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 38/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":1058589420528},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":17.12,"lowerIsBetter":false,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":861608274846},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"XiaomiMiMo/MiMo-V2.5","value":16.91,"lowerIsBetter":false,"percentile":33.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":310775040000},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"Qwen/Qwen3.5-397B-A17B","value":14.23,"lowerIsBetter":false,"percentile":16.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 40/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":403397928944},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"moonshotai/Kimi-K2.5","value":13.96,"lowerIsBetter":false,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":1058589420528},{"benchmarkId":"llamaindex/ParseBench","modelId":"KDLAI/KDL-Frontier-Parser-nano","value":76.36,"lowerIsBetter":false,"percentile":100,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: kdl_frontier_nano (standalone provider, run-llama/ParseBench PR #49). Full-set single-pass run (2,553 test cases, 0 failures): vLLM serving of the public weights + the deterministic provider pipeline. Layout dimension = layout_element_rule_pass_rate (official leade","filename":".eval_results/parsebench.yaml","parameters":1156026624},{"benchmarkId":"llamaindex/ParseBench","modelId":"infly/Infinity-Parser2-Pro","value":74.3,"lowerIsBetter":false,"percentile":94.12,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: infinity_parser2_pro","filename":".eval_results/parsebench.yaml","parameters":35107181936},{"benchmarkId":"llamaindex/ParseBench","modelId":"infly/Infinity-Parser2-Flash","value":73.25,"lowerIsBetter":false,"percentile":88.24,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: infinity_parser2_flash","filename":".eval_results/parsebench.yaml","parameters":2213241664},{"benchmarkId":"llamaindex/ParseBench","modelId":"opendatalab/MinerU2.5-Pro-2605-1.2B","value":72.78,"lowerIsBetter":false,"percentile":82.35,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: mineru2605pro_vllm","filename":".eval_results/parsebench.yaml","parameters":1156026624},{"benchmarkId":"llamaindex/ParseBench","modelId":"datalab-to/chandra-ocr-2","value":70.1,"lowerIsBetter":false,"percentile":76.47,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: chandra2_vllm","filename":".eval_results/parsebench.yaml","parameters":5295564288},{"benchmarkId":"llamaindex/ParseBench","modelId":"datalab-to/surya-ocr-2","value":64.83,"lowerIsBetter":false,"percentile":70.59,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: surya2_sdk","filename":".eval_results/parsebench.yaml","parameters":686154304},{"benchmarkId":"llamaindex/ParseBench","modelId":"rednote-hilab/dots.mocr","value":55.8,"lowerIsBetter":false,"percentile":64.71,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: dots_ocr_1_5_parse","filename":".eval_results/parsebench.yaml","parameters":3039179264},{"benchmarkId":"llamaindex/ParseBench","modelId":"tiiuae/Falcon-OCR","value":53.08,"lowerIsBetter":false,"percentile":58.82,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: falconocr_pipeline","filename":".eval_results/parsebench.yaml","parameters":269944416},{"benchmarkId":"llamaindex/ParseBench","modelId":"docling-project/docling-models","value":50.6,"lowerIsBetter":false,"percentile":52.94,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: docling_parse","filename":".eval_results/parsebench.yaml","parameters":null},{"benchmarkId":"llamaindex/ParseBench","modelId":"lightonai/LightOnOCR-2-1B","value":48,"lowerIsBetter":false,"percentile":47.06,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: lightonocr_vllm","filename":".eval_results/parsebench.yaml","parameters":1005647872},{"benchmarkId":"llamaindex/ParseBench","modelId":"Qwen/Qwen3-VL-8B-Instruct","value":46.8,"lowerIsBetter":false,"percentile":41.18,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: qwen3vl_layout","filename":".eval_results/parsebench.yaml","parameters":8767123696},{"benchmarkId":"llamaindex/ParseBench","modelId":"baidu/Qianfan-OCR","value":46.2,"lowerIsBetter":false,"percentile":35.29,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: qfocr_vllm_thinking","filename":".eval_results/parsebench.yaml","parameters":4741408256},{"benchmarkId":"llamaindex/ParseBench","modelId":"baidu/Unlimited-OCR","value":46.17,"lowerIsBetter":false,"percentile":29.41,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: unlimitedocr","filename":".eval_results/parsebench.yaml","parameters":3336106240},{"benchmarkId":"llamaindex/ParseBench","modelId":"opendatalab/MinerU2.5-2509-1.2B","value":45.9,"lowerIsBetter":false,"percentile":23.53,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: mineru25_vllm","filename":".eval_results/parsebench.yaml","parameters":1156026624},{"benchmarkId":"llamaindex/ParseBench","modelId":"Qwen/Qwen3.6-35B-A3B","value":44.1,"lowerIsBetter":false,"percentile":17.65,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: qwen3_6_35b_a3b_fp8_vllm_parse_layout","filename":".eval_results/parsebench.yaml","parameters":35951822704},{"benchmarkId":"llamaindex/ParseBench","modelId":"deepseek-ai/DeepSeek-OCR-2","value":41.2,"lowerIsBetter":false,"percentile":11.76,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: deepseekocr2_vllm","filename":".eval_results/parsebench.yaml","parameters":3389119360},{"benchmarkId":"llamaindex/ParseBench","modelId":"ibm-granite/granite-vision-4.1-4b","value":39.45,"lowerIsBetter":false,"percentile":5.88,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: granite_vision_4_1_4b","filename":".eval_results/parsebench.yaml","parameters":3997206464},{"benchmarkId":"llamaindex/ParseBench","modelId":"zai-org/GLM-OCR","value":29.6,"lowerIsBetter":false,"percentile":0,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: glmocr_pipeline","filename":".eval_results/parsebench.yaml","parameters":1325258240},{"benchmarkId":"MathArena/aime_2026","modelId":"stepfun-ai/Step-3.5-Flash","value":96.67,"lowerIsBetter":false,"percentile":100,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":199384301376},{"benchmarkId":"MathArena/aime_2026","modelId":"moonshotai/Kimi-K2.6","value":96.4,"lowerIsBetter":false,"percentile":93.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":1058589420528},{"benchmarkId":"MathArena/aime_2026","modelId":"moonshotai/Kimi-K2.5","value":95.83,"lowerIsBetter":false,"percentile":80,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":1058589420528},{"benchmarkId":"MathArena/aime_2026","modelId":"zai-org/GLM-5","value":95.83,"lowerIsBetter":false,"percentile":80,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":753864139008},{"benchmarkId":"MathArena/aime_2026","modelId":"inclusionAI/Ring-2.6-1T","value":95.83,"lowerIsBetter":false,"percentile":80,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ring-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"xhigh reasoning effort, Mean@64","filename":".eval_results/aime_2026.yaml","parameters":1025657871744},{"benchmarkId":"MathArena/aime_2026","modelId":"zai-org/GLM-5.1","value":95.3,"lowerIsBetter":false,"percentile":66.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":753864139008},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3.6-27B","value":94.1,"lowerIsBetter":false,"percentile":60,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":27781427952},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3.5-397B-A17B","value":93.33,"lowerIsBetter":false,"percentile":53.33,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":403397928944},{"benchmarkId":"MathArena/aime_2026","modelId":"openpangu/openPangu-2.0-Flash","value":93.3,"lowerIsBetter":false,"percentile":46.67,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3.6-35B-A3B","value":92.7,"lowerIsBetter":false,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":35951822704},{"benchmarkId":"MathArena/aime_2026","modelId":"LGAI-EXAONE/EXAONE-4.5-33B","value":92.6,"lowerIsBetter":false,"percentile":33.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":34350097664},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3.5-27B","value":90.83,"lowerIsBetter":false,"percentile":26.67,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":27781427952},{"benchmarkId":"MathArena/aime_2026","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":90,"lowerIsBetter":false,"percentile":20,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":123611012096},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3-30B-A3B-Thinking-2507","value":87.5,"lowerIsBetter":false,"percentile":13.33,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":30532122624},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3-4B-Thinking-2507","value":82.5,"lowerIsBetter":false,"percentile":6.67,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":4022468096},{"benchmarkId":"MathArena/aime_2026","modelId":"inclusionAI/Ling-2.6-flash","value":73.85,"lowerIsBetter":false,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ling-2.6-flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":107494409216},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-5.1","value":69,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"agent: Terminus 2(Claude Code)","filename":".eval_results/terminal_bench_2_claudecode.yaml","parameters":753864139008},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":68.4,"lowerIsBetter":false,"percentile":97.22,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":1023244718976},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":67.9,"lowerIsBetter":false,"percentile":94.44,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":861608274846},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"moonshotai/Kimi-K2.6","value":66.7,"lowerIsBetter":false,"percentile":91.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal_bench_2.yaml","parameters":1058589420528},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"XiaomiMiMo/MiMo-V2.5","value":65.8,"lowerIsBetter":false,"percentile":88.89,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":310775040000},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.6-27B","value":59.3,"lowerIsBetter":false,"percentile":86.11,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Harbor/Terminus-2 harness; 3h timeout, 32 CPU/48 GB RAM; temp=1.0, top_p=0.95, top_k=20, max_tokens=80K, 256K ctx; avg of 5 runs.","filename":".eval_results/terminal-bench-2.0.yaml","parameters":27781427952},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"MiniMaxAI/MiniMax-M2.7","value":57,"lowerIsBetter":false,"percentile":83.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":228703644928},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":56.9,"lowerIsBetter":false,"percentile":80.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":158069433298},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"tencent/Hy3-preview","value":54.4,"lowerIsBetter":false,"percentile":77.78,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3-preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal_bench.yaml","parameters":298786155776},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.5-397B-A17B","value":52.5,"lowerIsBetter":false,"percentile":75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminalbench_2.yaml","parameters":403397928944},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-5","value":52.4,"lowerIsBetter":false,"percentile":72.22,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":753864139008},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.6-35B-A3B","value":51.5,"lowerIsBetter":false,"percentile":69.44,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Harbor/Terminus-2 harness; 3h timeout, 32 CPU/48 GB RAM; temp=1.0, top_p=0.95, top_k=20, max_tokens=80K, 256K ctx; avg of 5 runs.","filename":".eval_results/terminal-bench-2.0.yaml","parameters":35951822704},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"stepfun-ai/Step-3.5-Flash","value":51,"lowerIsBetter":false,"percentile":66.67,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/terminal_bench_2.yaml","parameters":199384301376},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.5-122B-A10B","value":49.4,"lowerIsBetter":false,"percentile":63.89,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2_2.yaml","parameters":125086497008},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"poolside/Laguna-M.1","value":45.8,"lowerIsBetter":false,"percentile":61.11,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-M.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":225795725568},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"moonshotai/Kimi-K2.5","value":43.2,"lowerIsBetter":false,"percentile":58.33,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":1058589420528},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.5-27B","value":41.6,"lowerIsBetter":false,"percentile":55.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0_4.yaml","parameters":27781427952},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"poolside/Laguna-XS-2.1","value":37.5,"lowerIsBetter":false,"percentile":52.78,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":33442617088},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3-Coder-Next","value":36.2,"lowerIsBetter":false,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-Next","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":79674391296},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"CohereLabs/North-Mini-Code-1.0","value":36,"lowerIsBetter":false,"percentile":47.22,"sourceName":"North Mini Code Model Page","sourceUrl":"https://huggingface.co/CohereLabs/North-Mini-Code-1.0","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-v2.yaml","parameters":30484303872},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"moonshotai/Kimi-K2-Thinking","value":35.7,"lowerIsBetter":false,"percentile":43.06,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":1058118284416},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"poolside/Laguna-XS.2","value":35.7,"lowerIsBetter":false,"percentile":43.06,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":33442617088},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-4.7","value":33.4,"lowerIsBetter":false,"percentile":38.89,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":358337791296},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":31,"lowerIsBetter":false,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":123611012096},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":31,"lowerIsBetter":false,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":123611012096},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":31,"lowerIsBetter":false,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":120668707840},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":31,"lowerIsBetter":false,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":120668707840},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":31,"lowerIsBetter":false,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":120668707840},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"MuVeraAI/Laguna-XS.2","value":30.1,"lowerIsBetter":false,"percentile":22.22,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":33442617088},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"MiniMaxAI/MiniMax-M2","value":30,"lowerIsBetter":false,"percentile":19.44,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":228703644928},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"MiniMaxAI/MiniMax-M2.1","value":29.2,"lowerIsBetter":false,"percentile":16.67,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":228703644928},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"moonshotai/Kimi-K2-Instruct","value":27.8,"lowerIsBetter":false,"percentile":13.89,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":1026470731056},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"nvidia/Nemotron-Terminal-32B","value":27.4,"lowerIsBetter":false,"percentile":11.11,"sourceName":"Nemotron-Terminal-32B technical report","sourceUrl":"https://arxiv.org/pdf/2602.21193","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":32762123264},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-4.6","value":24.5,"lowerIsBetter":false,"percentile":8.33,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":356785898816},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct","value":23.9,"lowerIsBetter":false,"percentile":5.56,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":480154875392},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"nvidia/Nemotron-Terminal-14B","value":20.2,"lowerIsBetter":false,"percentile":2.78,"sourceName":"Nemotron-Terminal-14B technical report","sourceUrl":"https://arxiv.org/pdf/2602.21193","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":14768307200},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"nvidia/Nemotron-Terminal-8B","value":13,"lowerIsBetter":false,"percentile":0,"sourceName":"Nemotron-Terminal-8B technical report","sourceUrl":"https://arxiv.org/pdf/2602.21193","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":8190735360},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"rednote-hilab/dots.mocr","value":80.5,"lowerIsBetter":false,"percentile":100,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":3039179264},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"datalab-to/chandra-ocr-2","value":79.7,"lowerIsBetter":false,"percentile":90.91,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":5295564288},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"moonshotai/Kimi-K2.5","value":77.5,"lowerIsBetter":false,"percentile":81.82,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1058589420528},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"rednote-hilab/dots.ocr","value":76.5,"lowerIsBetter":false,"percentile":72.73,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":3039179264},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"opendatalab/MinerU2.5-Pro-2605-1.2B","value":71,"lowerIsBetter":false,"percentile":63.64,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1156026624},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"Qwen/Qwen3-VL-8B-Instruct","value":68.3,"lowerIsBetter":false,"percentile":50,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":8767123696},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"tencent/HunyuanOCR","value":68.3,"lowerIsBetter":false,"percentile":50,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1119925744},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"zai-org/GLM-OCR","value":67.3,"lowerIsBetter":false,"percentile":36.36,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1325258240},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"lightonai/LightOnOCR-2-1B","value":63.9,"lowerIsBetter":false,"percentile":27.27,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1005647872},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"tiiuae/Falcon-OCR","value":56.3,"lowerIsBetter":false,"percentile":18.18,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":269944416},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"deepseek-ai/DeepSeek-OCR","value":51.8,"lowerIsBetter":false,"percentile":9.09,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":3336106240},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"opendatalab/MinerU2.5-2509-1.2B","value":46.3,"lowerIsBetter":false,"percentile":0,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1156026624},{"benchmarkId":"actava/chi-bench","modelId":"zai-org/GLM-5.1","value":18.7,"lowerIsBetter":false,"percentile":100,"sourceName":"CHI-Bench","sourceUrl":"https://arxiv.org/abs/2605.16679","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"Harness: OpenAI Agents SDK; Protocol: 75 tasks x 3 trials; Metric: pass@1 (%)","filename":".eval_results/chi-bench.yaml","parameters":753864139008},{"benchmarkId":"actava/chi-bench","modelId":"moonshotai/Kimi-K2.6","value":15.6,"lowerIsBetter":false,"percentile":50,"sourceName":"CHI-Bench","sourceUrl":"https://arxiv.org/abs/2605.16679","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"Harness: Hermes; Protocol: 75 tasks x 3 trials; Metric: pass@1 (%)","filename":".eval_results/chi-bench.yaml","parameters":1058589420528},{"benchmarkId":"actava/chi-bench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":14.2,"lowerIsBetter":false,"percentile":0,"sourceName":"CHI-Bench","sourceUrl":"https://arxiv.org/abs/2605.16679","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"Harness: OpenAI Agents SDK; Protocol: 75 tasks x 3 trials; Metric: pass@1 (%)","filename":".eval_results/chi-bench.yaml","parameters":861608274846},{"benchmarkId":"meituan-longcat/WBench","modelId":"robbyant/lingbot-world-fast","value":78.8,"lowerIsBetter":false,"percentile":100,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"tencent/HY-WorldPlay","value":78.4,"lowerIsBetter":false,"percentile":85.71,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"tencent/HunyuanVideo-1.5","value":78.2,"lowerIsBetter":false,"percentile":71.43,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"Lightricks/LTX-2.3","value":74.4,"lowerIsBetter":false,"percentile":57.14,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"inspatio/world","value":74.3,"lowerIsBetter":false,"percentile":42.86,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"meituan-longcat/LongCat-Video","value":73.7,"lowerIsBetter":false,"percentile":28.57,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"ACERobotics/kairos-sensenova-robot-4B-480P","value":70.7,"lowerIsBetter":false,"percentile":14.29,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"tencent/Hunyuan-GameCraft-1.0","value":68.5,"lowerIsBetter":false,"percentile":0,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"bharatgenai/Shrutam-HindiASR-1.0","value":18.1,"lowerIsBetter":true,"percentile":100,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":null},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"mistralai/Voxtral-Mini-3B-2507","value":21.3,"lowerIsBetter":true,"percentile":83.33,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":4676271104},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"shunyalabs/pingala-v1-universal","value":22.1,"lowerIsBetter":true,"percentile":66.67,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":808878080},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"SPRINGLab/data2vec_aqc","value":23.7,"lowerIsBetter":true,"percentile":50,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":null},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"google/gemma-4-12B","value":24.6,"lowerIsBetter":true,"percentile":33.33,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":11959730224},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"facebook/omniASR-LLM-1B","value":25.6,"lowerIsBetter":true,"percentile":16.67,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":null},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"openai/whisper-large-v3","value":26.8,"lowerIsBetter":true,"percentile":0,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":1543490560},{"benchmarkId":"mteb/arguana","modelId":"google/embeddinggemma-300m","value":71.535,"lowerIsBetter":false,"percentile":100,"sourceName":"Obtained using MTEB v1.34.7","sourceUrl":"https://github.com/embeddings-benchmark/mteb/","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"Obtained using MTEB v1.34.7","filename":".eval_results/ArguAna.yaml","parameters":302863104},{"benchmarkId":"mteb/arguana","modelId":"mteb/baseline-bm25s","value":49.276,"lowerIsBetter":false,"percentile":50,"sourceName":"Obtained using MTEB v1.12.22","sourceUrl":"https://github.com/embeddings-benchmark/mteb/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Obtained using MTEB v1.12.22","filename":".eval_results/ArguAna.yaml","parameters":null},{"benchmarkId":"mteb/arguana","modelId":"Surpem/Supertron-embedding-190M","value":42.019,"lowerIsBetter":false,"percentile":0,"sourceName":"Supetron Modal benchmark run","sourceUrl":"https://huggingface.co/datasets/mteb/arguana","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Official mteb/arguana retrieval task. Metric: nDCG@10.","filename":".eval_results/eval_arguana.yaml","parameters":130450176},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"AutoArk-AI/ARK-ASR-3B","value":4.76,"lowerIsBetter":true,"percentile":100,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":4063438848},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"OpenMOSS-Team/MOSS-Transcribe-preview-2B","value":4.87,"lowerIsBetter":true,"percentile":98.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2418833792},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"CohereLabs/cohere-transcribe-03-2026","value":5.42,"lowerIsBetter":true,"percentile":96.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2065804048},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"AutoArk-AI/ARK-ASR-0.6B","value":5.53,"lowerIsBetter":true,"percentile":95,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1299463168},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M","value":5.64,"lowerIsBetter":true,"percentile":93.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"Qwen/Qwen3-ASR-1.7B","value":5.76,"lowerIsBetter":true,"percentile":91.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2349217408},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"microsoft/Phi-4-multimodal-instruct","value":6.02,"lowerIsBetter":true,"percentile":90,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":5574460384},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-tdt-0.6b-v2","value":6.05,"lowerIsBetter":true,"percentile":88.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-tdt-0.6b-v3","value":6.32,"lowerIsBetter":true,"percentile":86.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":627057286},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/canary-1b-flash","value":6.35,"lowerIsBetter":true,"percentile":85,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":811049984},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"kyutai/stt-2.6b-en","value":6.4,"lowerIsBetter":true,"percentile":83.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2617118720},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"Qwen/Qwen3-ASR-0.6B","value":6.42,"lowerIsBetter":true,"percentile":81.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":938008576},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/canary-1b","value":6.50375,"lowerIsBetter":true,"percentile":80,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-streaming-medium","value":6.66,"lowerIsBetter":true,"percentile":78.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":265898112},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"soundsgoodai/Zipformer-transducer-XL-290M","value":6.71,"lowerIsBetter":true,"percentile":76.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-tdt-1.1b","value":7.015,"lowerIsBetter":true,"percentile":75,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"zai-org/GLM-ASR-Nano-2512","value":7.03,"lowerIsBetter":true,"percentile":72.5,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2257843200},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"AutoArk-AI/Audio8-ASR-0.1B","value":7.03,"lowerIsBetter":true,"percentile":72.5,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":323990528},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"mistralai/Voxtral-Mini-3B-2507","value":7.05,"lowerIsBetter":true,"percentile":70,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":4676271104},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/canary-180m-flash","value":7.12,"lowerIsBetter":true,"percentile":68.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-rnnt-1.1b","value":7.12375,"lowerIsBetter":true,"percentile":66.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1070518785},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/canary-1b-v2","value":7.15,"lowerIsBetter":true,"percentile":65,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"distil-whisper/distil-large-v3.5","value":7.21,"lowerIsBetter":true,"percentile":63.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":756405760},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-ctc-1.1b","value":7.39875,"lowerIsBetter":true,"percentile":61.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1062626305},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"espnet/owsm_ctc_v4_1B","value":7.42,"lowerIsBetter":true,"percentile":60,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-large-v3","value":7.44,"lowerIsBetter":true,"percentile":58.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1543490560},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-tdt_ctc-110m","value":7.49,"lowerIsBetter":true,"percentile":56.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-rnnt-0.6b","value":7.495,"lowerIsBetter":true,"percentile":55,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":616741377},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-ctc-0.6b","value":7.69,"lowerIsBetter":true,"percentile":53.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":608848897},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"microsoft/VibeVoice-ASR-HF","value":7.77,"lowerIsBetter":true,"percentile":51.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":8330325888},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-large-v2","value":7.835,"lowerIsBetter":true,"percentile":50,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1543304960},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-streaming-small","value":7.84,"lowerIsBetter":true,"percentile":48.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":140135224},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-large","value":7.9425,"lowerIsBetter":true,"percentile":46.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1543304960},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-medium.en","value":8.09,"lowerIsBetter":true,"percentile":45,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":763856896},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"espnet/owsm_ctc_v3.1_1B","value":8.12,"lowerIsBetter":true,"percentile":43.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/stt_en_conformer_ctc_large","value":8.31875,"lowerIsBetter":true,"percentile":41.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"speechbrain/asr-conformer-loquacious","value":8.48,"lowerIsBetter":true,"percentile":40,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-small.en","value":8.59,"lowerIsBetter":true,"percentile":38.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":241734144},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"abr-ai/niagara-38m-batch.en","value":8.91,"lowerIsBetter":true,"percentile":36.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/stt_en_fastconformer_ctc_large","value":8.965,"lowerIsBetter":true,"percentile":35,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/stt_en_fastconformer_transducer_large","value":9.0575,"lowerIsBetter":true,"percentile":33.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-base","value":9.99,"lowerIsBetter":true,"percentile":31.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":61513920},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-base.en","value":10.3175,"lowerIsBetter":true,"percentile":30,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":72593408},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"abr-ai/niagara-19m-batch.en","value":10.47,"lowerIsBetter":true,"percentile":28.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/stt_en_conformer_ctc_small","value":11.15875,"lowerIsBetter":true,"percentile":26.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-streaming-tiny","value":12,"lowerIsBetter":true,"percentile":25,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":44054720},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-tiny","value":12.65,"lowerIsBetter":true,"percentile":23.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":27092736},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-tiny.en","value":12.80625,"lowerIsBetter":true,"percentile":21.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":37760256},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"speechbrain/asr-wav2vec2-librispeech","value":14.3475,"lowerIsBetter":true,"percentile":20,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-large-960h-lv60-self","value":21.2725,"lowerIsBetter":true,"percentile":18.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/mms-1b-all","value":22.53875,"lowerIsBetter":true,"percentile":16.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":964845850},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/hubert-xlarge-ls960-ft","value":22.5475,"lowerIsBetter":true,"percentile":15,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":962538400},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/hubert-large-ls960-ft","value":22.69375,"lowerIsBetter":true,"percentile":13.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-large-robust-ft-libri-960h","value":22.93125,"lowerIsBetter":true,"percentile":11.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":315471520},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/data2vec-audio-large-960h","value":23.21,"lowerIsBetter":true,"percentile":10,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-conformer-rope-large-960h-ft","value":23.28375,"lowerIsBetter":true,"percentile":8.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":593426112},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-conformer-rel-pos-large-960h-ft","value":23.29125,"lowerIsBetter":true,"percentile":6.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-large-960h","value":26.7725,"lowerIsBetter":true,"percentile":5,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/data2vec-audio-base-960h","value":28.3025,"lowerIsBetter":true,"percentile":3.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-base-960h","value":29.4025,"lowerIsBetter":true,"percentile":1.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":94395552},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/mms-1b-fl102","value":39.79625,"lowerIsBetter":true,"percentile":0,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":964748494},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"moonshotai/Kimi-K2.6","value":79.4,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":1058589420528},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"moonshotai/Kimi-K2.5","value":78.5,"lowerIsBetter":false,"percentile":87.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":1058589420528},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"internlm/Intern-S2-Preview","value":76.88,"lowerIsBetter":false,"percentile":75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":36098254656},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen3.6-27B","value":75.8,"lowerIsBetter":false,"percentile":62.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":27781427952},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen3.6-35B-A3B","value":75.3,"lowerIsBetter":false,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":35951822704},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen3.5-27B","value":75,"lowerIsBetter":false,"percentile":37.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":27781427952},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"ATH-MaaS/Ovis2.6-80B-A3B","value":66.3,"lowerIsBetter":false,"percentile":25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/AIDC-AI/Ovis2.6-80B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":80524245992},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen2.5-VL-7B-Instruct","value":34.3,"lowerIsBetter":false,"percentile":12.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":8292166656},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen2.5-VL-3B-Instruct","value":32.7,"lowerIsBetter":false,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":3754622976},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen3.5-122B-A10B","value":70.4,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":125086497008},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen3.5-27B","value":70.3,"lowerIsBetter":false,"percentile":95.24,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":27781427952},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-1.5-30B-A3B","value":69.6,"lowerIsBetter":false,"percentile":90.48,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":31070754032},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-1.5-8B","value":68.4,"lowerIsBetter":false,"percentile":85.71,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8767123696},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen3.5-397B-A17B","value":65.6,"lowerIsBetter":false,"percentile":80.95,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":403397928944},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Salesforce/GTA1-32B","value":63.6,"lowerIsBetter":false,"percentile":76.19,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":33452718336},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-Ground-72B","value":61.9,"lowerIsBetter":false,"percentile":71.43,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":73410777344},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"ByteDance-Seed/UI-TARS-1.5-7B","value":61.6,"lowerIsBetter":false,"percentile":66.67,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8292166656},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-1.5-2B","value":57.7,"lowerIsBetter":false,"percentile":61.9,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":2438696960},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Salesforce/GTA1-7B","value":55.5,"lowerIsBetter":false,"percentile":57.14,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8292166656},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen2.5-VL-72B-Instruct","value":53.3,"lowerIsBetter":false,"percentile":52.38,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":73410777344},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-Ground-7B","value":50.8,"lowerIsBetter":false,"percentile":47.62,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8292166656},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen2.5-VL-32B-Instruct","value":48,"lowerIsBetter":false,"percentile":42.86,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":33452718336},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"KDEGroup/UI-AGILE-3B","value":45,"lowerIsBetter":false,"percentile":38.1,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":3754622976},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"ByteDance-Seed/UI-TARS-72B-SFT","value":38.1,"lowerIsBetter":false,"percentile":33.33,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":73405560320},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"ByteDance-Seed/UI-TARS-7B-SFT","value":35.7,"lowerIsBetter":false,"percentile":28.57,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8291375616},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"ByteDance-Seed/UI-TARS-2B-SFT","value":27.7,"lowerIsBetter":false,"percentile":23.81,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":2442359296},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen2.5-VL-7B-Instruct","value":26.8,"lowerIsBetter":false,"percentile":19.05,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8292166656},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen2.5-VL-3B-Instruct","value":16.1,"lowerIsBetter":false,"percentile":14.29,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":3754622976},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"zai-org/CogAgent","value":7.7,"lowerIsBetter":false,"percentile":9.52,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":null},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"openbmb/MiniCPM-V-2","value":3,"lowerIsBetter":false,"percentile":4.76,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":3434965792},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen-VL","value":0.1,"lowerIsBetter":false,"percentile":0,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":null},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"deepseek-ai/DeepSeek-R1","value":52.41,"lowerIsBetter":false,"percentile":100,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":684531386000},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"Qwen/Qwen3-235B-A22B-Thinking-2507","value":48.19,"lowerIsBetter":false,"percentile":87.5,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":235093634560},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"openai/gpt-oss-120b","value":47.71,"lowerIsBetter":false,"percentile":75,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":120412337472},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"deepseek-ai/DeepSeek-V3","value":46.57,"lowerIsBetter":false,"percentile":62.5,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":684531386000},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"Qwen/Qwen3-32B","value":45.3,"lowerIsBetter":false,"percentile":50,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":32762123264},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"Qwen/Qwen3-Next-80B-A3B-Thinking","value":43.31,"lowerIsBetter":false,"percentile":37.5,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":81324862720},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"openai/gpt-oss-20b","value":40.78,"lowerIsBetter":false,"percentile":25,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":21511953984},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"microsoft/phi-4","value":40.66,"lowerIsBetter":false,"percentile":12.5,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":14659507200},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"mistralai/Ministral-8B-Instruct-2410","value":26.27,"lowerIsBetter":false,"percentile":0,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":8019808256},{"benchmarkId":"mercor/APEX-v1-extended","modelId":"zai-org/GLM-4.7","value":51.7,"lowerIsBetter":false,"percentile":100,"sourceName":"APEX Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-v1-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: direct_prompting; reasoning_effort: high","filename":".eval_results/apex-v1-extended.yaml","parameters":358337791296},{"benchmarkId":"mercor/APEX-v1-extended","modelId":"zai-org/GLM-5","value":49,"lowerIsBetter":false,"percentile":0,"sourceName":"APEX Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-v1-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: direct_prompting; reasoning_effort: thinking","filename":".eval_results/apex-v1-extended.yaml","parameters":753864139008},{"benchmarkId":"VLABench/vlabench_primitive_ft_lerobot_video","modelId":"lerobot/pi0_base","value":44.5,"lowerIsBetter":false,"percentile":100,"sourceName":"VLA Model Leaderboard","sourceUrl":"https://allenai.github.io/vla-evaluation-harness/leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Reproduction from ACoT-VLA paper (Table 3). A separate X-VLA paper reproduction reports 37.8.","filename":".eval_results/vlabench.yaml","parameters":3501372176},{"benchmarkId":"VLABench/vlabench_primitive_ft_lerobot_video","modelId":"lerobot/pi05_base","value":42,"lowerIsBetter":false,"percentile":66.67,"sourceName":"VLA Model Leaderboard","sourceUrl":"https://allenai.github.io/vla-evaluation-harness/leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/vlabench.yaml","parameters":3616757520},{"benchmarkId":"VLABench/vlabench_primitive_ft_lerobot_video","modelId":"nvidia/GR00T-N1-2B","value":39.7,"lowerIsBetter":false,"percentile":33.33,"sourceName":"VLA Model Leaderboard","sourceUrl":"https://allenai.github.io/vla-evaluation-harness/leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/vlabench.yaml","parameters":2190019826},{"benchmarkId":"VLABench/vlabench_primitive_ft_lerobot_video","modelId":"lerobot/pi0fast-base","value":34.1,"lowerIsBetter":false,"percentile":0,"sourceName":"VLA Model Leaderboard","sourceUrl":"https://allenai.github.io/vla-evaluation-harness/leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/vlabench.yaml","parameters":2923335408},{"benchmarkId":"FutureMa/EvasionBench","modelId":"zai-org/GLM-4.7","value":82.91,"lowerIsBetter":false,"percentile":100,"sourceName":"EvasionBench Paper","sourceUrl":"https://arxiv.org/abs/2601.09142","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/evasionbench.yaml","parameters":358337791296},{"benchmarkId":"FutureMa/EvasionBench","modelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct","value":78.16,"lowerIsBetter":false,"percentile":66.67,"sourceName":"EvasionBench Paper","sourceUrl":"https://arxiv.org/abs/2601.09142","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/evasionbench.yaml","parameters":480154875392},{"benchmarkId":"FutureMa/EvasionBench","modelId":"MiniMaxAI/MiniMax-M2.1","value":71.31,"lowerIsBetter":false,"percentile":33.33,"sourceName":"EvasionBench Paper","sourceUrl":"https://arxiv.org/abs/2601.09142","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/evasionbench.yaml","parameters":228703644928},{"benchmarkId":"FutureMa/EvasionBench","modelId":"moonshotai/Kimi-K2-Instruct-0905","value":66.68,"lowerIsBetter":false,"percentile":0,"sourceName":"EvasionBench Paper","sourceUrl":"https://arxiv.org/abs/2601.09142","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/evasionbench.yaml","parameters":1026470735448},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"moonshotai/Kimi-K2.6","value":92.7,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":1058589420528},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3.5-397B-A17B","value":87.88,"lowerIsBetter":false,"percentile":92.31,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":403397928944},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"internlm/Intern-S2-Preview","value":87.31,"lowerIsBetter":false,"percentile":84.62,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":36098254656},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"moonshotai/Kimi-K2.5","value":87.12,"lowerIsBetter":false,"percentile":76.92,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":1058589420528},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"stepfun-ai/Step-3.5-Flash","value":86.36,"lowerIsBetter":false,"percentile":65.38,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":199384301376},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"zai-org/GLM-5","value":86.36,"lowerIsBetter":false,"percentile":65.38,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":753864139008},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":84.85,"lowerIsBetter":false,"percentile":53.85,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":123611012096},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3.6-27B","value":84.3,"lowerIsBetter":false,"percentile":46.15,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":27781427952},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3.6-35B-A3B","value":83.6,"lowerIsBetter":false,"percentile":38.46,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":35951822704},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"zai-org/GLM-5.1","value":82.6,"lowerIsBetter":false,"percentile":30.77,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":753864139008},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3.5-27B","value":81.06,"lowerIsBetter":false,"percentile":23.08,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":27781427952},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3-30B-A3B-Thinking-2507","value":78.79,"lowerIsBetter":false,"percentile":15.38,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":30532122624},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3-4B-Thinking-2507","value":53.03,"lowerIsBetter":false,"percentile":7.69,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":4022468096},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"inclusionAI/Ling-2.6-flash","value":49.29,"lowerIsBetter":false,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ling-2.6-flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":107494409216},{"benchmarkId":"mteb/BRIGHT","modelId":"mteb/baseline-bm25s","value":0.11,"lowerIsBetter":false,"percentile":50,"sourceName":"Obtained using MTEB","sourceUrl":"https://github.com/embeddings-benchmark/mteb/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Obtained using MTEB","filename":".eval_results/BRIGHT(v1.1).yaml","parameters":null},{"benchmarkId":"collinear-ai/yc-bench","modelId":"MiniMaxAI/MiniMax-M3","value":2100000,"lowerIsBetter":false,"percentile":90.91,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 2.1M (monetary value, final assets fund). The benchmark's 'medium' task is used as the overall evaluation. Metric is monetary, not percentage-based.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"collinear-ai/yc-bench","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":2100000,"lowerIsBetter":false,"percentile":90.91,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 2.1M (monetary value, final assets fund). The benchmark's 'medium' task is used as the overall evaluation. Metric is monetary, not percentage-based.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"collinear-ai/yc-bench","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":2100000,"lowerIsBetter":false,"percentile":90.91,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 2.1M (monetary value, final assets fund). The benchmark's 'medium' task is used as the overall evaluation. Metric is monetary, not percentage-based.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"collinear-ai/yc-bench","modelId":"zai-org/GLM-5.1","value":1510772,"lowerIsBetter":false,"percentile":72.73,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":753864139008},{"benchmarkId":"collinear-ai/yc-bench","modelId":"zai-org/GLM-5","value":1208190,"lowerIsBetter":false,"percentile":63.64,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"avg final funds (USD) across seeds 1,2,3. GLM-5 (via OpenRouter z-ai/glm-5)","filename":".eval_results/yc-bench.yaml","parameters":753864139008},{"benchmarkId":"collinear-ai/yc-bench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":1066426,"lowerIsBetter":false,"percentile":54.55,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":861608274846},{"benchmarkId":"collinear-ai/yc-bench","modelId":"moonshotai/Kimi-K2.6","value":511137,"lowerIsBetter":false,"percentile":45.45,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":1058589420528},{"benchmarkId":"collinear-ai/yc-bench","modelId":"moonshotai/Kimi-K2.5","value":408822,"lowerIsBetter":false,"percentile":36.36,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"avg final funds (USD) across seeds 1,2,3. Kimi K2.5 (via OpenRouter moonshotai/kimi-k2.5)","filename":".eval_results/yc-bench.yaml","parameters":1058589420528},{"benchmarkId":"collinear-ai/yc-bench","modelId":"zai-org/GLM-4.7","value":398410,"lowerIsBetter":false,"percentile":27.27,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":358337791296},{"benchmarkId":"collinear-ai/yc-bench","modelId":"MiniMaxAI/MiniMax-M2.5","value":230465,"lowerIsBetter":false,"percentile":18.18,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":228703644928},{"benchmarkId":"collinear-ai/yc-bench","modelId":"Qwen/Qwen3.5-397B-A17B","value":90787,"lowerIsBetter":false,"percentile":9.09,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"avg final funds (USD) across seeds 1,2,3. Qwen 3.5-397B (via OpenRouter qwen/qwen3.5-397b-a17b)","filename":".eval_results/yc-bench.yaml","parameters":403397928944},{"benchmarkId":"collinear-ai/yc-bench","modelId":"Qwen/Qwen3.5-122B-A10B","value":0,"lowerIsBetter":false,"percentile":0,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":125086497008},{"benchmarkId":"internlm/WildClawBench","modelId":"tencent/Hy3","value":53.6,"lowerIsBetter":false,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":298786155776},{"benchmarkId":"internlm/WildClawBench","modelId":"nex-agi/Nex-N2-Pro","value":53.5,"lowerIsBetter":false,"percentile":91.67,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":396802360816},{"benchmarkId":"internlm/WildClawBench","modelId":"zai-org/GLM-5.1","value":48.2,"lowerIsBetter":false,"percentile":83.33,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":753864139008},{"benchmarkId":"internlm/WildClawBench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":43.7,"lowerIsBetter":false,"percentile":75,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":861608274846},{"benchmarkId":"internlm/WildClawBench","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":43,"lowerIsBetter":false,"percentile":66.67,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":1023244718976},{"benchmarkId":"internlm/WildClawBench","modelId":"zai-org/GLM-5","value":42.6,"lowerIsBetter":false,"percentile":58.33,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":753864139008},{"benchmarkId":"internlm/WildClawBench","modelId":"openpangu/openPangu-2.0-Flash","value":41.5,"lowerIsBetter":false,"percentile":50,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@3, Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"internlm/WildClawBench","modelId":"internlm/Intern-S2-Preview","value":39.2,"lowerIsBetter":false,"percentile":41.67,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":36098254656},{"benchmarkId":"internlm/WildClawBench","modelId":"Qwen/Qwen3.5-397B-A17B","value":34.5,"lowerIsBetter":false,"percentile":33.33,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":403397928944},{"benchmarkId":"internlm/WildClawBench","modelId":"MiniMaxAI/MiniMax-M2.7","value":33.8,"lowerIsBetter":false,"percentile":25,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":228703644928},{"benchmarkId":"internlm/WildClawBench","modelId":"moonshotai/Kimi-K2.5","value":30.8,"lowerIsBetter":false,"percentile":16.67,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":1058589420528},{"benchmarkId":"internlm/WildClawBench","modelId":"MiniMaxAI/MiniMax-M2.5","value":27.1,"lowerIsBetter":false,"percentile":8.33,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":228703644928},{"benchmarkId":"internlm/WildClawBench","modelId":"stepfun-ai/Step-3.5-Flash","value":26.7,"lowerIsBetter":false,"percentile":0,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":199384301376},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepreinforce-ai/Ornith-1.0-397B","value":77.1,"lowerIsBetter":false,"percentile":100,"sourceName":"Ornith-1.0-397B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-397B.yaml","parameters":396802360816},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"MiniMaxAI/MiniMax-M3","value":74.5,"lowerIsBetter":false,"percentile":88.24,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports a single 'Claw-Eval' score. Mapped to the 'general' task (overall); the exact task split is not specified.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":74.5,"lowerIsBetter":false,"percentile":88.24,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports a single 'Claw-Eval' score. Mapped to the 'general' task (overall); the exact task split is not specified.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":74.5,"lowerIsBetter":false,"percentile":88.24,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports a single 'Claw-Eval' score. Mapped to the 'general' task (overall); the exact task split is not specified.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepreinforce-ai/Ornith-1.0-35B","value":69.8,"lowerIsBetter":false,"percentile":76.47,"sourceName":"Ornith-1.0-35B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-35B.yaml","parameters":664944},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":64,"lowerIsBetter":false,"percentile":70.59,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":1023244718976},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"inclusionAI/Ring-2.6-1T","value":63.82,"lowerIsBetter":false,"percentile":64.71,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ring-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"high reasoning effort, Pass³ | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":1025657871744},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepreinforce-ai/Ornith-1.0-9B","value":63.1,"lowerIsBetter":false,"percentile":58.82,"sourceName":"Ornith-1.0-9B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-9B.yaml","parameters":1469680},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"zai-org/GLM-5.1","value":62.7,"lowerIsBetter":false,"percentile":52.94,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw-eval.yaml","parameters":753864139008},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"XiaomiMiMo/MiMo-V2.5","value":62.1,"lowerIsBetter":false,"percentile":47.06,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":310775040000},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"moonshotai/Kimi-K2.6","value":61.5,"lowerIsBetter":false,"percentile":41.18,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":1058589420528},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":58.4,"lowerIsBetter":false,"percentile":35.29,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw-eval.yaml","parameters":861608274846},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"openpangu/openPangu-2.0-Flash","value":58.2,"lowerIsBetter":false,"percentile":29.41,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Pass^3, Non-Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"Qwen/Qwen3.5-397B-A17B","value":57.8,"lowerIsBetter":false,"percentile":20.59,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":403397928944},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":57.8,"lowerIsBetter":false,"percentile":20.59,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw-eval.yaml","parameters":158069433298},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"moonshotai/Kimi-K2.5","value":52.8,"lowerIsBetter":false,"percentile":11.76,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":1058589420528},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"MiniMaxAI/MiniMax-M2.7","value":49.7,"lowerIsBetter":false,"percentile":5.88,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":228703644928},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":6.8,"lowerIsBetter":false,"percentile":0,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":123611012096},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"MiniMaxAI/MiniMax-M3","value":85.4,"lowerIsBetter":false,"percentile":75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 'VideoMME (w/ sub)'. Mapped to the closest registered benchmark on the Hub, Video-MME-v2.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":85.4,"lowerIsBetter":false,"percentile":75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 'VideoMME (w/ sub)'. Mapped to the closest registered benchmark on the Hub, Video-MME-v2.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":85.4,"lowerIsBetter":false,"percentile":75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 'VideoMME (w/ sub)'. Mapped to the closest registered benchmark on the Hub, Video-MME-v2.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"moonshotai/Kimi-K2.5","value":61.1,"lowerIsBetter":false,"percentile":25,"sourceName":"VideoMMEv2 leaderboard","sourceUrl":"https://video-mme-v2.netlify.app/#leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"512 frames","filename":".eval_results/videomme_v2.yaml","parameters":1058589420528},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"Qwen/Qwen3.5-397B-A17B","value":55.9,"lowerIsBetter":false,"percentile":0,"sourceName":"VideoMMEv2 leaderboard","sourceUrl":"https://video-mme-v2.netlify.app/#leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"512 frames","filename":".eval_results/videomme_v2.yaml","parameters":403397928944},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"crosbylegal/gpt-5.5","value":50.5,"lowerIsBetter":false,"percentile":100,"sourceName":"RedlineBench report","sourceUrl":"https://intelligence.crosby.ai/benchmark/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"agent=claude-code; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); published report figure","filename":".eval_results/redlinebench.yaml","parameters":null},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"crosbylegal/claude-fable-5","value":47.3,"lowerIsBetter":false,"percentile":75,"sourceName":"RedlineBench report","sourceUrl":"https://intelligence.crosby.ai/benchmark/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"agent=claude-code; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); published report figure","filename":".eval_results/redlinebench.yaml","parameters":null},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"zai-org/GLM-5.2","value":45.7,"lowerIsBetter":false,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"agent=glm-5.2; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); post-publication run","filename":".eval_results/redlinebench.yaml","parameters":753329940480},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"crosbylegal/gemini-3.5-flash","value":45.1,"lowerIsBetter":false,"percentile":25,"sourceName":"RedlineBench report","sourceUrl":"https://intelligence.crosby.ai/benchmark/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"agent=opencode; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); published report figure","filename":".eval_results/redlinebench.yaml","parameters":null},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"crosbylegal/claude-opus-4-8","value":44.4,"lowerIsBetter":false,"percentile":0,"sourceName":"RedlineBench report","sourceUrl":"https://intelligence.crosby.ai/benchmark/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"agent=claude-code; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); published report figure","filename":".eval_results/redlinebench.yaml","parameters":null}],"rawScores":[{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"InternScience/Agents-A1","value":93.25,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Agents-A1 eval trace","sourceUrl":"https://huggingface.co/datasets/InternScience/Agents-A1-ifstruct-eval-20260703-041434","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/Agents-A1.yaml","parameters":35107181936},{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"openai/gpt-oss-20b","value":91.95,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":75,"sourceName":"Liquid AI — IFStruct v1.0 blog (gpt-oss-20b)","sourceUrl":"https://www.liquid.ai/blog/ifstruct-v1.0","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/openai-gpt-oss-20b.yaml","parameters":21511953984},{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","value":86.8,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":50,"sourceName":"Liquid AI — IFStruct v1.0 blog (Nemotron-3-Nano-30B-A3B)","sourceUrl":"https://www.liquid.ai/blog/ifstruct-v1.0","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/nvidia-NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.yaml","parameters":31577937344},{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"ibm-granite/granite-4.1-8b","value":68.45,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":25,"sourceName":"Liquid AI — IFStruct v1.0 blog (granite-4.1-8b)","sourceUrl":"https://www.liquid.ai/blog/ifstruct-v1.0","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ibm-granite-granite-4.1-8b.yaml","parameters":8791592960},{"benchmarkId":"LiquidAI/ifstruct-v1.0","modelId":"ibm-granite/granite-4.0-h-tiny","value":38.75,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":0,"sourceName":"Liquid AI — IFStruct v1.0 blog (granite-4.0-h-tiny)","sourceUrl":"https://www.liquid.ai/blog/ifstruct-v1.0","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ibm-granite-granite-4.0-h-tiny.yaml","parameters":6939037248},{"benchmarkId":"openai/gsm8k","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":99.6,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":1023244718976},{"benchmarkId":"openai/gsm8k","modelId":"meta-llama/Llama-3.1-405B","value":96.8,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":94.12,"sourceName":"Model Card","sourceUrl":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"8-shot CoT","filename":".eval_results/gsm8k.yaml","parameters":405853388800},{"benchmarkId":"openai/gsm8k","modelId":"ibm-granite/granite-4.1-30b","value":94.16,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":88.24,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-30b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":28865728512},{"benchmarkId":"openai/gsm8k","modelId":"meta-llama/Llama-3.2-90B-Vision-Instruct","value":93.1008339651,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":82.35,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/41/24/41243885-1629-4ecf-bc92-be4fa346aeba.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":88593355323},{"benchmarkId":"openai/gsm8k","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":92.6,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":76.47,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":861608274846},{"benchmarkId":"openai/gsm8k","modelId":"ibm-granite/granite-4.1-8b","value":92.49,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":70.59,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-8b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":8791592960},{"benchmarkId":"openai/gsm8k","modelId":"microsoft/Phi-3-medium-4k-instruct","value":91,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":64.71,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/microsoft/Phi-3-medium-4k-instruct","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"8-shot CoT","filename":".eval_results/gsm8k.yaml","parameters":13960238080},{"benchmarkId":"openai/gsm8k","modelId":"Qwen/Qwen2-72B","value":89.5,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":58.82,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen2-72B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":72706203648},{"benchmarkId":"openai/gsm8k","modelId":"deepseek-ai/DeepSeek-V3","value":89.3,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":52.94,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":684531386000},{"benchmarkId":"openai/gsm8k","modelId":"ibm-granite/granite-4.1-3b","value":86.88,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":47.06,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-3b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":3402836480},{"benchmarkId":"openai/gsm8k","modelId":"microsoft/Phi-3.5-mini-instruct","value":86.2,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":41.18,"sourceName":"Phi-3 Technical Report","sourceUrl":"https://hf.co/papers/2404.14219","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":3821079552},{"benchmarkId":"openai/gsm8k","modelId":"internlm/internlm2_5-7b-chat","value":86,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":35.29,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/internlm2_5-7b-chat","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"0-shot CoT","filename":".eval_results/gsm8k.yaml","parameters":7737708544},{"benchmarkId":"openai/gsm8k","modelId":"microsoft/Phi-3-mini-4k-instruct","value":85.7,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":29.41,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/microsoft/Phi-3-mini-4k-instruct","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"8-shot CoT","filename":".eval_results/gsm8k.yaml","parameters":3821079552},{"benchmarkId":"openai/gsm8k","modelId":"JetBrains/Mellum2-12B-A2.5B-Base-Pretrain","value":81.73,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":20.59,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval, no-tools, exact match","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"openai/gsm8k","modelId":"JetBrains/Mellum2-12B-A2.5B-Base","value":81.73,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":20.59,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval (pre-YaRN), no-tools, exact match","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"openai/gsm8k","modelId":"Qwen/Qwen2-7B","value":79.9,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":11.76,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen2-7B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"4-shot","filename":".eval_results/gsm8k.yaml","parameters":7615616512},{"benchmarkId":"openai/gsm8k","modelId":"internlm/internlm2-chat-20b","value":79.6,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":5.88,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/internlm2-chat-20b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":19861149696},{"benchmarkId":"openai/gsm8k","modelId":"deepseek-ai/DeepSeek-V2","value":79.2,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gsm8k.yaml","parameters":235741434880},{"benchmarkId":"allenai/olmOCR-bench","modelId":"infly/Infinity-Parser2-Pro","value":87.6,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Infinity Parser technical report","sourceUrl":"https://huggingface.co/papers/2506.03197","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":35107181936},{"benchmarkId":"allenai/olmOCR-bench","modelId":"datalab-to/chandra-ocr-2","value":85.8,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":92.86,"sourceName":"Chandra OCR 2 Model Card","sourceUrl":"https://huggingface.co/datalab-to/chandra-ocr-2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":5295564288},{"benchmarkId":"allenai/olmOCR-bench","modelId":"rednote-hilab/dots.mocr","value":83.9,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":85.71,"sourceName":"dots.mocr technical report","sourceUrl":"https://huggingface.co/papers/2603.13032","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":3039179264},{"benchmarkId":"allenai/olmOCR-bench","modelId":"datalab-to/surya-ocr-2","value":83.3,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":78.57,"sourceName":"Surya OCR 2 Model Card","sourceUrl":"https://huggingface.co/datalab-to/surya-ocr-2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":686154304},{"benchmarkId":"allenai/olmOCR-bench","modelId":"lightonai/LightOnOCR-2-1B","value":83.2,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":71.43,"sourceName":"LightOnOCR technical report","sourceUrl":"https://huggingface.co/papers/2601.14251","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"H&F rewards omission, not transcription thus a model that outputs nothing scores perfectly. Excluded to keep Overall focused on real OCR quality.","filename":".eval_results/olmocrbench.yaml","parameters":1005647872},{"benchmarkId":"allenai/olmOCR-bench","modelId":"datalab-to/chandra","value":83.1,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":64.29,"sourceName":"OlmOCR-Bench Github repository","sourceUrl":"https://github.com/allenai/olmocr/tree/main/olmocr/bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":8767123696},{"benchmarkId":"allenai/olmOCR-bench","modelId":"infly/Infinity-Parser-7B","value":82.5,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":57.14,"sourceName":"Infinity Parser technical report","sourceUrl":"https://huggingface.co/papers/2506.03197","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":8292166656},{"benchmarkId":"allenai/olmOCR-bench","modelId":"tiiuae/Falcon-OCR","value":80.3,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":50,"sourceName":"Falcon-OCR Model Card","sourceUrl":"https://huggingface.co/tiiuae/Falcon-OCR","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"English-subset only","filename":".eval_results/olmocrbench.yaml","parameters":269944416},{"benchmarkId":"allenai/olmOCR-bench","modelId":"baidu/Qianfan-OCR","value":79.8,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":42.86,"sourceName":"Qianfan-OCR technical report","sourceUrl":"https://huggingface.co/papers/2603.13398","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/olm_ocr_bench.yaml","parameters":4741408256},{"benchmarkId":"allenai/olmOCR-bench","modelId":"rednote-hilab/dots.ocr","value":79.1,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":35.71,"sourceName":"dots.ocr technical report","sourceUrl":"https://huggingface.co/papers/2512.02498","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":3039179264},{"benchmarkId":"allenai/olmOCR-bench","modelId":"deepseek-ai/DeepSeek-OCR-2","value":76.3,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":28.57,"sourceName":"Tweet by @staghado","sourceUrl":"https://x.com/staghado/status/2016161372938117205/photo/1","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":3389119360},{"benchmarkId":"allenai/olmOCR-bench","modelId":"lightonai/LightOnOCR-1B-1025","value":76.1,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":21.43,"sourceName":"LightOnOCR technical report","sourceUrl":"https://huggingface.co/papers/2601.14251","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Excluding Headers & Footers category","filename":".eval_results/olmocrbench.yaml","parameters":1161230336},{"benchmarkId":"allenai/olmOCR-bench","modelId":"deepseek-ai/DeepSeek-OCR","value":75.7,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":14.29,"sourceName":"OlmOCR-Bench Github repository","sourceUrl":"https://github.com/allenai/olmocr/tree/main/olmocr/bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":3336106240},{"benchmarkId":"allenai/olmOCR-bench","modelId":"opendatalab/MinerU2.5-2509-1.2B","value":75.2,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":3.57,"sourceName":"MinerU2.5 technical report","sourceUrl":"https://huggingface.co/papers/2509.22186","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/olmocrbench.yaml","parameters":1156026624},{"benchmarkId":"allenai/olmOCR-bench","modelId":"zai-org/GLM-OCR","value":75.2,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":3.57,"sourceName":"GLM-OCR API evaluation","sourceUrl":"https://huggingface.co/zai-org/GLM-OCR","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Excluding Headers & Footers category. Using ZAI API.","filename":".eval_results/olmocrbench.yaml","parameters":1325258240},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5.2","value":54.7,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle.yaml","parameters":753329940480},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2.6","value":54,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":97.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":1058589420528},{"benchmarkId":"cais/hle","modelId":"tencent/Hy3","value":53.2,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":95,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":298786155776},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5.1","value":52.3,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":92.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":753864139008},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5","value":50.4,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":90,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":753864139008},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2.5","value":50.2,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":87.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":1058589420528},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-27B","value":48.5,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":85,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"with tools","filename":".eval_results/hle_with_tools_3.yaml","parameters":27781427952},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-397B-A17B","value":48.3,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":82.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":403397928944},{"benchmarkId":"cais/hle","modelId":"stepfun-ai/Step-3.7-Flash","value":48.1,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":80,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":201365316160},{"benchmarkId":"cais/hle","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":48,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":77.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"with tools","filename":".eval_results/hle.yaml","parameters":1023244718976},{"benchmarkId":"cais/hle","modelId":"InternScience/Agents-A1","value":47.6,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":75,"sourceName":"Agents-A1 model card","sourceUrl":"https://huggingface.co/InternScience/Agents-A1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/Agents-A1.yaml","parameters":35107181936},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-122B-A10B","value":47.5,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":72.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"with tools","filename":".eval_results/hle_with_tools_4.yaml","parameters":125086497008},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2-Thinking","value":44.9,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":70,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":1058118284416},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.7","value":42.8,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":67.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":358337791296},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5.2","value":40.5,"lowerIsBetter":false,"registryRank":15,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":753329940480},{"benchmarkId":"cais/hle","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":37.7,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":65,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":861608274846},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":37.4,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":61.25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":560524578816},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":37.4,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":61.25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":335038821080},{"benchmarkId":"cais/hle","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":34.8,"lowerIsBetter":false,"registryRank":19,"selected":true,"percentile":57.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":158069433298},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2.6","value":34.7,"lowerIsBetter":false,"registryRank":20,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":1058589420528},{"benchmarkId":"cais/hle","modelId":"PolarSeeker/OpenSeeker-v2-30B-SFT","value":34.6,"lowerIsBetter":false,"registryRank":21,"selected":true,"percentile":55,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/PolarSeeker/OpenSeeker-v2-30B-SFT","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":30532122624},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5.1","value":31,"lowerIsBetter":false,"registryRank":22,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":753864139008},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-5","value":30.5,"lowerIsBetter":false,"registryRank":23,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":753864139008},{"benchmarkId":"cais/hle","modelId":"tencent/Hy3-preview","value":30,"lowerIsBetter":false,"registryRank":24,"selected":true,"percentile":52.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3-preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Text-only","filename":".eval_results/hle.yaml","parameters":298786155776},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-397B-A17B","value":28.7,"lowerIsBetter":false,"registryRank":25,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":403397928944},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":26.7,"lowerIsBetter":false,"registryRank":26,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"No tools","filename":".eval_results/hle.yaml","parameters":560524578816},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":26.1,"lowerIsBetter":false,"registryRank":27,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"No tools","filename":".eval_results/hle.yaml","parameters":335038821080},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-122B-A10B","value":25.3,"lowerIsBetter":false,"registryRank":28,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"chain of thought","filename":".eval_results/hle_chain_of_thought_3.yaml","parameters":125086497008},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.7","value":24.8,"lowerIsBetter":false,"registryRank":29,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":358337791296},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2.5","value":24.37,"lowerIsBetter":false,"registryRank":30,"selected":false,"percentile":null,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/aa/05/aa055fe5-5174-4517-8b10-19d46da94f3e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":1058589420528},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.5-27B","value":24.3,"lowerIsBetter":false,"registryRank":31,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"chain of thought","filename":".eval_results/hle_chain_of_thought_2.yaml","parameters":27781427952},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.6-27B","value":24,"lowerIsBetter":false,"registryRank":32,"selected":true,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":27781427952},{"benchmarkId":"cais/hle","modelId":"moonshotai/Kimi-K2-Thinking","value":23.9,"lowerIsBetter":false,"registryRank":33,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":1058118284416},{"benchmarkId":"cais/hle","modelId":"stepfun-ai/Step-3.5-Flash","value":23.1,"lowerIsBetter":false,"registryRank":34,"selected":true,"percentile":47.5,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Text Only","filename":".eval_results/hle.yaml","parameters":199384301376},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":22.82,"lowerIsBetter":false,"registryRank":35,"selected":true,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":123611012096},{"benchmarkId":"cais/hle","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":22.82,"lowerIsBetter":false,"registryRank":36,"selected":true,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":123611012096},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":22.82,"lowerIsBetter":false,"registryRank":37,"selected":true,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":22.82,"lowerIsBetter":false,"registryRank":38,"selected":true,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":22.82,"lowerIsBetter":false,"registryRank":39,"selected":true,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/hle_with_tools.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"MiniMaxAI/MiniMax-M2.1","value":22.2,"lowerIsBetter":false,"registryRank":40,"selected":true,"percentile":32.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":228703644928},{"benchmarkId":"cais/hle","modelId":"XiaomiMiMo/MiMo-V2-Flash","value":22.1,"lowerIsBetter":false,"registryRank":41,"selected":true,"percentile":30,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":309785318400},{"benchmarkId":"cais/hle","modelId":"internlm/Intern-S2-Preview","value":21.94,"lowerIsBetter":false,"registryRank":42,"selected":true,"percentile":27.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Text only","filename":".eval_results/hle.yaml","parameters":36098254656},{"benchmarkId":"cais/hle","modelId":"Qwen/Qwen3.6-35B-A3B","value":21.4,"lowerIsBetter":false,"registryRank":43,"selected":true,"percentile":25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":35951822704},{"benchmarkId":"cais/hle","modelId":"MiniMaxAI/MiniMax-M2.5","value":19.4,"lowerIsBetter":false,"registryRank":44,"selected":true,"percentile":22.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":228703644928},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-120b","value":19,"lowerIsBetter":false,"registryRank":45,"selected":true,"percentile":20,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high, With tools","filename":".eval_results/hle_high_with_tools.yaml","parameters":120412337472},{"benchmarkId":"cais/hle","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":18.26,"lowerIsBetter":false,"registryRank":46,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":123611012096},{"benchmarkId":"cais/hle","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":18.26,"lowerIsBetter":false,"registryRank":47,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":123611012096},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":18.26,"lowerIsBetter":false,"registryRank":48,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":18.26,"lowerIsBetter":false,"registryRank":49,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":18.26,"lowerIsBetter":false,"registryRank":50,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":120668707840},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-20b","value":17.3,"lowerIsBetter":false,"registryRank":51,"selected":true,"percentile":17.5,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high, With tools","filename":".eval_results/hle_high_with_tools.yaml","parameters":21511953984},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-120b","value":14.9,"lowerIsBetter":false,"registryRank":52,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high","filename":".eval_results/hle_high.yaml","parameters":120412337472},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.7-Flash","value":14.4,"lowerIsBetter":false,"registryRank":53,"selected":true,"percentile":15,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":31221488576},{"benchmarkId":"cais/hle","modelId":"LGAI-EXAONE/K-EXAONE-236B-A23B","value":13.6,"lowerIsBetter":false,"registryRank":54,"selected":true,"percentile":12.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":237099669632},{"benchmarkId":"cais/hle","modelId":"MiniMaxAI/MiniMax-M2","value":12.5,"lowerIsBetter":false,"registryRank":55,"selected":true,"percentile":10,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":228703644928},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-120b","value":11.3,"lowerIsBetter":false,"registryRank":56,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium, With tools","filename":".eval_results/hle_medium_with_tools.yaml","parameters":120412337472},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-20b","value":10.9,"lowerIsBetter":false,"registryRank":57,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high","filename":".eval_results/hle_high.yaml","parameters":21511953984},{"benchmarkId":"cais/hle","modelId":"HelpingAI/Dhanishtha-2.0-0126","value":9.92,"lowerIsBetter":false,"registryRank":58,"selected":true,"percentile":7.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/HelpingAI/Dhanishtha-2.0-0126","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":14768307200},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-120b","value":9.1,"lowerIsBetter":false,"registryRank":59,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low, With tools","filename":".eval_results/hle_low_with_tools.yaml","parameters":120412337472},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-20b","value":8.8,"lowerIsBetter":false,"registryRank":60,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium, With tools","filename":".eval_results/hle_medium_with_tools.yaml","parameters":21511953984},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-120b","value":8.6,"lowerIsBetter":false,"registryRank":61,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium","filename":".eval_results/hle_medium.yaml","parameters":120412337472},{"benchmarkId":"cais/hle","modelId":"skt/A.X-K1","value":8.6,"lowerIsBetter":false,"registryRank":62,"selected":true,"percentile":5,"sourceName":"A.X K1 model card","sourceUrl":"https://huggingface.co/skt/A.X-K1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Humanity's Last Exam score reported in Thinking Mode.","filename":".eval_results/A.X-K1.yaml","parameters":518983059456},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.5","value":8.32,"lowerIsBetter":false,"registryRank":63,"selected":true,"percentile":2.5,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/93/cb/93cbdfdf-9ec6-4afb-87f4-d771cf29a378.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":358337791296},{"benchmarkId":"cais/hle","modelId":"zai-org/GLM-4.5-Air","value":8.12,"lowerIsBetter":false,"registryRank":64,"selected":true,"percentile":0,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/e9/03/e90308ab-e898-4434-aa93-13d131887737.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/hle.yaml","parameters":110468824832},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-20b","value":7,"lowerIsBetter":false,"registryRank":65,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium","filename":".eval_results/hle_medium.yaml","parameters":21511953984},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-20b","value":6.3,"lowerIsBetter":false,"registryRank":66,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low, With tools","filename":".eval_results/hle_low_with_tools.yaml","parameters":21511953984},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-120b","value":5.2,"lowerIsBetter":false,"registryRank":67,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low","filename":".eval_results/hle_low.yaml","parameters":120412337472},{"benchmarkId":"cais/hle","modelId":"openai/gpt-oss-20b","value":4.2,"lowerIsBetter":false,"registryRank":68,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low","filename":".eval_results/hle_low.yaml","parameters":21511953984},{"benchmarkId":"datacurve/deep-swe","modelId":"zai-org/GLM-5.2","value":46.2,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/deep-swe.yaml","parameters":753329940480},{"benchmarkId":"datacurve/deep-swe","modelId":"tencent/Hy3","value":28,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/deep-swe.yaml","parameters":298786155776},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-M2.1","value":88,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":99.64,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/dd/c9/ddc99cec-f5d3-4cc4-9cc5-bb534377b5f6.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":228703644928},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/Intern-S2-Preview","value":88,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":99.64,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":36098254656},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.5-397B-A17B","value":87.8,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":98.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":403397928944},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":87.5,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":97.84,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":861608274846},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"moonshotai/Kimi-K2.5","value":87.1,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":97.12,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1058589420528},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":86.8,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":96.04,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":560524578816},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":86.8,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":96.04,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":335038821080},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.5-122B-A10B","value":86.7,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":94.96,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/af/3c/af3c554a-1eb9-4a79-80dd-678c7aebf0aa.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":125086497008},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":86.4,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":94.24,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":158069433298},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.6-27B","value":86.2,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":93.53,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":27781427952},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.5-27B","value":86.1,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":92.81,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/15/df/15df0778-3ca6-4ff9-9b34-41f74dc4ced4.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":27781427952},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"zai-org/GLM-5","value":86,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":92.09,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/76/7d/767d7365-4f30-4ac0-9fc4-e0ade16a161f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":753864139008},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3.6-35B-A3B","value":85.2,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":91.37,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":35951822704},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-R1-0528","value":85,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":90.65,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":684531386000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"zai-org/GLM-4.5","value":84.6,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":89.93,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/04/c7/04c77f44-dff1-4cc7-80a1-35f4e9e9237f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":358337791296},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"stepfun-ai/Step-3.5-Flash","value":84.4,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":89.21,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":199384301376},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-R1","value":84,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":88.49,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":684531386000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/K-EXAONE-236B-A23B","value":83.8,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":87.77,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":237099669632},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":83.73,"lowerIsBetter":false,"registryRank":19,"selected":true,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":123611012096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":83.73,"lowerIsBetter":false,"registryRank":20,"selected":true,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":123611012096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":83.73,"lowerIsBetter":false,"registryRank":21,"selected":true,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":120668707840},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":83.73,"lowerIsBetter":false,"registryRank":22,"selected":true,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":120668707840},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":83.73,"lowerIsBetter":false,"registryRank":23,"selected":true,"percentile":85.61,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":120668707840},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/Intern-S1","value":83.5,"lowerIsBetter":false,"registryRank":24,"selected":true,"percentile":83.45,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4a/0a/4a0a0ab9-bb59-411e-a406-f6ac49a1e9f1.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":240709856128},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/EXAONE-4.5-33B","value":83.3,"lowerIsBetter":false,"registryRank":25,"selected":true,"percentile":82.73,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":34350097664},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-235B-A22B-Instruct-2507","value":83,"lowerIsBetter":false,"registryRank":26,"selected":true,"percentile":82.01,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/df/98/df9861f7-59cf-4b5e-8988-571481f47d14.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":235093634560},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ByteDance-Seed/Seed-OSS-36B-Instruct","value":82.7,"lowerIsBetter":false,"registryRank":27,"selected":true,"percentile":80.94,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/1b/40/1b405e01-7137-4189-b5d2-83e0f4004dc9.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":36151104512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meituan-longcat/LongCat-Flash-Chat","value":82.7,"lowerIsBetter":false,"registryRank":28,"selected":true,"percentile":80.94,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/19/91/1991ed80-048e-428c-a9f7-e32c71bd65ea.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":561862880256},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-M2","value":82,"lowerIsBetter":false,"registryRank":29,"selected":true,"percentile":79.86,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":228703644928},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"skt/A.X-K1","value":81.5,"lowerIsBetter":false,"registryRank":30,"selected":true,"percentile":79.14,"sourceName":"A.X K1 model card","sourceUrl":"https://huggingface.co/skt/A.X-K1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"English MMLU-Pro score reported in Thinking Mode.","filename":".eval_results/A.X-K1.yaml","parameters":518983059456},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"zai-org/GLM-4.5-Air","value":81.4,"lowerIsBetter":false,"registryRank":31,"selected":true,"percentile":78.42,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/07/43/074397da-f5e5-441c-bc45-ac16b599ca7c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":110468824832},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V3-0324","value":81.2,"lowerIsBetter":false,"registryRank":32,"selected":true,"percentile":77.7,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":684531386000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-M1-40k","value":81.1,"lowerIsBetter":false,"registryRank":33,"selected":true,"percentile":76.98,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/3b/7b/3b7bfaac-ee52-4508-8ecd-676d82e06c1c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":456089655296},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"jdopensource/JoyAI-LLM-Flash","value":81.02,"lowerIsBetter":false,"registryRank":34,"selected":true,"percentile":76.26,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/jdopensource/JoyAI-LLM-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":49286094592},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"moonshotai/Kimi-K2-Instruct","value":81,"lowerIsBetter":false,"registryRank":35,"selected":true,"percentile":75.54,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4a/ae/4aae2732-e24b-42a2-9dc1-a35cd215a8ec.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1026470731056},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-30B-A3B-Thinking-2507","value":80.9,"lowerIsBetter":false,"registryRank":36,"selected":true,"percentile":74.82,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/46/a3/46a34cab-9475-40a1-ba07-2c0528f6bf5d.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":30532122624},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"openai/gpt-oss-120b","value":80.8,"lowerIsBetter":false,"registryRank":37,"selected":true,"percentile":74.1,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/e4/8d/e48dbb1a-9e1a-4c99-abbf-cb32942b48e7.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":120412337472},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-M2.5","value":80.1,"lowerIsBetter":false,"registryRank":38,"selected":true,"percentile":73.38,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/c5/4c/c54c4ee8-ff99-4cda-a81f-a2e3a4347fb8.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":228703644928},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"baidu/ERNIE-4.5-300B-A47B-PT","value":78.4,"lowerIsBetter":false,"registryRank":39,"selected":true,"percentile":72.66,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/e6/6b/e66bffdc-f3d1-4808-90a4-43f204aa883e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":300474051776},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meituan-longcat/LongCat-Flash-Lite","value":78.29,"lowerIsBetter":false,"registryRank":40,"selected":true,"percentile":71.94,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":69073335552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"MiniMaxAI/MiniMax-Text-01","value":75.7,"lowerIsBetter":false,"registryRank":41,"selected":true,"percentile":71.22,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/2a/73/2a734d0f-7fcf-48d0-bea6-ad17cd749ee4.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":456089655296},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"openai/gpt-oss-20b","value":73.6,"lowerIsBetter":false,"registryRank":42,"selected":true,"percentile":70.5,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ca/ef/caef6dbc-0f07-4491-9009-2b0d26dc9724.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":21511953984},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-72B","value":71.59,"lowerIsBetter":false,"registryRank":43,"selected":true,"percentile":69.78,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/06/60/06600438-ea9f-4078-8eef-701c59af71a4.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":72706203648},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/phi-4","value":70.4,"lowerIsBetter":false,"registryRank":44,"selected":true,"percentile":69.06,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/c2/37/c23724de-5d83-4794-abcb-9af3ce249886.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":14659507200},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-4B-Instruct-2507","value":69.6,"lowerIsBetter":false,"registryRank":45,"selected":true,"percentile":68.35,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":4022468096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"baidu/ERNIE-4.5-300B-A47B-Base-PT","value":69.5,"lowerIsBetter":false,"registryRank":46,"selected":true,"percentile":67.63,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/bc/f1/bcf18d24-d600-4ed9-ba95-73f8d58569e1.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":299484163264},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-32B","value":69.23,"lowerIsBetter":false,"registryRank":47,"selected":true,"percentile":66.91,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/da/c5/dac51285-4928-4ac7-b052-510e4705981b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":32763876352},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":68.5,"lowerIsBetter":false,"registryRank":48,"selected":true,"percentile":66.19,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":1023244718976},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-235B-A22B","value":68.18,"lowerIsBetter":false,"registryRank":49,"selected":true,"percentile":65.47,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/99/98/99989790-84de-4fd9-af37-1d9c28dd95b3.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":235093634560},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Large-Instruct-2411","value":67.94,"lowerIsBetter":false,"registryRank":50,"selected":true,"percentile":64.75,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/03/98/03985ef7-288d-4421-9257-ce6b77dcd858.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":122610069504},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"tencent/Hunyuan-A13B-Instruct","value":67.3,"lowerIsBetter":false,"registryRank":51,"selected":true,"percentile":64.03,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4b/ff/4bffdd42-60c3-41a9-9ef8-e5849e114d9e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":80393183232},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Large-Instruct-2407","value":65.91,"lowerIsBetter":false,"registryRank":52,"selected":true,"percentile":63.31,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b7/99/b799f854-5a9c-413c-b766-ab127e0cd103.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":122610069504},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V2.5","value":65.83,"lowerIsBetter":false,"registryRank":53,"selected":true,"percentile":62.59,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/65/c2/65c29cb3-af56-45f1-be1b-751630185a59.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":235741434880},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ByteDance-Seed/Seed-OSS-36B-Base","value":65.1,"lowerIsBetter":false,"registryRank":54,"selected":true,"percentile":61.51,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/cf/2d/cf2d98c9-1e57-4994-9e49-9a7962a2706d.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":36151104512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16","value":65.1,"lowerIsBetter":false,"registryRank":55,"selected":true,"percentile":61.51,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/2a/e5/2ae5bb55-f5e3-4aa2-beef-141f450a4562.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":31577937344},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V3","value":64.4,"lowerIsBetter":false,"registryRank":56,"selected":true,"percentile":60.43,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu-pro.yaml","parameters":684531386000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-4.1-30b","value":64.09,"lowerIsBetter":false,"registryRank":57,"selected":true,"percentile":59.71,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-30b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":28865728512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-14B","value":63.69,"lowerIsBetter":false,"registryRank":58,"selected":true,"percentile":58.99,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/cc/7c/cc7c2263-9baf-45fc-b58b-64c15989e358.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":14770033664},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen3-30B-A3B-Base","value":61.7,"lowerIsBetter":false,"registryRank":59,"selected":true,"percentile":58.27,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/74/e6/74e614fc-75a5-4f12-b077-cbf525141a9f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":30532122624},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.1-405B","value":61.6,"lowerIsBetter":false,"registryRank":60,"selected":true,"percentile":57.55,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/50/a3/50a33ec6-cf9b-4acc-9f45-61cd8356207c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":405853388800},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"nvidia/Nemotron-H-56B-Base-8K","value":60.5,"lowerIsBetter":false,"registryRank":61,"selected":true,"percentile":56.83,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/8b/b3/8bb31817-e160-4285-a781-272851ae2c41.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":56324350464},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ByteDance-Seed/Seed-OSS-36B-Base-woSyn","value":60.4,"lowerIsBetter":false,"registryRank":62,"selected":true,"percentile":56.12,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/60/1d/601d782d-660b-4f01-bcae-5c4105223c85.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":36151104512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"tencent/Tencent-Hunyuan-Large","value":60.2,"lowerIsBetter":false,"registryRank":63,"selected":true,"percentile":55.4,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5c/9f/5c9f18ed-3247-4af2-b44f-2a504735554b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":null},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"JetBrains/Mellum2-12B-A2.5B-Base-Pretrain","value":59.31,"lowerIsBetter":false,"registryRank":64,"selected":true,"percentile":54.32,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval, no-tools, exact match","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"JetBrains/Mellum2-12B-A2.5B-Base","value":59.31,"lowerIsBetter":false,"registryRank":65,"selected":true,"percentile":54.32,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval (pre-YaRN), no-tools, exact match","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/EXAONE-3.5-32B-Instruct","value":58.91,"lowerIsBetter":false,"registryRank":66,"selected":true,"percentile":53.24,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/de/c9/dec9e4cf-cc67-42e1-9474-f8de9048014b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":32003200000},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"XiaomiMiMo/MiMo-7B-RL","value":58.6,"lowerIsBetter":false,"registryRank":67,"selected":true,"percentile":52.52,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/eb/b6/ebb62699-a109-4160-9f12-152a17ac9c5b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7833409536},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/internlm3-8b-instruct","value":57.6,"lowerIsBetter":false,"registryRank":68,"selected":true,"percentile":51.8,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/46/a7/46a7e0d0-c351-46ac-99f0-98aebcf3fef7.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8804241408},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"baidu/ERNIE-4.5-21B-A3B-Base-PT","value":56.7,"lowerIsBetter":false,"registryRank":69,"selected":true,"percentile":51.08,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5d/0e/5d0edbf1-b369-43eb-b885-d5a87c818d1f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":21825437888},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-4.1-8b","value":55.99,"lowerIsBetter":false,"registryRank":70,"selected":true,"percentile":50.36,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-8b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8791592960},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3-medium-4k-instruct","value":55.7,"lowerIsBetter":false,"registryRank":71,"selected":true,"percentile":49.64,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/63/f9/63f9e7e6-d69f-4522-a81d-7280eacf730c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":13960238080},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-V2-Chat","value":54.81,"lowerIsBetter":false,"registryRank":72,"selected":true,"percentile":48.92,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/a7/68/a768afc2-e0b4-4ea5-ba40-166136c33b3b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":235741434880},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Small-24B-Base-2501","value":54.4,"lowerIsBetter":false,"registryRank":73,"selected":true,"percentile":48.2,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/d4/89/d489ea6c-1287-43bd-aa64-5193c09331b2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":23572403200},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-4-mini-instruct","value":52.8,"lowerIsBetter":false,"registryRank":74,"selected":true,"percentile":47.48,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b2/6e/b26e73bc-2a30-4fa4-8223-148df3d82658.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3836021760},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Meta-Llama-3-70B","value":52.78,"lowerIsBetter":false,"registryRank":75,"selected":true,"percentile":46.76,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/77/50/77508bc1-dc52-4a84-9df1-deb62975c053.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":70553706496},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.1-70B","value":52.47,"lowerIsBetter":false,"registryRank":76,"selected":true,"percentile":46.04,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/3b/18/3b18649e-fd29-4193-a8c1-6d6d93d1ebd2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":70553706496},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-1.5-34B-Chat","value":52.29,"lowerIsBetter":false,"registryRank":77,"selected":true,"percentile":45.32,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/67/6f/676f4465-ce78-411a-9f5a-c97b3d2eac4f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":34388917248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3-medium-128k-instruct","value":51.91,"lowerIsBetter":false,"registryRank":78,"selected":true,"percentile":44.6,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/22/1e/221e4697-1155-4d8d-87df-9778573a3ad7.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":13960238080},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"TIGER-Lab/MAmmoTH2-8x7B-Plus","value":50.4,"lowerIsBetter":false,"registryRank":79,"selected":true,"percentile":43.88,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/17/d1/17d1bf78-2fbe-414d-b555-6d672f57ddf2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":46702792704},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen1.5-110B","value":49.93,"lowerIsBetter":false,"registryRank":80,"selected":true,"percentile":43.17,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/33/3e/333e0d9f-7e39-4da3-96cb-0501d2380c03.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":111209914368},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-4.1-3b","value":49.83,"lowerIsBetter":false,"registryRank":81,"selected":true,"percentile":42.45,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-3b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3402836480},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ai21labs/AI21-Jamba-Large-1.5","value":49.46,"lowerIsBetter":false,"registryRank":82,"selected":true,"percentile":41.73,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/aa/2b/aa2be737-1a21-4cc9-93f2-83316b7dc0cd.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":398555145696},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Small-Instruct-2409","value":48.4,"lowerIsBetter":false,"registryRank":83,"selected":true,"percentile":41.01,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/71/31/7131c1f0-8fce-4050-8117-51d9b5e651ca.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":22247282688},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"zai-org/glm-4-9b","value":47.92,"lowerIsBetter":false,"registryRank":84,"selected":true,"percentile":40.29,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/92/ff/92ff34d6-a9d7-48af-a31e-a72c2367edff.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":9399951392},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3.5-mini-instruct","value":47.87,"lowerIsBetter":false,"registryRank":85,"selected":true,"percentile":39.57,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/03/b7/03b77a5a-1723-4cab-9d50-1a634bf8b06a.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3821079552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct","value":46.24,"lowerIsBetter":false,"registryRank":86,"selected":true,"percentile":38.85,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/c6/8f/c68fc694-d6dd-4b2a-a699-e5f737ae550f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7818448896},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-1.5-9B-Chat","value":45.95,"lowerIsBetter":false,"registryRank":87,"selected":true,"percentile":38.13,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/94/9e/949ec028-f03f-4211-8783-c810af6489a4.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8829407232},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3-mini-4k-instruct","value":45.66,"lowerIsBetter":false,"registryRank":88,"selected":true,"percentile":37.41,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/05/3a/053a7b11-0d89-4289-bfe4-ed3eca7c4a97.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3821079552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"CohereLabs/aya-expanse-32b","value":45.41,"lowerIsBetter":false,"registryRank":89,"selected":true,"percentile":36.69,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/12/29/1229c8e0-d21f-43e8-a9c7-3ea0d09408d5.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":32296476672},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"google/gemma-2-9b","value":45.1,"lowerIsBetter":false,"registryRank":90,"selected":true,"percentile":35.97,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/76/6f/766fb522-5c40-49f9-bcad-bd5496404129.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":9241705984},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-7B","value":45,"lowerIsBetter":false,"registryRank":91,"selected":true,"percentile":35.25,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/0c/64/0c645bb3-1e9c-4400-a704-f99748356114.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7615616512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"microsoft/Phi-3-mini-128k-instruct","value":43.86,"lowerIsBetter":false,"registryRank":92,"selected":true,"percentile":34.53,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ab/4d/ab4d706d-1629-46ac-8db3-cb6fac6de332.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3821079552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-3B","value":43.73,"lowerIsBetter":false,"registryRank":93,"selected":true,"percentile":33.81,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ed/3a/ed3af7f3-5881-4ddd-bab1-75ecda64c98e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3085938688},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"TIGER-Lab/MAmmoTH2-8B-Plus","value":43.35,"lowerIsBetter":false,"registryRank":94,"selected":true,"percentile":33.09,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/1f/96/1f963bf0-4985-4d1f-a322-55865369de75.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-34B","value":43.03,"lowerIsBetter":false,"registryRank":95,"selected":true,"percentile":32.37,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9d/42/9d42931c-6ec3-48ac-ae0a-cebb9c1f68aa.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":34388917248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mathstral-7B-v0.1","value":42,"lowerIsBetter":false,"registryRank":96,"selected":true,"percentile":31.65,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b7/6c/b76c036b-b67b-4dd4-9c7f-d1938b83f254.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7248023552},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"XiaomiMiMo/MiMo-7B-Base","value":41.9,"lowerIsBetter":false,"registryRank":97,"selected":true,"percentile":30.94,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/67/a9/67a990d8-bf28-4d9e-94b8-a472bde1efbd.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7833409536},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct","value":41.57,"lowerIsBetter":false,"registryRank":98,"selected":true,"percentile":30.22,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/0c/0f/0c0f446a-6c2a-47c7-a120-4fafb90f92a3.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":15706484224},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mixtral-8x7B-v0.1","value":41.03,"lowerIsBetter":false,"registryRank":99,"selected":true,"percentile":29.5,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/2b/dd/2bddced4-34a8-4a1c-b582-90bfe03346f1.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":46702792704},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Meta-Llama-3-8B-Instruct","value":40.98,"lowerIsBetter":false,"registryRank":100,"selected":true,"percentile":28.78,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/3c/1f/3c1f9257-27aa-4da0-b772-60d62242a72b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"TIGER-Lab/MAmmoTH2-7B-Plus","value":40.85,"lowerIsBetter":false,"registryRank":101,"selected":true,"percentile":28.06,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/1b/16/1b16feea-1def-49ae-b3da-ee3af193a705.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7241732096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2-7B","value":40.73,"lowerIsBetter":false,"registryRank":102,"selected":true,"percentile":27.34,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/37/79/3779cfdb-412d-49fa-94d4-5c7ae1af8ac6.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7615616512},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-Nemo-Base-2407","value":39.77,"lowerIsBetter":false,"registryRank":103,"selected":true,"percentile":26.62,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/be/91/be919504-16fb-4669-8d9b-3bfdfd2e6364.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":12247782400},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct","value":39.1,"lowerIsBetter":false,"registryRank":104,"selected":true,"percentile":25.9,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ce/1a/ce1a8a1a-5d16-4403-9e85-bf0f3d72f09f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":2405327360},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-1.5-6B-Chat","value":38.23,"lowerIsBetter":false,"registryRank":105,"selected":true,"percentile":25.18,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/bd/05/bd056a61-8ede-45b4-823d-093343bdd880.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":6061035520},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen1.5-14B-Chat","value":38.02,"lowerIsBetter":false,"registryRank":106,"selected":true,"percentile":24.46,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/09/ca/09ca61cf-1158-46e6-aeae-1d68f5dfbc34.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":14167290880},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Ministral-8B-Instruct-2410","value":37.93,"lowerIsBetter":false,"registryRank":107,"selected":true,"percentile":23.74,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b0/f5/b0f59e78-883f-4c57-b728-b983c859f23f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8019808256},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"CohereLabs/c4ai-command-r-v01","value":37.9,"lowerIsBetter":false,"registryRank":108,"selected":true,"percentile":23.02,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b3/5f/b35fcd95-c193-4ed0-b50c-bc535af5756f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":34980831232},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/internlm2-math-plus-20b","value":37.1,"lowerIsBetter":false,"registryRank":109,"selected":true,"percentile":22.3,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/6f/ee/6fee4d03-47d0-4c2e-b449-978442fa002c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":19861149696},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"GSAI-ML/LLaDA-8B-Instruct","value":37,"lowerIsBetter":false,"registryRank":110,"selected":true,"percentile":21.58,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/67/cc/67cc35fb-ae5a-4632-91da-9346a6b2849e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8015581184},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"abacusai/Llama-3-Smaug-8B","value":36.93,"lowerIsBetter":false,"registryRank":111,"selected":true,"percentile":20.86,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b0/a9/b0a990c3-c1a2-4a69-abed-e1c2c51d8763.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.1-8B","value":36.6,"lowerIsBetter":false,"registryRank":112,"selected":true,"percentile":20.14,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/45/ba/45baf8ce-a6cc-412f-a134-2242a4af4c93.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Meta-Llama-3-8B","value":35.36,"lowerIsBetter":false,"registryRank":113,"selected":true,"percentile":19.42,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ac/75/ac75fe42-62e5-4ea9-a130-1eeacc8e9fb2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8030261248},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/deepseek-math-7b-instruct","value":35.3,"lowerIsBetter":false,"registryRank":114,"selected":true,"percentile":18.71,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/65/7f/657f147a-6450-42fe-a10d-e626f9000d29.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":null},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"deepseek-ai/DeepSeek-Coder-V2-Lite-Base","value":34.37,"lowerIsBetter":false,"registryRank":115,"selected":true,"percentile":17.99,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/1a/c8/1ac85691-ef95-4bf5-8618-6bac456e2792.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":15706484224},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"CohereLabs/aya-expanse-8b","value":33.74,"lowerIsBetter":false,"registryRank":116,"selected":true,"percentile":17.27,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/33/5b/335b15a4-a7fd-4ffc-81db-9d5feed90657.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8028033024},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"internlm/internlm2-math-plus-7b","value":33.5,"lowerIsBetter":false,"registryRank":117,"selected":true,"percentile":16.55,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/37/20/37203543-7ca5-4441-be5c-e4cbd12293c2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7737708544},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.1-8b-base","value":33.08,"lowerIsBetter":false,"registryRank":118,"selected":true,"percentile":15.83,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5b/c9/5bc90039-eb1c-4772-aa34-1cfb7c2343b6.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8170835968},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-1.5B","value":32.1,"lowerIsBetter":false,"registryRank":119,"selected":true,"percentile":15.11,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/e1/d5/e1d5921c-130a-44f8-ae14-baed069e565e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1543714304},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.0-8b-base","value":31.03,"lowerIsBetter":false,"registryRank":120,"selected":true,"percentile":14.39,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/d9/f9/d9f9b73a-5b6d-418b-8f26-f89b4d2b6792.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":8170835968},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistralai/Mistral-7B-Instruct-v0.2","value":30.84,"lowerIsBetter":false,"registryRank":121,"selected":true,"percentile":13.67,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9d/8d/9d8dc94b-067c-478d-aa99-874b71721fc3.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7241732096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"mistral-community/Mistral-7B-v0.2","value":30.43,"lowerIsBetter":false,"registryRank":122,"selected":true,"percentile":12.95,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/93/21/9321cec5-309d-4328-aa2c-709af17cff9c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7241732096},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen1.5-7B-Chat","value":29.06,"lowerIsBetter":false,"registryRank":123,"selected":true,"percentile":12.23,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/db/e1/dbe12346-25db-4fac-9421-5153fc4c661c.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":7721324544},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-6B-Chat","value":28.84,"lowerIsBetter":false,"registryRank":124,"selected":true,"percentile":11.51,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/28/1d/281df2d2-60b5-4053-b30e-bba4976c3efd.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":6061035520},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"01-ai/Yi-6B","value":26.51,"lowerIsBetter":false,"registryRank":125,"selected":true,"percentile":10.79,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/8b/02/8b02ff6f-b3ae-4230-8edd-50c3ffa34592.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":6061035520},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.1-2b-base","value":23.89,"lowerIsBetter":false,"registryRank":126,"selected":true,"percentile":10.07,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/d4/c0/d4c06d3d-8a53-44e5-9db6-ebffc99390d2.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":2533525504},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"EleutherAI/llemma_7b","value":23.45,"lowerIsBetter":false,"registryRank":127,"selected":true,"percentile":9.35,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/f0/87/f087fc33-d4b9-4939-b3cf-2d3fb9094177.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":null},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2-1.5B-Instruct","value":22.62,"lowerIsBetter":false,"registryRank":128,"selected":true,"percentile":8.63,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/18/ea/18ea6501-7d93-4ec4-bd82-86991bb5cc68.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1543714304},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2-1.5B","value":22.56,"lowerIsBetter":false,"registryRank":129,"selected":true,"percentile":7.91,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ff/fc/fffc978a-e6ae-41f2-bded-06bb776ee8b9.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1543714304},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.2-3B","value":22.17,"lowerIsBetter":false,"registryRank":130,"selected":true,"percentile":7.19,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/91/89/9189a395-7ef2-453e-84e0-259870efc2f7.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3212749824},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.0-2b-base","value":21.72,"lowerIsBetter":false,"registryRank":131,"selected":true,"percentile":6.47,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/06/7f/067fe2c1-7ba3-4f79-8344-e55e999ae537.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":2533525504},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.1-3b-a800m-base","value":20.39,"lowerIsBetter":false,"registryRank":132,"selected":true,"percentile":5.76,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/a9/31/a931868f-9ae1-4cd5-a2a7-8ea402101bbe.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":3298788864},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"HuggingFaceTB/SmolLM2-1.7B","value":18.31,"lowerIsBetter":false,"registryRank":133,"selected":true,"percentile":5.04,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/33/c9/33c9180c-621e-40a2-bb6f-02b90ecff1fd.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1711376384},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2-0.5B","value":14.97,"lowerIsBetter":false,"registryRank":134,"selected":true,"percentile":4.32,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/85/72/8572a257-22bc-45c5-8891-d698ba6fc206.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":494032768},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-0.5B","value":14.92,"lowerIsBetter":false,"registryRank":135,"selected":true,"percentile":3.6,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5b/03/5b03aafd-e973-4ea4-850c-2ab97c1abb27.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":494032768},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"ibm-granite/granite-3.1-1b-a400m-base","value":12.34,"lowerIsBetter":false,"registryRank":136,"selected":true,"percentile":2.88,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4a/f2/4af2fd82-845a-4087-83eb-ae9b4b7561d1.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1334625280},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"meta-llama/Llama-3.2-1B","value":11.95,"lowerIsBetter":false,"registryRank":137,"selected":true,"percentile":2.16,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/d5/a3/d5a3c88a-3fee-40b3-a8c7-8c4cc65baf5f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":1235814400},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"HuggingFaceTB/SmolLM2-360M","value":11.38,"lowerIsBetter":false,"registryRank":138,"selected":true,"percentile":1.44,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/23/ae/23aee40b-5bea-46cf-a87b-8263e12e2d1f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":361821120},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"HuggingFaceTB/SmolLM2-135M","value":10.85,"lowerIsBetter":false,"registryRank":139,"selected":true,"percentile":0.72,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/ac/90/ac90804d-cb99-41cc-b3e7-65ed31484008.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":134515008},{"benchmarkId":"TIGER-Lab/MMLU-Pro","modelId":"Qwen/Qwen2.5-VL-72B-Instruct","value":0.6494348404255319,"lowerIsBetter":false,"registryRank":140,"selected":true,"percentile":0,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9c/45/9c455b8c-1153-4c24-9de0-1d506297d805.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":null,"filename":".eval_results/mmlu_pro.yaml","parameters":73410777344},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"deepreinforce-ai/Ornith-1.0-397B","value":62.2,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Ornith-1.0-397B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-397B.yaml","parameters":396802360816},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"zai-org/GLM-5.2","value":62.1,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":96.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":753329940480},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MiniMaxAI/MiniMax-M3","value":59,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Testing logic is aligned with the official evaluation.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":59,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Testing logic is aligned with the official evaluation.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":59,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Testing logic is aligned with the official evaluation.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"moonshotai/Kimi-K2.6","value":58.6,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":83.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":1058589420528},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"zai-org/GLM-5.1","value":58.4,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":80,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"high reasoning","filename":".eval_results/swe_bench_pro.yaml","parameters":753864139008},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"tencent/Hy3","value":57.9,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":76.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":298786155776},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":57.2,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":73.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":1023244718976},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"stepfun-ai/Step-3.7-Flash","value":56.3,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":70,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":201365316160},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MiniMaxAI/MiniMax-M2.7","value":56.2,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":66.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":228703644928},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"XiaomiMiMo/MiMo-V2.5","value":56.1,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":63.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":310775040000},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MiniMaxAI/MiniMax-M2.5","value":55.4,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":58.33,"sourceName":"Model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":228703644928},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":55.4,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":58.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":861608274846},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3.6-27B","value":53.5,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":53.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":27781427952},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"moonshotai/Kimi-K2.5","value":50.7,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":1058589420528},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"deepreinforce-ai/Ornith-1.0-35B","value":50.4,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":46.67,"sourceName":"Ornith-1.0-35B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-35B.yaml","parameters":664944},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3.6-35B-A3B","value":49.5,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":43.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":35951822704},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"poolside/Laguna-M.1","value":49.2,"lowerIsBetter":false,"registryRank":19,"selected":true,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-M.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":225795725568},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"poolside/Laguna-XS-2.1","value":47.6,"lowerIsBetter":false,"registryRank":20,"selected":true,"percentile":36.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":33442617088},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"poolside/Laguna-XS.2","value":46.3,"lowerIsBetter":false,"registryRank":21,"selected":true,"percentile":33.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":33442617088},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MuVeraAI/Laguna-XS.2","value":44.5,"lowerIsBetter":false,"registryRank":22,"selected":true,"percentile":30,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_pro.yaml","parameters":33442617088},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3-Coder-Next","value":44.3,"lowerIsBetter":false,"registryRank":23,"selected":true,"percentile":26.67,"sourceName":"Qwen3-Coder-Next technical report","sourceUrl":"https://huggingface.co/papers/2603.00729","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"SWE-Agent as harness","filename":".eval_results/.eval_results/swe_bench_pro.yaml","parameters":79674391296},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"deepreinforce-ai/Ornith-1.0-9B","value":42.9,"lowerIsBetter":false,"registryRank":24,"selected":true,"percentile":23.33,"sourceName":"Ornith-1.0-9B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-9B.yaml","parameters":1469680},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"CohereLabs/North-Mini-Code-1.0","value":40.2,"lowerIsBetter":false,"registryRank":25,"selected":true,"percentile":20,"sourceName":"North Mini Code Model Page","sourceUrl":"https://huggingface.co/CohereLabs/North-Mini-Code-1.0","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/swe-bench-pro.yaml","parameters":30484303872},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct","value":38.7,"lowerIsBetter":false,"registryRank":26,"selected":true,"percentile":16.67,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":480154875392},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"MiniMaxAI/MiniMax-M2.1","value":36.81,"lowerIsBetter":false,"registryRank":27,"selected":true,"percentile":13.33,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":228703644928},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"moonshotai/Kimi-K2-Instruct","value":27.67,"lowerIsBetter":false,"registryRank":28,"selected":true,"percentile":10,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":1026470731056},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"Qwen/Qwen3-235B-A22B","value":21.41,"lowerIsBetter":false,"registryRank":29,"selected":true,"percentile":6.67,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":235093634560},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"openai/gpt-oss-120b","value":16.2,"lowerIsBetter":false,"registryRank":30,"selected":true,"percentile":3.33,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":120412337472},{"benchmarkId":"ScaleAI/SWE-bench_Pro","modelId":"zai-org/GLM-4.6","value":9.67,"lowerIsBetter":false,"registryRank":31,"selected":true,"percentile":0,"sourceName":"SWE-Bench Pro official evaluation results","sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/swe_bench_pro.yaml","parameters":356785898816},{"benchmarkId":"mercor/apex-agents","modelId":"MiniMaxAI/MiniMax-M3","value":27.7,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on the apex-agents benchmark.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"mercor/apex-agents","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":27.7,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on the apex-agents benchmark.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"mercor/apex-agents","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":27.7,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":90,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on the apex-agents benchmark.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"mercor/apex-agents","modelId":"tencent/Hy3","value":25.6,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":70,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/apex-agents.yaml","parameters":298786155776},{"benchmarkId":"mercor/apex-agents","modelId":"zai-org/GLM-5","value":17.2,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":60,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: thinking","filename":".eval_results/apex-agents.yaml","parameters":753864139008},{"benchmarkId":"mercor/apex-agents","modelId":"moonshotai/Kimi-K2.5","value":14.4,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":50,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: thinking","filename":".eval_results/apex-agents.yaml","parameters":1058589420528},{"benchmarkId":"mercor/apex-agents","modelId":"Qwen/Qwen3.5-397B-A17B","value":13.6,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":40,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: thinking","filename":".eval_results/apex-agents.yaml","parameters":403397928944},{"benchmarkId":"mercor/apex-agents","modelId":"MiniMaxAI/MiniMax-M2.5","value":6.2,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":30,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: high","filename":".eval_results/apex-agents.yaml","parameters":228703644928},{"benchmarkId":"mercor/apex-agents","modelId":"moonshotai/Kimi-K2-Instruct","value":4.1,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":20,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: thinking","filename":".eval_results/apex-agents.yaml","parameters":1026470731056},{"benchmarkId":"mercor/apex-agents","modelId":"zai-org/GLM-4.6","value":4,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":10,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: high","filename":".eval_results/apex-agents.yaml","parameters":356785898816},{"benchmarkId":"mercor/apex-agents","modelId":"zai-org/GLM-4.7","value":3.1,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":0,"sourceName":"APEX-Agents Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-agents-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: react_toolbelt_agent; reasoning_effort: high","filename":".eval_results/apex-agents.yaml","parameters":358337791296},{"benchmarkId":"benchflow/skillsbench","modelId":"zai-org/GLM-5.1","value":58.4,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":753864139008},{"benchmarkId":"benchflow/skillsbench","modelId":"tencent/Hy3","value":55.3,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":85.71,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/skillsbench.yaml","parameters":298786155776},{"benchmarkId":"benchflow/skillsbench","modelId":"moonshotai/Kimi-K2.6","value":54,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":71.43,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":1058589420528},{"benchmarkId":"benchflow/skillsbench","modelId":"MiniMaxAI/MiniMax-M3","value":53,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":57.14,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":427040140160},{"benchmarkId":"benchflow/skillsbench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":50.1,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":42.86,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":861608274846},{"benchmarkId":"benchflow/skillsbench","modelId":"Qwen/Qwen3.6-27B","value":48.2,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":28.57,"sourceName":"Qwen3.6-27B model card — Benchmark Results (Language > Coding Agent)","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"SkillsBench Avg5. Evaluated via OpenCode on 78 tasks (self-contained subset, excluding API-dependent tasks); avg of 5 runs. Mapped to the Hub's benchflow/skillsbench task skillsbench_v1_1.","filename":".eval_results/Qwen3.6-27B.yaml","parameters":27781427952},{"benchmarkId":"benchflow/skillsbench","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":44.7,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":14.29,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":158069433298},{"benchmarkId":"benchflow/skillsbench","modelId":"MiniMaxAI/MiniMax-M2.7","value":34.9,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":0,"sourceName":"SkillsBench v1.1 official leaderboard","sourceUrl":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"with-skills; BenchFlow harness; OpenHands agent; 87 tasks x 3 trials; full 261/261 coverage","filename":".eval_results/skillsbench.yaml","parameters":228703644928},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5.2","value":91.2,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":753329940480},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-398B-JGOS","value":90.9,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":98.68,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-398B-JGOS","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"greedy decoding (temperature=0), single-sample (no voting / no test-time engine), max_tokens=16384, options shuffled seed=42; hardware: NVIDIA B200 x6 (TP2 x PP3), vLLM bfloat16","filename":".eval_results/gpqa_diamond.yaml","parameters":403397928944},{"benchmarkId":"Idavidrein/gpqa","modelId":"moonshotai/Kimi-K2.6","value":90.5,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":97.37,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":1058589420528},{"benchmarkId":"Idavidrein/gpqa","modelId":"tencent/Hy3","value":90.4,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":96.05,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":298786155776},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":90.1,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":94.74,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":861608274846},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-28B-REASON","value":89.39,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":93.42,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-28B-REASON","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Darwin-DELPHI test-time engine, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":26895998464},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.5-397B-A17B","value":88.4,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":91.45,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":403397928944},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-36B-Opus","value":88.4,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":91.45,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-36B-Opus","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Standard inference, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":34660610688},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-60B-DUO","value":88.38,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":89.47,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-60B-DUO","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"DELPHI cascade system, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":null},{"benchmarkId":"Idavidrein/gpqa","modelId":"inclusionAI/Ring-2.6-1T","value":88.27,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":88.16,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ring-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"xhigh reasoning effort, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":1025657871744},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":88.1,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":86.84,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":158069433298},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":87.9,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":85.53,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"No tools","filename":".eval_results/gpqa.yaml","parameters":335038821080},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.7-FP8","value":87.8787878788,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":84.21,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/97/fa/97faabc6-a7ca-4cad-8d29-307103287d91.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":358458391872},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.6-27B","value":87.8,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":82.89,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":27781427952},{"benchmarkId":"Idavidrein/gpqa","modelId":"moonshotai/Kimi-K2.5","value":87.6,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":81.58,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":1058589420528},{"benchmarkId":"Idavidrein/gpqa","modelId":"moonshotai/Kimi-K2.5","value":87.3737373737,"lowerIsBetter":false,"registryRank":16,"selected":false,"percentile":null,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5c/4b/5c4b9bd9-14db-4c11-bf99-9661461459f6.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":1058589420528},{"benchmarkId":"Idavidrein/gpqa","modelId":"tencent/Hy3-preview","value":87.2,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":80.26,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3-preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":298786155776},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":87,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":78.95,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"No tools","filename":".eval_results/gpqa.yaml","parameters":560524578816},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-27B-Opus","value":86.9,"lowerIsBetter":false,"registryRank":19,"selected":true,"percentile":77.63,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-27B-Opus","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Standard inference, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":27781427952},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.5-122B-A10B","value":86.6,"lowerIsBetter":false,"registryRank":20,"selected":true,"percentile":76.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_1.yaml","parameters":125086497008},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5.1","value":86.2,"lowerIsBetter":false,"registryRank":21,"selected":true,"percentile":75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":753864139008},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5","value":86,"lowerIsBetter":false,"registryRank":22,"selected":true,"percentile":73.03,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":753864139008},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.6-35B-A3B","value":86,"lowerIsBetter":false,"registryRank":23,"selected":true,"percentile":73.03,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":35951822704},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-31B-Opus","value":85.9,"lowerIsBetter":false,"registryRank":24,"selected":true,"percentile":71.05,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-31B-Opus","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Standard inference, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":32682372656},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.7","value":85.7,"lowerIsBetter":false,"registryRank":25,"selected":true,"percentile":69.74,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":358337791296},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.5-27B","value":85.5,"lowerIsBetter":false,"registryRank":26,"selected":true,"percentile":68.42,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_1.yaml","parameters":27781427952},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5-FP8","value":85.3535353535,"lowerIsBetter":false,"registryRank":27,"selected":true,"percentile":67.11,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/8a/87/8a87d622-4abb-48a7-8ac3-594e31a85525.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":753910024032},{"benchmarkId":"Idavidrein/gpqa","modelId":"MiniMaxAI/MiniMax-M2.5","value":85.2,"lowerIsBetter":false,"registryRank":28,"selected":true,"percentile":65.79,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":228703644928},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-4B-David","value":85,"lowerIsBetter":false,"registryRank":29,"selected":true,"percentile":64.47,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-4B-David","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"4B class Gen-2 evolution, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":7996156490},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.5-122B-A10B","value":84.8484848485,"lowerIsBetter":false,"registryRank":30,"selected":false,"percentile":null,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/58/60/5860f5bd-926e-4ece-bc87-a1af551a6280.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":125086497008},{"benchmarkId":"Idavidrein/gpqa","modelId":"moonshotai/Kimi-K2-Thinking","value":84.5,"lowerIsBetter":false,"registryRank":31,"selected":true,"percentile":63.16,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":1058118284416},{"benchmarkId":"Idavidrein/gpqa","modelId":"FINAL-Bench/Darwin-9B-NEG","value":84.34,"lowerIsBetter":false,"registryRank":32,"selected":true,"percentile":61.18,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/FINAL-Bench/Darwin-9B-NEG","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"9B class, standard inference, Pass@1","filename":".eval_results/gpqa_diamond.yaml","parameters":9653104368},{"benchmarkId":"Idavidrein/gpqa","modelId":"JGOS-Model/JGOS-31B-Citizen","value":84.34,"lowerIsBetter":false,"registryRank":33,"selected":true,"percentile":61.18,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/JGOS-Model/JGOS-31B-Citizen","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"maj@8 + DELPHI + near-miss maj@32-64 weighted vote, Pass@1 (167/198)","filename":".eval_results/gpqa_diamond.yaml","parameters":31273086512},{"benchmarkId":"Idavidrein/gpqa","modelId":"openpangu/openPangu-2.0-Flash","value":83.7,"lowerIsBetter":false,"registryRank":34,"selected":true,"percentile":59.21,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@4, Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"Idavidrein/gpqa","modelId":"stepfun-ai/Step-3.5-Flash","value":83.5,"lowerIsBetter":false,"registryRank":35,"selected":true,"percentile":57.89,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":199384301376},{"benchmarkId":"Idavidrein/gpqa","modelId":"XiaomiMiMo/MiMo-V2-Flash","value":83.3333333333,"lowerIsBetter":false,"registryRank":36,"selected":true,"percentile":55.92,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/36/22/3622b785-41c0-4a96-b867-5bde46851587.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":309785318400},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-5.1-FP8","value":83.3333333333,"lowerIsBetter":false,"registryRank":37,"selected":true,"percentile":55.92,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/52/23/522348c0-d242-4517-b97c-4e55c4261882.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":753910024032},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":82.7,"lowerIsBetter":false,"registryRank":38,"selected":true,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":123611012096},{"benchmarkId":"Idavidrein/gpqa","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":82.7,"lowerIsBetter":false,"registryRank":39,"selected":true,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":123611012096},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":82.7,"lowerIsBetter":false,"registryRank":40,"selected":true,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":82.7,"lowerIsBetter":false,"registryRank":41,"selected":true,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":82.7,"lowerIsBetter":false,"registryRank":42,"selected":true,"percentile":51.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"With tools","filename":".eval_results/gpqa_with_tools.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3.5-27B","value":81.8181818182,"lowerIsBetter":false,"registryRank":43,"selected":false,"percentile":null,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5b/a4/5ba4cf19-18b3-4d08-bad0-ef29422cb18a.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":27781427952},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.6-FP8","value":81.3131313131,"lowerIsBetter":false,"registryRank":44,"selected":true,"percentile":47.37,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/7e/18/7e18ad63-4a0a-4d9d-a4ec-40b683b42981.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":358458543424},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-120b","value":80.9,"lowerIsBetter":false,"registryRank":45,"selected":true,"percentile":46.05,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high, With tools","filename":".eval_results/gpqa_diamond_high_with_tools.yaml","parameters":120412337472},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-120b","value":80.8080808081,"lowerIsBetter":false,"registryRank":46,"selected":false,"percentile":null,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5d/3e/5d3e8832-c770-4796-957b-dfaefbd3bb2a.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":120412337472},{"benchmarkId":"Idavidrein/gpqa","modelId":"MiniMaxAI/MiniMax-M2.1","value":80.8080808081,"lowerIsBetter":false,"registryRank":47,"selected":true,"percentile":44.74,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/08/7b/087b0dc6-3c87-4f40-8458-16f19de92200.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":228703644928},{"benchmarkId":"Idavidrein/gpqa","modelId":"meituan-longcat/LongCat-Flash-Thinking-2601","value":80.5,"lowerIsBetter":false,"registryRank":48,"selected":true,"percentile":42.76,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":561862880256},{"benchmarkId":"Idavidrein/gpqa","modelId":"LGAI-EXAONE/EXAONE-4.5-33B","value":80.5,"lowerIsBetter":false,"registryRank":49,"selected":true,"percentile":42.76,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":34350097664},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-120b","value":80.1,"lowerIsBetter":false,"registryRank":50,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high","filename":".eval_results/gpqa_diamond_high.yaml","parameters":120412337472},{"benchmarkId":"Idavidrein/gpqa","modelId":"openpangu/openPangu-2.0-Flash","value":79.8,"lowerIsBetter":false,"registryRank":51,"selected":false,"percentile":null,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@4, Non-Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":79.23,"lowerIsBetter":false,"registryRank":52,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":123611012096},{"benchmarkId":"Idavidrein/gpqa","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":79.23,"lowerIsBetter":false,"registryRank":53,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":123611012096},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":79.23,"lowerIsBetter":false,"registryRank":54,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":79.23,"lowerIsBetter":false,"registryRank":55,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":79.23,"lowerIsBetter":false,"registryRank":56,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":120668707840},{"benchmarkId":"Idavidrein/gpqa","modelId":"LGAI-EXAONE/K-EXAONE-236B-A23B","value":79.1,"lowerIsBetter":false,"registryRank":57,"selected":true,"percentile":40.79,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":237099669632},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-R1-0528","value":78.7878787879,"lowerIsBetter":false,"registryRank":58,"selected":true,"percentile":39.47,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/a1/dd/a1dd2ea2-f092-423e-bc53-04c2fba5948d.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa_diamond.yaml","parameters":684531386000},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","value":77.2727272727,"lowerIsBetter":false,"registryRank":59,"selected":true,"percentile":38.16,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/bd/1f/bd1fe04f-7d58-4045-be60-7150500d537f.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":123611012096},{"benchmarkId":"Idavidrein/gpqa","modelId":"nvidia/Nemotron-Cascade-2-30B-A3B","value":76.1,"lowerIsBetter":false,"registryRank":60,"selected":true,"percentile":36.84,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":31577937344},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.7-Flash","value":75.2,"lowerIsBetter":false,"registryRank":61,"selected":true,"percentile":35.53,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":31221488576},{"benchmarkId":"Idavidrein/gpqa","modelId":"jdopensource/JoyAI-LLM-Flash","value":74.43,"lowerIsBetter":false,"registryRank":62,"selected":true,"percentile":34.21,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/jdopensource/JoyAI-LLM-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":49286094592},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-20b","value":74.2,"lowerIsBetter":false,"registryRank":63,"selected":true,"percentile":32.89,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high, With tools","filename":".eval_results/gpqa_diamond_high_with_tools.yaml","parameters":21511953984},{"benchmarkId":"Idavidrein/gpqa","modelId":"skt/A.X-K1","value":74,"lowerIsBetter":false,"registryRank":64,"selected":true,"percentile":31.58,"sourceName":"A.X K1 model card","sourceUrl":"https://huggingface.co/skt/A.X-K1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"GPQA-Diamond score reported in Thinking Mode.","filename":".eval_results/A.X-K1.yaml","parameters":518983059456},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-120b","value":73.5,"lowerIsBetter":false,"registryRank":65,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium, With tools","filename":".eval_results/gpqa_diamond_medium_with_tools.yaml","parameters":120412337472},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-120b","value":73.1,"lowerIsBetter":false,"registryRank":66,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium","filename":".eval_results/gpqa_diamond_medium.yaml","parameters":120412337472},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3-30B-A3B-Thinking-2507","value":72.2222222222,"lowerIsBetter":false,"registryRank":67,"selected":true,"percentile":30.26,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4b/02/4b02c12c-3f7b-45c8-b746-c590860a7a36.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":30532122624},{"benchmarkId":"Idavidrein/gpqa","modelId":"zai-org/GLM-4.5-Air","value":71.7171717172,"lowerIsBetter":false,"registryRank":68,"selected":true,"percentile":28.95,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9c/77/9c7740fd-9cad-445c-9681-eb576e2a110e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":110468824832},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-R1","value":71.5,"lowerIsBetter":false,"registryRank":69,"selected":true,"percentile":27.63,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":684531386000},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-20b","value":71.5,"lowerIsBetter":false,"registryRank":70,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high","filename":".eval_results/gpqa_diamond_high.yaml","parameters":21511953984},{"benchmarkId":"Idavidrein/gpqa","modelId":"mistralai/Mistral-Small-4-119B-2603","value":71.2,"lowerIsBetter":false,"registryRank":71,"selected":true,"percentile":26.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"reasoning: high","filename":".eval_results/gpqa_diamond.yaml","parameters":119401317952},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-120b","value":68.1,"lowerIsBetter":false,"registryRank":72,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low, With tools","filename":".eval_results/gpqa_diamond_low_with_tools.yaml","parameters":120412337472},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-120b","value":67.1,"lowerIsBetter":false,"registryRank":73,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low","filename":".eval_results/gpqa_diamond_low.yaml","parameters":120412337472},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-20b","value":67.1,"lowerIsBetter":false,"registryRank":74,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium, With tools","filename":".eval_results/gpqa_diamond_medium_with_tools.yaml","parameters":21511953984},{"benchmarkId":"Idavidrein/gpqa","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":66.7,"lowerIsBetter":false,"registryRank":75,"selected":true,"percentile":25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":1023244718976},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-20b","value":66,"lowerIsBetter":false,"registryRank":76,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium","filename":".eval_results/gpqa_diamond_medium.yaml","parameters":21511953984},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3-4B-Thinking-2507","value":65.8,"lowerIsBetter":false,"registryRank":77,"selected":true,"percentile":23.68,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":4022468096},{"benchmarkId":"Idavidrein/gpqa","modelId":"Qwen/Qwen3-4B-Instruct-2507","value":62,"lowerIsBetter":false,"registryRank":78,"selected":true,"percentile":22.37,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":4022468096},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-20b","value":58.5858585859,"lowerIsBetter":false,"registryRank":79,"selected":false,"percentile":null,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/6f/c3/6fc3630c-36f0-4ba9-9f34-3c9f73dec76a.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":21511953984},{"benchmarkId":"Idavidrein/gpqa","modelId":"deepseek-ai/DeepSeek-V3","value":58.2070707071,"lowerIsBetter":false,"registryRank":80,"selected":true,"percentile":21.05,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/0a/db/0adbcd9f-38e6-414a-88b1-7bd928d4c72e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa_diamond.yaml","parameters":684531386000},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-20b","value":58,"lowerIsBetter":false,"registryRank":81,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low, With tools","filename":".eval_results/gpqa_diamond_low_with_tools.yaml","parameters":21511953984},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Thinking","value":57.6,"lowerIsBetter":false,"registryRank":82,"selected":true,"percentile":19.74,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"post-training eval (SFT + RLVR), with thinking, no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"openai/gpt-oss-20b","value":56.8,"lowerIsBetter":false,"registryRank":83,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low","filename":".eval_results/gpqa_diamond_low.yaml","parameters":21511953984},{"benchmarkId":"Idavidrein/gpqa","modelId":"CohereLabs/c4ai-command-a-03-2025","value":50.5050505051,"lowerIsBetter":false,"registryRank":84,"selected":true,"percentile":18.42,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b2/77/b27740dc-a017-4738-8dd0-c18973b61d9e.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":111057580032},{"benchmarkId":"Idavidrein/gpqa","modelId":"meta-llama/Llama-3.2-90B-Vision-Instruct","value":46.0858585859,"lowerIsBetter":false,"registryRank":85,"selected":true,"percentile":17.11,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/94/0f/940ff5c0-b932-4c37-9eb5-27cbd4997484.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":88593355323},{"benchmarkId":"Idavidrein/gpqa","modelId":"ibm-granite/granite-4.1-30b","value":45.76,"lowerIsBetter":false,"registryRank":86,"selected":true,"percentile":15.79,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-30b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":28865728512},{"benchmarkId":"Idavidrein/gpqa","modelId":"ibm-granite/granite-4.1-8b","value":41.96,"lowerIsBetter":false,"registryRank":87,"selected":true,"percentile":14.47,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-8b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":8791592960},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Instruct","value":40.9,"lowerIsBetter":false,"registryRank":88,"selected":true,"percentile":13.16,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"post-training eval (SFT + RLVR), no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Thinking-SFT","value":39.9,"lowerIsBetter":false,"registryRank":89,"selected":true,"percentile":11.84,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"post-training eval (SFT only), with thinking, no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Instruct-SFT","value":38.9,"lowerIsBetter":false,"registryRank":90,"selected":true,"percentile":10.53,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"post-training eval (SFT only), no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"CohereLabs/c4ai-command-r-plus-08-2024","value":34.3434343434,"lowerIsBetter":false,"registryRank":91,"selected":true,"percentile":9.21,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/af/03/af03cc06-a493-48b7-a049-61d9b690c8f3.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":103810674688},{"benchmarkId":"Idavidrein/gpqa","modelId":"ibm-granite/granite-4.1-3b","value":31.7,"lowerIsBetter":false,"registryRank":92,"selected":true,"percentile":7.89,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.1-3b","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/gpqa_diamond.yaml","parameters":3402836480},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Base-Pretrain","value":31.31,"lowerIsBetter":false,"registryRank":93,"selected":true,"percentile":5.92,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval, no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"JetBrains/Mellum2-12B-A2.5B-Base","value":31.31,"lowerIsBetter":false,"registryRank":94,"selected":true,"percentile":5.92,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"pre-training eval (pre-YaRN), no-tools","filename":".eval_results/mellum2.yaml","parameters":12149923072},{"benchmarkId":"Idavidrein/gpqa","modelId":"CohereLabs/c4ai-command-r-08-2024","value":26.7676767677,"lowerIsBetter":false,"registryRank":95,"selected":true,"percentile":3.29,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9a/17/9a17fcf2-ee22-4a4f-b992-0d07290a56fc.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":32296476672},{"benchmarkId":"Idavidrein/gpqa","modelId":"CohereLabs/c4ai-command-r7b-12-2024","value":26.7676767677,"lowerIsBetter":false,"registryRank":96,"selected":true,"percentile":3.29,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/69/1d/691d4ef0-94b0-47e2-a7c9-b85f1bdc625b.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":8028033024},{"benchmarkId":"Idavidrein/gpqa","modelId":"Muse-research/Muse-2-350M","value":25.79,"lowerIsBetter":false,"registryRank":97,"selected":true,"percentile":1.32,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Muse-research/Muse-2-350M","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/gpqa.yaml","parameters":354980864},{"benchmarkId":"Idavidrein/gpqa","modelId":"meta-llama/Llama-3.2-1B-Instruct","value":18.6868686869,"lowerIsBetter":false,"registryRank":98,"selected":true,"percentile":0,"sourceName":"EvalEval","sourceUrl":"https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/aa/ad/aaad0db3-7c5b-4834-a1a2-d96624bdd003.json","sourceClass":"independent","sourceConfidence":0.76,"verified":false,"notes":"GPQA Diamond","filename":".eval_results/gpqa-diamond.yaml","parameters":1235814400},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepreinforce-ai/Ornith-1.0-397B","value":82.4,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Ornith-1.0-397B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-397B.yaml","parameters":396802360816},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":80.6,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":97.92,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":861608274846},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MiniMaxAI/MiniMax-M3","value":80.5,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":93.75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Each test was run 4 times and the average was taken.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":80.5,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":93.75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Each test was run 4 times and the average was taken.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":80.5,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":93.75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Evaluated on internal infrastructure using Claude Code as the scaffolding. Each test was run 4 times and the average was taken.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"moonshotai/Kimi-K2.6","value":80.2,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":89.58,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":1058589420528},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":79,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":87.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":158069433298},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":78.9,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":85.42,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":1023244718976},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"tencent/Hy3","value":78,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":83.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":298786155776},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"zai-org/GLM-5","value":77.8,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":81.25,"sourceName":"Model card","sourceUrl":"https://huggingface.co/zai-org/GLM-5/","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Z.ai reported number","filename":".eval_results/swe_bench_verified.yaml","parameters":753864139008},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"mistralai/Mistral-Medium-3.5-128B","value":77.6,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":79.17,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":127704211408},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.6-27B","value":77.2,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":77.08,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":27781427952},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.5-397B-A17B","value":76.4,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":403397928944},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MiniMaxAI/MiniMax-M2.5","value":75.8,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":72.92,"sourceName":"SWE-Bench official evaluation","sourceUrl":"https://www.swebench.com/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"high reasoning","filename":".eval_results/swe_bench_verified.yaml","parameters":228703644928},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepreinforce-ai/Ornith-1.0-35B","value":75.6,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":70.83,"sourceName":"Ornith-1.0-35B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-35B.yaml","parameters":664944},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Multilingual-Multimodal-NLP/IndustrialCoder","value":74.8,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":68.75,"sourceName":"IndustrialCoder technical report","sourceUrl":"https://huggingface.co/papers/2603.16790","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":31992714240},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"poolside/Laguna-M.1","value":74.6,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":66.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-M.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":225795725568},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"stepfun-ai/Step-3.5-Flash","value":74.4,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":63.54,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":199384301376},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"tencent/Hy3-preview","value":74.4,"lowerIsBetter":false,"registryRank":19,"selected":true,"percentile":63.54,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3-preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":298786155776},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MiniMaxAI/MiniMax-M2.1","value":74,"lowerIsBetter":false,"registryRank":20,"selected":true,"percentile":59.38,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":228703644928},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"inclusionAI/Ring-2.6-1T","value":74,"lowerIsBetter":false,"registryRank":21,"selected":true,"percentile":59.38,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ring-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"high reasoning effort","filename":".eval_results/swe_bench_verified.yaml","parameters":1025657871744},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"zai-org/GLM-4.7","value":73.8,"lowerIsBetter":false,"registryRank":22,"selected":true,"percentile":56.25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":358337791296},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.6-35B-A3B","value":73.4,"lowerIsBetter":false,"registryRank":23,"selected":true,"percentile":54.17,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":35951822704},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"zai-org/GLM-5","value":72.8,"lowerIsBetter":false,"registryRank":24,"selected":false,"percentile":null,"sourceName":"SWE-Bench official evaluation","sourceUrl":"https://www.swebench.com/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"high reasoning, official","filename":".eval_results/swe_bench_verified.yaml","parameters":753864139008},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.5-27B","value":72.4,"lowerIsBetter":false,"registryRank":25,"selected":true,"percentile":52.08,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":27781427952},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"inclusionAI/Ling-2.6-1T","value":72.2,"lowerIsBetter":false,"registryRank":26,"selected":true,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ling-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":1025657871744},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3.5-122B-A10B","value":72,"lowerIsBetter":false,"registryRank":27,"selected":true,"percentile":47.92,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":125086497008},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","value":71.9,"lowerIsBetter":false,"registryRank":28,"selected":true,"percentile":45.83,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":560524578816},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"moonshotai/Kimi-K2-Thinking","value":71.3,"lowerIsBetter":false,"registryRank":29,"selected":true,"percentile":43.75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":1058118284416},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"poolside/Laguna-XS-2.1","value":70.9,"lowerIsBetter":false,"registryRank":30,"selected":true,"percentile":41.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":33442617088},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"moonshotai/Kimi-K2.5","value":70.8,"lowerIsBetter":false,"registryRank":31,"selected":true,"percentile":39.58,"sourceName":"SWE-Bench official evaluation","sourceUrl":"https://www.swebench.com/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"high reasoning","filename":".eval_results/swe_bench_verified.yaml","parameters":1058589420528},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"Qwen/Qwen3-Coder-Next","value":70.6,"lowerIsBetter":false,"registryRank":32,"selected":true,"percentile":37.5,"sourceName":"Qwen3-Coder-Next technical report","sourceUrl":"https://huggingface.co/papers/2603.00729","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"SWE-Agent as harness","filename":".eval_results/swe_bench_verified.yaml","parameters":79674391296},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"poolside/Laguna-XS.2","value":69.9,"lowerIsBetter":false,"registryRank":33,"selected":true,"percentile":35.42,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":33442617088},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","value":69.7,"lowerIsBetter":false,"registryRank":34,"selected":true,"percentile":33.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":335038821080},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MiniMaxAI/MiniMax-M2","value":69.4,"lowerIsBetter":false,"registryRank":35,"selected":true,"percentile":30.21,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":228703644928},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"deepreinforce-ai/Ornith-1.0-9B","value":69.4,"lowerIsBetter":false,"registryRank":36,"selected":true,"percentile":30.21,"sourceName":"Ornith-1.0-9B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-9B.yaml","parameters":1469680},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"MuVeraAI/Laguna-XS.2","value":68.2,"lowerIsBetter":false,"registryRank":37,"selected":true,"percentile":27.08,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":33442617088},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"CohereLabs/North-Mini-Code-1.0","value":67.6,"lowerIsBetter":false,"registryRank":38,"selected":true,"percentile":25,"sourceName":"North Mini Code Model Page","sourceUrl":"https://huggingface.co/CohereLabs/North-Mini-Code-1.0","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/swe-bench-verified.yaml","parameters":30484303872},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"internlm/Intern-S2-Preview","value":64,"lowerIsBetter":false,"registryRank":39,"selected":true,"percentile":22.92,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":36098254656},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openpangu/openPangu-2.0-Flash","value":63.1,"lowerIsBetter":false,"registryRank":40,"selected":true,"percentile":20.83,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@3, Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openai/gpt-oss-120b","value":62.4,"lowerIsBetter":false,"registryRank":41,"selected":true,"percentile":18.75,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high","filename":".eval_results/swe_bench_verified_high.yaml","parameters":120412337472},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"inclusionAI/Ling-2.6-flash","value":61.2,"lowerIsBetter":false,"registryRank":42,"selected":true,"percentile":16.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ling-2.6-flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/swe-bench_verified.yaml","parameters":107494409216},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openai/gpt-oss-20b","value":60.7,"lowerIsBetter":false,"registryRank":43,"selected":true,"percentile":14.58,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: high","filename":".eval_results/swe_bench_verified_high.yaml","parameters":21511953984},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":60.47,"lowerIsBetter":false,"registryRank":44,"selected":true,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":123611012096},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":60.47,"lowerIsBetter":false,"registryRank":45,"selected":true,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":123611012096},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":60.47,"lowerIsBetter":false,"registryRank":46,"selected":true,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":60.47,"lowerIsBetter":false,"registryRank":47,"selected":true,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":60.47,"lowerIsBetter":false,"registryRank":48,"selected":true,"percentile":8.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenHands harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"zai-org/GLM-4.7-Flash","value":59.2,"lowerIsBetter":false,"registryRank":49,"selected":true,"percentile":2.08,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/swe_bench_verified.yaml","parameters":31221488576},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":59.2,"lowerIsBetter":false,"registryRank":50,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenCode harness","filename":".eval_results/swe_bench_verified.yaml","parameters":123611012096},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":59.2,"lowerIsBetter":false,"registryRank":51,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenCode harness","filename":".eval_results/swe_bench_verified.yaml","parameters":123611012096},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":59.2,"lowerIsBetter":false,"registryRank":52,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenCode harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":59.2,"lowerIsBetter":false,"registryRank":53,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenCode harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":59.2,"lowerIsBetter":false,"registryRank":54,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"OpenCode harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openpangu/openPangu-2.0-Flash","value":57.6,"lowerIsBetter":false,"registryRank":55,"selected":false,"percentile":null,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@3, Non-Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"facebook/cwm","value":53.9,"lowerIsBetter":false,"registryRank":56,"selected":true,"percentile":0,"sourceName":"CWM technical report","sourceUrl":"https://huggingface.co/papers/2510.02387","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"averaged over 4 runs","filename":".eval_results/swe_bench_verified.yaml","parameters":32581097472},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":53.73,"lowerIsBetter":false,"registryRank":57,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Codex harness","filename":".eval_results/swe_bench_verified.yaml","parameters":123611012096},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":53.73,"lowerIsBetter":false,"registryRank":58,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Codex harness","filename":".eval_results/swe_bench_verified.yaml","parameters":123611012096},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":53.73,"lowerIsBetter":false,"registryRank":59,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Codex harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":53.73,"lowerIsBetter":false,"registryRank":60,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Codex harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":53.73,"lowerIsBetter":false,"registryRank":61,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Codex harness","filename":".eval_results/swe_bench_verified.yaml","parameters":120668707840},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openai/gpt-oss-20b","value":53.2,"lowerIsBetter":false,"registryRank":62,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium","filename":".eval_results/swe_bench_verified_medium.yaml","parameters":21511953984},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openai/gpt-oss-120b","value":52.6,"lowerIsBetter":false,"registryRank":63,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: medium","filename":".eval_results/swe_bench_verified_medium.yaml","parameters":120412337472},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openai/gpt-oss-120b","value":47.9,"lowerIsBetter":false,"registryRank":64,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low","filename":".eval_results/swe_bench_verified_low.yaml","parameters":120412337472},{"benchmarkId":"SWE-bench/SWE-bench_Verified","modelId":"openai/gpt-oss-20b","value":37.4,"lowerIsBetter":false,"registryRank":65,"selected":false,"percentile":null,"sourceName":"GPT-OSS Model Card","sourceUrl":"https://arxiv.org/abs/2508.10925","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Reasoning: low","filename":".eval_results/swe_bench_verified_low.yaml","parameters":21511953984},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"zai-org/GLM-5.2","value":20.709230769230768,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":753329940480},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"zai-org/GLM-5.1","value":18.19,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":83.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 40/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":753864139008},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"moonshotai/Kimi-K2.6","value":18,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":66.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 38/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":1058589420528},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":17.12,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":861608274846},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"XiaomiMiMo/MiMo-V2.5","value":16.91,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":33.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":310775040000},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"Qwen/Qwen3.5-397B-A17B","value":14.23,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":16.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 40/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":403397928944},{"benchmarkId":"InternScience/ResearchClawBench","modelId":"moonshotai/Kimi-K2.5","value":13.96,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.","filename":".eval_results/researchclawbench.yaml","parameters":1058589420528},{"benchmarkId":"llamaindex/ParseBench","modelId":"KDLAI/KDL-Frontier-Parser-nano","value":76.36,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: kdl_frontier_nano (standalone provider, run-llama/ParseBench PR #49). Full-set single-pass run (2,553 test cases, 0 failures): vLLM serving of the public weights + the deterministic provider pipeline. Layout dimension = layout_element_rule_pass_rate (official leade","filename":".eval_results/parsebench.yaml","parameters":1156026624},{"benchmarkId":"llamaindex/ParseBench","modelId":"infly/Infinity-Parser2-Pro","value":74.3,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":94.12,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: infinity_parser2_pro","filename":".eval_results/parsebench.yaml","parameters":35107181936},{"benchmarkId":"llamaindex/ParseBench","modelId":"infly/Infinity-Parser2-Flash","value":73.25,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":88.24,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: infinity_parser2_flash","filename":".eval_results/parsebench.yaml","parameters":2213241664},{"benchmarkId":"llamaindex/ParseBench","modelId":"opendatalab/MinerU2.5-Pro-2605-1.2B","value":72.78,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":82.35,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: mineru2605pro_vllm","filename":".eval_results/parsebench.yaml","parameters":1156026624},{"benchmarkId":"llamaindex/ParseBench","modelId":"datalab-to/chandra-ocr-2","value":70.1,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":76.47,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: chandra2_vllm","filename":".eval_results/parsebench.yaml","parameters":5295564288},{"benchmarkId":"llamaindex/ParseBench","modelId":"datalab-to/surya-ocr-2","value":64.83,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":70.59,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: surya2_sdk","filename":".eval_results/parsebench.yaml","parameters":686154304},{"benchmarkId":"llamaindex/ParseBench","modelId":"rednote-hilab/dots.mocr","value":55.8,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":64.71,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: dots_ocr_1_5_parse","filename":".eval_results/parsebench.yaml","parameters":3039179264},{"benchmarkId":"llamaindex/ParseBench","modelId":"tiiuae/Falcon-OCR","value":53.08,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":58.82,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: falconocr_pipeline","filename":".eval_results/parsebench.yaml","parameters":269944416},{"benchmarkId":"llamaindex/ParseBench","modelId":"docling-project/docling-models","value":50.6,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":52.94,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: docling_parse","filename":".eval_results/parsebench.yaml","parameters":null},{"benchmarkId":"llamaindex/ParseBench","modelId":"lightonai/LightOnOCR-2-1B","value":48,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":47.06,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: lightonocr_vllm","filename":".eval_results/parsebench.yaml","parameters":1005647872},{"benchmarkId":"llamaindex/ParseBench","modelId":"Qwen/Qwen3-VL-8B-Instruct","value":46.8,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":41.18,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: qwen3vl_layout","filename":".eval_results/parsebench.yaml","parameters":8767123696},{"benchmarkId":"llamaindex/ParseBench","modelId":"baidu/Qianfan-OCR","value":46.2,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":35.29,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: qfocr_vllm_thinking","filename":".eval_results/parsebench.yaml","parameters":4741408256},{"benchmarkId":"llamaindex/ParseBench","modelId":"baidu/Unlimited-OCR","value":46.17,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":29.41,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: unlimitedocr","filename":".eval_results/parsebench.yaml","parameters":3336106240},{"benchmarkId":"llamaindex/ParseBench","modelId":"opendatalab/MinerU2.5-2509-1.2B","value":45.9,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":23.53,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: mineru25_vllm","filename":".eval_results/parsebench.yaml","parameters":1156026624},{"benchmarkId":"llamaindex/ParseBench","modelId":"Qwen/Qwen3.6-35B-A3B","value":44.1,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":17.65,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: qwen3_6_35b_a3b_fp8_vllm_parse_layout","filename":".eval_results/parsebench.yaml","parameters":35951822704},{"benchmarkId":"llamaindex/ParseBench","modelId":"deepseek-ai/DeepSeek-OCR-2","value":41.2,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":11.76,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: deepseekocr2_vllm","filename":".eval_results/parsebench.yaml","parameters":3389119360},{"benchmarkId":"llamaindex/ParseBench","modelId":"ibm-granite/granite-vision-4.1-4b","value":39.45,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":5.88,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: granite_vision_4_1_4b","filename":".eval_results/parsebench.yaml","parameters":3997206464},{"benchmarkId":"llamaindex/ParseBench","modelId":"zai-org/GLM-OCR","value":29.6,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":0,"sourceName":"ParseBench","sourceUrl":"https://huggingface.co/datasets/llamaindex/ParseBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pipeline name: glmocr_pipeline","filename":".eval_results/parsebench.yaml","parameters":1325258240},{"benchmarkId":"MathArena/aime_2026","modelId":"stepfun-ai/Step-3.5-Flash","value":96.67,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":199384301376},{"benchmarkId":"MathArena/aime_2026","modelId":"moonshotai/Kimi-K2.6","value":96.4,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":93.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":1058589420528},{"benchmarkId":"MathArena/aime_2026","modelId":"moonshotai/Kimi-K2.5","value":95.83,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":80,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":1058589420528},{"benchmarkId":"MathArena/aime_2026","modelId":"zai-org/GLM-5","value":95.83,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":80,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":753864139008},{"benchmarkId":"MathArena/aime_2026","modelId":"inclusionAI/Ring-2.6-1T","value":95.83,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":80,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ring-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"xhigh reasoning effort, Mean@64","filename":".eval_results/aime_2026.yaml","parameters":1025657871744},{"benchmarkId":"MathArena/aime_2026","modelId":"zai-org/GLM-5.1","value":95.3,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":66.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":753864139008},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3.6-27B","value":94.1,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":60,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":27781427952},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3.5-397B-A17B","value":93.33,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":53.33,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":403397928944},{"benchmarkId":"MathArena/aime_2026","modelId":"openpangu/openPangu-2.0-Flash","value":93.3,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":46.67,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3.6-35B-A3B","value":92.7,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":40,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":35951822704},{"benchmarkId":"MathArena/aime_2026","modelId":"LGAI-EXAONE/EXAONE-4.5-33B","value":92.6,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":33.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":34350097664},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3.5-27B","value":90.83,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":26.67,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":27781427952},{"benchmarkId":"MathArena/aime_2026","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":90,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":20,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":123611012096},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3-30B-A3B-Thinking-2507","value":87.5,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":13.33,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":30532122624},{"benchmarkId":"MathArena/aime_2026","modelId":"openpangu/openPangu-2.0-Flash","value":86.5,"lowerIsBetter":false,"registryRank":15,"selected":false,"percentile":null,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Non-Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"MathArena/aime_2026","modelId":"Qwen/Qwen3-4B-Thinking-2507","value":82.5,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":6.67,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=aime--aime_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--aime_2026.yaml","parameters":4022468096},{"benchmarkId":"MathArena/aime_2026","modelId":"inclusionAI/Ling-2.6-flash","value":73.85,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ling-2.6-flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/aime_2026.yaml","parameters":107494409216},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-5.1","value":69,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"agent: Terminus 2(Claude Code)","filename":".eval_results/terminal_bench_2_claudecode.yaml","parameters":753864139008},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":68.4,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":97.22,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":1023244718976},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":67.9,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":94.44,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":861608274846},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"moonshotai/Kimi-K2.6","value":66.7,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":91.67,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal_bench_2.yaml","parameters":1058589420528},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"XiaomiMiMo/MiMo-V2.5","value":65.8,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":88.89,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":310775040000},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-5.1","value":63.5,"lowerIsBetter":false,"registryRank":6,"selected":false,"percentile":null,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal_bench_2.yaml","parameters":753864139008},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.6-27B","value":59.3,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":86.11,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Harbor/Terminus-2 harness; 3h timeout, 32 CPU/48 GB RAM; temp=1.0, top_p=0.95, top_k=20, max_tokens=80K, 256K ctx; avg of 5 runs.","filename":".eval_results/terminal-bench-2.0.yaml","parameters":27781427952},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"MiniMaxAI/MiniMax-M2.7","value":57,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":83.33,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":228703644928},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":56.9,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":80.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":158069433298},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"tencent/Hy3-preview","value":54.4,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":77.78,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3-preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal_bench.yaml","parameters":298786155776},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.5-397B-A17B","value":52.5,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminalbench_2.yaml","parameters":403397928944},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-5","value":52.4,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":72.22,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":753864139008},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.6-35B-A3B","value":51.5,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":69.44,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Harbor/Terminus-2 harness; 3h timeout, 32 CPU/48 GB RAM; temp=1.0, top_p=0.95, top_k=20, max_tokens=80K, 256K ctx; avg of 5 runs.","filename":".eval_results/terminal-bench-2.0.yaml","parameters":35951822704},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"stepfun-ai/Step-3.5-Flash","value":51,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":66.67,"sourceName":"Step 3.5 Flash Paper","sourceUrl":"https://arxiv.org/abs/2602.10604","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/terminal_bench_2.yaml","parameters":199384301376},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.5-122B-A10B","value":49.4,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":63.89,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2_2.yaml","parameters":125086497008},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"poolside/Laguna-M.1","value":45.8,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":61.11,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-M.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":225795725568},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"moonshotai/Kimi-K2.5","value":43.2,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":58.33,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":1058589420528},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3.5-27B","value":41.6,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":55.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0_4.yaml","parameters":27781427952},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"poolside/Laguna-XS-2.1","value":37.5,"lowerIsBetter":false,"registryRank":19,"selected":true,"percentile":52.78,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":33442617088},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3-Coder-Next","value":36.2,"lowerIsBetter":false,"registryRank":20,"selected":true,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-Next","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":79674391296},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"CohereLabs/North-Mini-Code-1.0","value":36,"lowerIsBetter":false,"registryRank":21,"selected":true,"percentile":47.22,"sourceName":"North Mini Code Model Page","sourceUrl":"https://huggingface.co/CohereLabs/North-Mini-Code-1.0","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-v2.yaml","parameters":30484303872},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"moonshotai/Kimi-K2-Thinking","value":35.7,"lowerIsBetter":false,"registryRank":22,"selected":true,"percentile":43.06,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":1058118284416},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"poolside/Laguna-XS.2","value":35.7,"lowerIsBetter":false,"registryRank":23,"selected":true,"percentile":43.06,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":33442617088},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-4.7","value":33.4,"lowerIsBetter":false,"registryRank":24,"selected":true,"percentile":38.89,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":358337791296},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":31,"lowerIsBetter":false,"registryRank":25,"selected":true,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":123611012096},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":31,"lowerIsBetter":false,"registryRank":26,"selected":true,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":123611012096},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm","value":31,"lowerIsBetter":false,"registryRank":27,"selected":true,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":120668707840},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm","value":31,"lowerIsBetter":false,"registryRank":28,"selected":true,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":120668707840},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm","value":31,"lowerIsBetter":false,"registryRank":29,"selected":true,"percentile":30.56,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench_2.0.yaml","parameters":120668707840},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"MuVeraAI/Laguna-XS.2","value":30.1,"lowerIsBetter":false,"registryRank":30,"selected":true,"percentile":22.22,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/poolside/Laguna-XS.2","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/terminal-bench-2.0.yaml","parameters":33442617088},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"MiniMaxAI/MiniMax-M2","value":30,"lowerIsBetter":false,"registryRank":31,"selected":true,"percentile":19.44,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":228703644928},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"MiniMaxAI/MiniMax-M2.1","value":29.2,"lowerIsBetter":false,"registryRank":32,"selected":true,"percentile":16.67,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":228703644928},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"moonshotai/Kimi-K2-Instruct","value":27.8,"lowerIsBetter":false,"registryRank":33,"selected":true,"percentile":13.89,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":1026470731056},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"nvidia/Nemotron-Terminal-32B","value":27.4,"lowerIsBetter":false,"registryRank":34,"selected":true,"percentile":11.11,"sourceName":"Nemotron-Terminal-32B technical report","sourceUrl":"https://arxiv.org/pdf/2602.21193","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":32762123264},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"zai-org/GLM-4.6","value":24.5,"lowerIsBetter":false,"registryRank":35,"selected":true,"percentile":8.33,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":356785898816},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct","value":23.9,"lowerIsBetter":false,"registryRank":36,"selected":true,"percentile":5.56,"sourceName":"Terminal-Bench Leaderboard","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench.yaml","parameters":480154875392},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"nvidia/Nemotron-Terminal-14B","value":20.2,"lowerIsBetter":false,"registryRank":37,"selected":true,"percentile":2.78,"sourceName":"Nemotron-Terminal-14B technical report","sourceUrl":"https://arxiv.org/pdf/2602.21193","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":14768307200},{"benchmarkId":"harborframework/terminal-bench-2.0","modelId":"nvidia/Nemotron-Terminal-8B","value":13,"lowerIsBetter":false,"registryRank":38,"selected":true,"percentile":0,"sourceName":"Nemotron-Terminal-8B technical report","sourceUrl":"https://arxiv.org/pdf/2602.21193","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"agent: Terminus 2","filename":".eval_results/terminal_bench_2.yaml","parameters":8190735360},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"rednote-hilab/dots.mocr","value":80.5,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":3039179264},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"datalab-to/chandra-ocr-2","value":79.7,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":90.91,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":5295564288},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"moonshotai/Kimi-K2.5","value":77.5,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":81.82,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1058589420528},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"rednote-hilab/dots.ocr","value":76.5,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":72.73,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":3039179264},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"opendatalab/MinerU2.5-Pro-2605-1.2B","value":71,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":63.64,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1156026624},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"Qwen/Qwen3-VL-8B-Instruct","value":68.3,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":50,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":8767123696},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"tencent/HunyuanOCR","value":68.3,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":50,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1119925744},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"zai-org/GLM-OCR","value":67.3,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":36.36,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1325258240},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"lightonai/LightOnOCR-2-1B","value":63.9,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":27.27,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1005647872},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"tiiuae/Falcon-OCR","value":56.3,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":18.18,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":269944416},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"deepseek-ai/DeepSeek-OCR","value":51.8,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":9.09,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":3336106240},{"benchmarkId":"Delores-Lin/MDPBench","modelId":"opendatalab/MinerU2.5-2509-1.2B","value":46.3,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":0,"sourceName":"MDPBench leaderboard","sourceUrl":"https://huggingface.co/datasets/Delores-Lin/MDPBench","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/mdpbench.yaml","parameters":1156026624},{"benchmarkId":"actava/chi-bench","modelId":"zai-org/GLM-5.1","value":18.7,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"CHI-Bench","sourceUrl":"https://arxiv.org/abs/2605.16679","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"Harness: OpenAI Agents SDK; Protocol: 75 tasks x 3 trials; Metric: pass@1 (%)","filename":".eval_results/chi-bench.yaml","parameters":753864139008},{"benchmarkId":"actava/chi-bench","modelId":"moonshotai/Kimi-K2.6","value":15.6,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":50,"sourceName":"CHI-Bench","sourceUrl":"https://arxiv.org/abs/2605.16679","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"Harness: Hermes; Protocol: 75 tasks x 3 trials; Metric: pass@1 (%)","filename":".eval_results/chi-bench.yaml","parameters":1058589420528},{"benchmarkId":"actava/chi-bench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":14.2,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":0,"sourceName":"CHI-Bench","sourceUrl":"https://arxiv.org/abs/2605.16679","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"Harness: OpenAI Agents SDK; Protocol: 75 tasks x 3 trials; Metric: pass@1 (%)","filename":".eval_results/chi-bench.yaml","parameters":861608274846},{"benchmarkId":"meituan-longcat/WBench","modelId":"robbyant/lingbot-world-fast","value":78.8,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"tencent/HY-WorldPlay","value":78.4,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":85.71,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"tencent/HunyuanVideo-1.5","value":78.2,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":71.43,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"Lightricks/LTX-2.3","value":74.4,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":57.14,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"inspatio/world","value":74.3,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":42.86,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"meituan-longcat/LongCat-Video","value":73.7,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":28.57,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"ACERobotics/kairos-sensenova-robot-4B-480P","value":70.7,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":14.29,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"meituan-longcat/WBench","modelId":"tencent/Hunyuan-GameCraft-1.0","value":68.5,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":0,"sourceName":"WBench Leaderboard","sourceUrl":"https://meituan-longcat.github.io/WBench/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/wbench.yaml","parameters":null},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"bharatgenai/Shrutam-HindiASR-1.0","value":18.1,"lowerIsBetter":true,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":null},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"mistralai/Voxtral-Mini-3B-2507","value":21.3,"lowerIsBetter":true,"registryRank":2,"selected":true,"percentile":83.33,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":4676271104},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"shunyalabs/pingala-v1-universal","value":22.1,"lowerIsBetter":true,"registryRank":3,"selected":true,"percentile":66.67,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":808878080},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"SPRINGLab/data2vec_aqc","value":23.7,"lowerIsBetter":true,"registryRank":4,"selected":true,"percentile":50,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":null},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"google/gemma-4-12B","value":24.6,"lowerIsBetter":true,"registryRank":5,"selected":true,"percentile":33.33,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":11959730224},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"facebook/omniASR-LLM-1B","value":25.6,"lowerIsBetter":true,"registryRank":6,"selected":true,"percentile":16.67,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":null},{"benchmarkId":"ARTPARK-IISc/Vaani-Benchmark-V1.0","modelId":"openai/whisper-large-v3","value":26.8,"lowerIsBetter":true,"registryRank":7,"selected":true,"percentile":0,"sourceName":"Unspecified source","sourceUrl":null,"sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/ARTPARK-IISc-Vaani-Benchmark-V1-0.yaml","parameters":1543490560},{"benchmarkId":"mteb/arguana","modelId":"google/embeddinggemma-300m","value":71.535,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Obtained using MTEB v1.34.7","sourceUrl":"https://github.com/embeddings-benchmark/mteb/","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"Obtained using MTEB v1.34.7","filename":".eval_results/ArguAna.yaml","parameters":302863104},{"benchmarkId":"mteb/arguana","modelId":"mteb/baseline-bm25s","value":49.276,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":50,"sourceName":"Obtained using MTEB v1.12.22","sourceUrl":"https://github.com/embeddings-benchmark/mteb/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Obtained using MTEB v1.12.22","filename":".eval_results/ArguAna.yaml","parameters":null},{"benchmarkId":"mteb/arguana","modelId":"Surpem/Supertron-embedding-190M","value":42.019,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":0,"sourceName":"Supetron Modal benchmark run","sourceUrl":"https://huggingface.co/datasets/mteb/arguana","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Official mteb/arguana retrieval task. Metric: nDCG@10.","filename":".eval_results/eval_arguana.yaml","parameters":130450176},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"AutoArk-AI/ARK-ASR-3B","value":4.76,"lowerIsBetter":true,"registryRank":1,"selected":true,"percentile":100,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":4063438848},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"OpenMOSS-Team/MOSS-Transcribe-preview-2B","value":4.87,"lowerIsBetter":true,"registryRank":2,"selected":true,"percentile":98.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2418833792},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"CohereLabs/cohere-transcribe-03-2026","value":5.42,"lowerIsBetter":true,"registryRank":3,"selected":true,"percentile":96.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2065804048},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"AutoArk-AI/ARK-ASR-0.6B","value":5.53,"lowerIsBetter":true,"registryRank":4,"selected":true,"percentile":95,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1299463168},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M","value":5.64,"lowerIsBetter":true,"registryRank":5,"selected":true,"percentile":93.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"Qwen/Qwen3-ASR-1.7B","value":5.76,"lowerIsBetter":true,"registryRank":6,"selected":true,"percentile":91.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2349217408},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"microsoft/Phi-4-multimodal-instruct","value":6.02,"lowerIsBetter":true,"registryRank":7,"selected":true,"percentile":90,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":5574460384},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-tdt-0.6b-v2","value":6.05,"lowerIsBetter":true,"registryRank":8,"selected":true,"percentile":88.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-tdt-0.6b-v3","value":6.32,"lowerIsBetter":true,"registryRank":9,"selected":true,"percentile":86.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":627057286},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/canary-1b-flash","value":6.35,"lowerIsBetter":true,"registryRank":10,"selected":true,"percentile":85,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":811049984},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"kyutai/stt-2.6b-en","value":6.4,"lowerIsBetter":true,"registryRank":11,"selected":true,"percentile":83.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2617118720},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"Qwen/Qwen3-ASR-0.6B","value":6.42,"lowerIsBetter":true,"registryRank":12,"selected":true,"percentile":81.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":938008576},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/canary-1b","value":6.50375,"lowerIsBetter":true,"registryRank":13,"selected":true,"percentile":80,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-streaming-medium","value":6.66,"lowerIsBetter":true,"registryRank":14,"selected":true,"percentile":78.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":265898112},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"soundsgoodai/Zipformer-transducer-XL-290M","value":6.71,"lowerIsBetter":true,"registryRank":15,"selected":true,"percentile":76.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-tdt-1.1b","value":7.015,"lowerIsBetter":true,"registryRank":16,"selected":true,"percentile":75,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"zai-org/GLM-ASR-Nano-2512","value":7.03,"lowerIsBetter":true,"registryRank":17,"selected":true,"percentile":72.5,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":2257843200},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"AutoArk-AI/Audio8-ASR-0.1B","value":7.03,"lowerIsBetter":true,"registryRank":18,"selected":true,"percentile":72.5,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/datasets/hf-audio/open-asr-leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":323990528},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"mistralai/Voxtral-Mini-3B-2507","value":7.05,"lowerIsBetter":true,"registryRank":19,"selected":true,"percentile":70,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":4676271104},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/canary-180m-flash","value":7.12,"lowerIsBetter":true,"registryRank":20,"selected":true,"percentile":68.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-rnnt-1.1b","value":7.12375,"lowerIsBetter":true,"registryRank":21,"selected":true,"percentile":66.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1070518785},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/canary-1b-v2","value":7.15,"lowerIsBetter":true,"registryRank":22,"selected":true,"percentile":65,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"distil-whisper/distil-large-v3.5","value":7.21,"lowerIsBetter":true,"registryRank":23,"selected":true,"percentile":63.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":756405760},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-ctc-1.1b","value":7.39875,"lowerIsBetter":true,"registryRank":24,"selected":true,"percentile":61.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1062626305},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"espnet/owsm_ctc_v4_1B","value":7.42,"lowerIsBetter":true,"registryRank":25,"selected":true,"percentile":60,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-large-v3","value":7.44,"lowerIsBetter":true,"registryRank":26,"selected":true,"percentile":58.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1543490560},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-tdt_ctc-110m","value":7.49,"lowerIsBetter":true,"registryRank":27,"selected":true,"percentile":56.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-rnnt-0.6b","value":7.495,"lowerIsBetter":true,"registryRank":28,"selected":true,"percentile":55,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":616741377},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/parakeet-ctc-0.6b","value":7.69,"lowerIsBetter":true,"registryRank":29,"selected":true,"percentile":53.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":608848897},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"microsoft/VibeVoice-ASR-HF","value":7.77,"lowerIsBetter":true,"registryRank":30,"selected":true,"percentile":51.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":8330325888},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-large-v2","value":7.835,"lowerIsBetter":true,"registryRank":31,"selected":true,"percentile":50,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1543304960},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-streaming-small","value":7.84,"lowerIsBetter":true,"registryRank":32,"selected":true,"percentile":48.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":140135224},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-large","value":7.9425,"lowerIsBetter":true,"registryRank":33,"selected":true,"percentile":46.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":1543304960},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-medium.en","value":8.09,"lowerIsBetter":true,"registryRank":34,"selected":true,"percentile":45,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":763856896},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"espnet/owsm_ctc_v3.1_1B","value":8.12,"lowerIsBetter":true,"registryRank":35,"selected":true,"percentile":43.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/stt_en_conformer_ctc_large","value":8.31875,"lowerIsBetter":true,"registryRank":36,"selected":true,"percentile":41.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"speechbrain/asr-conformer-loquacious","value":8.48,"lowerIsBetter":true,"registryRank":37,"selected":true,"percentile":40,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-small.en","value":8.59,"lowerIsBetter":true,"registryRank":38,"selected":true,"percentile":38.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":241734144},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"abr-ai/niagara-38m-batch.en","value":8.91,"lowerIsBetter":true,"registryRank":39,"selected":true,"percentile":36.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/stt_en_fastconformer_ctc_large","value":8.965,"lowerIsBetter":true,"registryRank":40,"selected":true,"percentile":35,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/stt_en_fastconformer_transducer_large","value":9.0575,"lowerIsBetter":true,"registryRank":41,"selected":true,"percentile":33.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-base","value":9.99,"lowerIsBetter":true,"registryRank":42,"selected":true,"percentile":31.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":61513920},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-base.en","value":10.3175,"lowerIsBetter":true,"registryRank":43,"selected":true,"percentile":30,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":72593408},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"abr-ai/niagara-19m-batch.en","value":10.47,"lowerIsBetter":true,"registryRank":44,"selected":true,"percentile":28.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"nvidia/stt_en_conformer_ctc_small","value":11.15875,"lowerIsBetter":true,"registryRank":45,"selected":true,"percentile":26.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-streaming-tiny","value":12,"lowerIsBetter":true,"registryRank":46,"selected":true,"percentile":25,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":44054720},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"UsefulSensors/moonshine-tiny","value":12.65,"lowerIsBetter":true,"registryRank":47,"selected":true,"percentile":23.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":27092736},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"openai/whisper-tiny.en","value":12.80625,"lowerIsBetter":true,"registryRank":48,"selected":true,"percentile":21.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":37760256},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"speechbrain/asr-wav2vec2-librispeech","value":14.3475,"lowerIsBetter":true,"registryRank":49,"selected":true,"percentile":20,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-large-960h-lv60-self","value":21.2725,"lowerIsBetter":true,"registryRank":50,"selected":true,"percentile":18.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/mms-1b-all","value":22.53875,"lowerIsBetter":true,"registryRank":51,"selected":true,"percentile":16.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":964845850},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/hubert-xlarge-ls960-ft","value":22.5475,"lowerIsBetter":true,"registryRank":52,"selected":true,"percentile":15,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":962538400},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/hubert-large-ls960-ft","value":22.69375,"lowerIsBetter":true,"registryRank":53,"selected":true,"percentile":13.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-large-robust-ft-libri-960h","value":22.93125,"lowerIsBetter":true,"registryRank":54,"selected":true,"percentile":11.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":315471520},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/data2vec-audio-large-960h","value":23.21,"lowerIsBetter":true,"registryRank":55,"selected":true,"percentile":10,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-conformer-rope-large-960h-ft","value":23.28375,"lowerIsBetter":true,"registryRank":56,"selected":true,"percentile":8.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":593426112},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-conformer-rel-pos-large-960h-ft","value":23.29125,"lowerIsBetter":true,"registryRank":57,"selected":true,"percentile":6.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-large-960h","value":26.7725,"lowerIsBetter":true,"registryRank":58,"selected":true,"percentile":5,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/data2vec-audio-base-960h","value":28.3025,"lowerIsBetter":true,"registryRank":59,"selected":true,"percentile":3.33,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":null},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/wav2vec2-base-960h","value":29.4025,"lowerIsBetter":true,"registryRank":60,"selected":true,"percentile":1.67,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":94395552},{"benchmarkId":"hf-audio/open-asr-leaderboard","modelId":"facebook/mms-1b-fl102","value":39.79625,"lowerIsBetter":true,"registryRank":61,"selected":true,"percentile":0,"sourceName":"open-asr-leaderboard","sourceUrl":"https://huggingface.co/hf-audio","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/open_asr_leaderboard.yaml","parameters":964748494},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"moonshotai/Kimi-K2.6","value":79.4,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":1058589420528},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"moonshotai/Kimi-K2.5","value":78.5,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":87.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":1058589420528},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"internlm/Intern-S2-Preview","value":76.88,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":75,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":36098254656},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen3.6-27B","value":75.8,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":62.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":27781427952},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen3.6-35B-A3B","value":75.3,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":35951822704},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen3.5-27B","value":75,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":37.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":27781427952},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"ATH-MaaS/Ovis2.6-80B-A3B","value":66.3,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":25,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/AIDC-AI/Ovis2.6-80B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":80524245992},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen2.5-VL-7B-Instruct","value":34.3,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":12.5,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":8292166656},{"benchmarkId":"MMMU/MMMU_Pro","modelId":"Qwen/Qwen2.5-VL-3B-Instruct","value":32.7,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/mmmu_pro.yaml","parameters":3754622976},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen3.5-122B-A10B","value":70.4,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":125086497008},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen3.5-27B","value":70.3,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":95.24,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":27781427952},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-1.5-30B-A3B","value":69.6,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":90.48,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":31070754032},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-1.5-8B","value":68.4,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":85.71,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8767123696},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen3.5-397B-A17B","value":65.6,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":80.95,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":403397928944},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Salesforce/GTA1-32B","value":63.6,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":76.19,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":33452718336},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-Ground-72B","value":61.9,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":71.43,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":73410777344},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"ByteDance-Seed/UI-TARS-1.5-7B","value":61.6,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":66.67,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8292166656},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-1.5-2B","value":57.7,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":61.9,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":2438696960},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Salesforce/GTA1-7B","value":55.5,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":57.14,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8292166656},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen2.5-VL-72B-Instruct","value":53.3,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":52.38,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":73410777344},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"inclusionAI/UI-Venus-Ground-7B","value":50.8,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":47.62,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8292166656},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen2.5-VL-32B-Instruct","value":48,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":42.86,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":33452718336},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"KDEGroup/UI-AGILE-3B","value":45,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":38.1,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":3754622976},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"ByteDance-Seed/UI-TARS-72B-SFT","value":38.1,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":33.33,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":73405560320},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"ByteDance-Seed/UI-TARS-7B-SFT","value":35.7,"lowerIsBetter":false,"registryRank":16,"selected":true,"percentile":28.57,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8291375616},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"ByteDance-Seed/UI-TARS-2B-SFT","value":27.7,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":23.81,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":2442359296},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen2.5-VL-7B-Instruct","value":26.8,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":19.05,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":8292166656},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen2.5-VL-3B-Instruct","value":16.1,"lowerIsBetter":false,"registryRank":19,"selected":true,"percentile":14.29,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":3754622976},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"zai-org/CogAgent","value":7.7,"lowerIsBetter":false,"registryRank":20,"selected":true,"percentile":9.52,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":null},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"openbmb/MiniCPM-V-2","value":3,"lowerIsBetter":false,"registryRank":21,"selected":true,"percentile":4.76,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":3434965792},{"benchmarkId":"likaixin/ScreenSpot-Pro","modelId":"Qwen/Qwen-VL","value":0.1,"lowerIsBetter":false,"registryRank":22,"selected":true,"percentile":0,"sourceName":"ScreenSpot-Pro Leaderboard","sourceUrl":"https://gui-agent.github.io/grounding-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/screenspot_pro.yaml","parameters":null},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"deepseek-ai/DeepSeek-R1","value":52.41,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":684531386000},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"Qwen/Qwen3-235B-A22B-Thinking-2507","value":48.19,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":87.5,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":235093634560},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"openai/gpt-oss-120b","value":47.71,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":75,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":120412337472},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"deepseek-ai/DeepSeek-V3","value":46.57,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":62.5,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":684531386000},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"Qwen/Qwen3-32B","value":45.3,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":50,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":32762123264},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"Qwen/Qwen3-Next-80B-A3B-Thinking","value":43.31,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":37.5,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":81324862720},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"openai/gpt-oss-20b","value":40.78,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":25,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":21511953984},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"microsoft/phi-4","value":40.66,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":12.5,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":14659507200},{"benchmarkId":"LEXam-Benchmark/LEXam","modelId":"mistralai/Ministral-8B-Instruct-2410","value":26.27,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":0,"sourceName":"LEXam Leaderboard","sourceUrl":"https://lexam-benchmark.github.io/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/lexam.yaml","parameters":8019808256},{"benchmarkId":"mercor/APEX-v1-extended","modelId":"zai-org/GLM-4.7","value":51.7,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"APEX Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-v1-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: direct_prompting; reasoning_effort: high","filename":".eval_results/apex-v1-extended.yaml","parameters":358337791296},{"benchmarkId":"mercor/APEX-v1-extended","modelId":"zai-org/GLM-5","value":49,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":0,"sourceName":"APEX Leaderboard","sourceUrl":"https://www.mercor.com/apex/apex-v1-leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"harness: direct_prompting; reasoning_effort: thinking","filename":".eval_results/apex-v1-extended.yaml","parameters":753864139008},{"benchmarkId":"VLABench/vlabench_primitive_ft_lerobot_video","modelId":"lerobot/pi0_base","value":44.5,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"VLA Model Leaderboard","sourceUrl":"https://allenai.github.io/vla-evaluation-harness/leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Reproduction from ACoT-VLA paper (Table 3). A separate X-VLA paper reproduction reports 37.8.","filename":".eval_results/vlabench.yaml","parameters":3501372176},{"benchmarkId":"VLABench/vlabench_primitive_ft_lerobot_video","modelId":"lerobot/pi05_base","value":42,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":66.67,"sourceName":"VLA Model Leaderboard","sourceUrl":"https://allenai.github.io/vla-evaluation-harness/leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/vlabench.yaml","parameters":3616757520},{"benchmarkId":"VLABench/vlabench_primitive_ft_lerobot_video","modelId":"nvidia/GR00T-N1-2B","value":39.7,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":33.33,"sourceName":"VLA Model Leaderboard","sourceUrl":"https://allenai.github.io/vla-evaluation-harness/leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/vlabench.yaml","parameters":2190019826},{"benchmarkId":"VLABench/vlabench_primitive_ft_lerobot_video","modelId":"lerobot/pi0fast-base","value":34.1,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":0,"sourceName":"VLA Model Leaderboard","sourceUrl":"https://allenai.github.io/vla-evaluation-harness/leaderboard/","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/vlabench.yaml","parameters":2923335408},{"benchmarkId":"FutureMa/EvasionBench","modelId":"zai-org/GLM-4.7","value":82.91,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"EvasionBench Paper","sourceUrl":"https://arxiv.org/abs/2601.09142","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/evasionbench.yaml","parameters":358337791296},{"benchmarkId":"FutureMa/EvasionBench","modelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct","value":78.16,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":66.67,"sourceName":"EvasionBench Paper","sourceUrl":"https://arxiv.org/abs/2601.09142","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/evasionbench.yaml","parameters":480154875392},{"benchmarkId":"FutureMa/EvasionBench","modelId":"MiniMaxAI/MiniMax-M2.1","value":71.31,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":33.33,"sourceName":"EvasionBench Paper","sourceUrl":"https://arxiv.org/abs/2601.09142","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/evasionbench.yaml","parameters":228703644928},{"benchmarkId":"FutureMa/EvasionBench","modelId":"moonshotai/Kimi-K2-Instruct-0905","value":66.68,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":0,"sourceName":"EvasionBench Paper","sourceUrl":"https://arxiv.org/abs/2601.09142","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/evasionbench.yaml","parameters":1026470735448},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"moonshotai/Kimi-K2.6","value":92.7,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":1058589420528},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3.5-397B-A17B","value":87.88,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":92.31,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":403397928944},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"internlm/Intern-S2-Preview","value":87.31,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":84.62,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/internlm/Intern-S2-Preview","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":36098254656},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"moonshotai/Kimi-K2.5","value":87.12,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":76.92,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":1058589420528},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"stepfun-ai/Step-3.5-Flash","value":86.36,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":65.38,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":199384301376},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"zai-org/GLM-5","value":86.36,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":65.38,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":753864139008},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":84.85,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":53.85,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":123611012096},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3.6-27B","value":84.3,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":46.15,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":27781427952},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3.6-35B-A3B","value":83.6,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":38.46,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":35951822704},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"zai-org/GLM-5.1","value":82.6,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":30.77,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":753864139008},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3.5-27B","value":81.06,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":23.08,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":27781427952},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3-30B-A3B-Thinking-2507","value":78.79,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":15.38,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":30532122624},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"Qwen/Qwen3-4B-Thinking-2507","value":53.03,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":7.69,"sourceName":"Official MathArena Evaluation","sourceUrl":"https://matharena.ai/?comp=hmmt--hmmt_feb_2026","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":null,"filename":".eval_results/MathArena--hmmt_feb_2026.yaml","parameters":4022468096},{"benchmarkId":"MathArena/hmmt_feb_2026","modelId":"inclusionAI/Ling-2.6-flash","value":49.29,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":0,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ling-2.6-flash","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":null,"filename":".eval_results/hmmt_feb_2026.yaml","parameters":107494409216},{"benchmarkId":"mteb/BRIGHT","modelId":"mteb/baseline-bm25s","value":0.11,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":50,"sourceName":"Obtained using MTEB","sourceUrl":"https://github.com/embeddings-benchmark/mteb/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"Obtained using MTEB","filename":".eval_results/BRIGHT(v1.1).yaml","parameters":null},{"benchmarkId":"collinear-ai/yc-bench","modelId":"MiniMaxAI/MiniMax-M3","value":2100000,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":90.91,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 2.1M (monetary value, final assets fund). The benchmark's 'medium' task is used as the overall evaluation. Metric is monetary, not percentage-based.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"collinear-ai/yc-bench","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":2100000,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":90.91,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 2.1M (monetary value, final assets fund). The benchmark's 'medium' task is used as the overall evaluation. Metric is monetary, not percentage-based.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"collinear-ai/yc-bench","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":2100000,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":90.91,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 2.1M (monetary value, final assets fund). The benchmark's 'medium' task is used as the overall evaluation. Metric is monetary, not percentage-based.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"collinear-ai/yc-bench","modelId":"zai-org/GLM-5.1","value":1510772,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":72.73,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":753864139008},{"benchmarkId":"collinear-ai/yc-bench","modelId":"zai-org/GLM-5","value":1208190,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":63.64,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"avg final funds (USD) across seeds 1,2,3. GLM-5 (via OpenRouter z-ai/glm-5)","filename":".eval_results/yc-bench.yaml","parameters":753864139008},{"benchmarkId":"collinear-ai/yc-bench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":1066426,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":54.55,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":861608274846},{"benchmarkId":"collinear-ai/yc-bench","modelId":"moonshotai/Kimi-K2.6","value":511137,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":45.45,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":1058589420528},{"benchmarkId":"collinear-ai/yc-bench","modelId":"moonshotai/Kimi-K2.5","value":408822,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":36.36,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"avg final funds (USD) across seeds 1,2,3. Kimi K2.5 (via OpenRouter moonshotai/kimi-k2.5)","filename":".eval_results/yc-bench.yaml","parameters":1058589420528},{"benchmarkId":"collinear-ai/yc-bench","modelId":"zai-org/GLM-4.7","value":398410,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":27.27,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":358337791296},{"benchmarkId":"collinear-ai/yc-bench","modelId":"MiniMaxAI/MiniMax-M2.5","value":230465,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":18.18,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":228703644928},{"benchmarkId":"collinear-ai/yc-bench","modelId":"Qwen/Qwen3.5-397B-A17B","value":90787,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":9.09,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"avg final funds (USD) across seeds 1,2,3. Qwen 3.5-397B (via OpenRouter qwen/qwen3.5-397b-a17b)","filename":".eval_results/yc-bench.yaml","parameters":403397928944},{"benchmarkId":"collinear-ai/yc-bench","modelId":"Qwen/Qwen3.5-122B-A10B","value":0,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":0,"sourceName":"YC-Bench eval","sourceUrl":"https://github.com/collinear-ai/yc-bench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":"medium preset, avg final funds (USD) across seeds 1,2,3","filename":".eval_results/yc-bench.yaml","parameters":125086497008},{"benchmarkId":"internlm/WildClawBench","modelId":"tencent/Hy3","value":53.6,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/tencent/Hy3","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":298786155776},{"benchmarkId":"internlm/WildClawBench","modelId":"nex-agi/Nex-N2-Pro","value":53.5,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":91.67,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":396802360816},{"benchmarkId":"internlm/WildClawBench","modelId":"zai-org/GLM-5.1","value":48.2,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":83.33,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":753864139008},{"benchmarkId":"internlm/WildClawBench","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":43.7,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":75,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":861608274846},{"benchmarkId":"internlm/WildClawBench","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":43,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":66.67,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":1023244718976},{"benchmarkId":"internlm/WildClawBench","modelId":"zai-org/GLM-5","value":42.6,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":58.33,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":753864139008},{"benchmarkId":"internlm/WildClawBench","modelId":"openpangu/openPangu-2.0-Flash","value":41.5,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":50,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@3, Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"internlm/WildClawBench","modelId":"internlm/Intern-S2-Preview","value":39.2,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":41.67,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":36098254656},{"benchmarkId":"internlm/WildClawBench","modelId":"openpangu/openPangu-2.0-Flash","value":35,"lowerIsBetter":false,"registryRank":9,"selected":false,"percentile":null,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Avg@3, Non-Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"internlm/WildClawBench","modelId":"Qwen/Qwen3.5-397B-A17B","value":34.5,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":33.33,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":403397928944},{"benchmarkId":"internlm/WildClawBench","modelId":"MiniMaxAI/MiniMax-M2.7","value":33.8,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":25,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":228703644928},{"benchmarkId":"internlm/WildClawBench","modelId":"moonshotai/Kimi-K2.5","value":30.8,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":16.67,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":1058589420528},{"benchmarkId":"internlm/WildClawBench","modelId":"MiniMaxAI/MiniMax-M2.5","value":27.1,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":8.33,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":228703644928},{"benchmarkId":"internlm/WildClawBench","modelId":"stepfun-ai/Step-3.5-Flash","value":26.7,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":0,"sourceName":"WildClawBench","sourceUrl":"https://internlm.github.io/WildClawBench","sourceClass":"self-reported","sourceConfidence":0.62,"verified":false,"notes":null,"filename":".eval_results/wildclawbench.yaml","parameters":199384301376},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepreinforce-ai/Ornith-1.0-397B","value":77.1,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"Ornith-1.0-397B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-397B.yaml","parameters":396802360816},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"MiniMaxAI/MiniMax-M3","value":74.5,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":88.24,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports a single 'Claw-Eval' score. Mapped to the 'general' task (overall); the exact task split is not specified.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":74.5,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":88.24,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports a single 'Claw-Eval' score. Mapped to the 'general' task (overall); the exact task split is not specified.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":74.5,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":88.24,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports a single 'Claw-Eval' score. Mapped to the 'general' task (overall); the exact task split is not specified.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepreinforce-ai/Ornith-1.0-35B","value":69.8,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":76.47,"sourceName":"Ornith-1.0-35B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-35B.yaml","parameters":664944},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"XiaomiMiMo/MiMo-V2.5-Pro","value":64,"lowerIsBetter":false,"registryRank":6,"selected":true,"percentile":70.59,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":1023244718976},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"inclusionAI/Ring-2.6-1T","value":63.82,"lowerIsBetter":false,"registryRank":7,"selected":true,"percentile":64.71,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/inclusionAI/Ring-2.6-1T","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"high reasoning effort, Pass³ | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":1025657871744},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepreinforce-ai/Ornith-1.0-9B","value":63.1,"lowerIsBetter":false,"registryRank":8,"selected":true,"percentile":58.82,"sourceName":"Ornith-1.0-9B model card","sourceUrl":"https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":null,"filename":".eval_results/Ornith-1.0-9B.yaml","parameters":1469680},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"zai-org/GLM-5.1","value":62.7,"lowerIsBetter":false,"registryRank":9,"selected":true,"percentile":52.94,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw-eval.yaml","parameters":753864139008},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"XiaomiMiMo/MiMo-V2.5","value":62.1,"lowerIsBetter":false,"registryRank":10,"selected":true,"percentile":47.06,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":310775040000},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"moonshotai/Kimi-K2.6","value":61.5,"lowerIsBetter":false,"registryRank":11,"selected":true,"percentile":41.18,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":1058589420528},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepseek-ai/DeepSeek-V4-Pro","value":58.4,"lowerIsBetter":false,"registryRank":12,"selected":true,"percentile":35.29,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw-eval.yaml","parameters":861608274846},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"openpangu/openPangu-2.0-Flash","value":58.2,"lowerIsBetter":false,"registryRank":13,"selected":true,"percentile":29.41,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Pass^3, Non-Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"Qwen/Qwen3.5-397B-A17B","value":57.8,"lowerIsBetter":false,"registryRank":14,"selected":true,"percentile":20.59,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":403397928944},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"deepseek-ai/DeepSeek-V4-Flash","value":57.8,"lowerIsBetter":false,"registryRank":15,"selected":true,"percentile":20.59,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw-eval.yaml","parameters":158069433298},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"openpangu/openPangu-2.0-Flash","value":57.7,"lowerIsBetter":false,"registryRank":16,"selected":false,"percentile":null,"sourceName":"openPangu-2.0-Flash model card","sourceUrl":"https://huggingface.co/openpangu/openPangu-2.0-Flash","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"Pass^3, Thinking","filename":".eval_results/openPangu-2.0-Flash.yaml","parameters":100136311993},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"moonshotai/Kimi-K2.5","value":52.8,"lowerIsBetter":false,"registryRank":17,"selected":true,"percentile":11.76,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":1058589420528},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"MiniMaxAI/MiniMax-M2.7","value":49.7,"lowerIsBetter":false,"registryRank":18,"selected":true,"percentile":5.88,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":228703644928},{"benchmarkId":"claw-eval/Claw-Eval","modelId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","value":6.8,"lowerIsBetter":false,"registryRank":19,"selected":true,"percentile":0,"sourceName":"Claw-Eval Leaderboard","sourceUrl":"https://claw-eval.github.io","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"Pass³% | N=3 | 161 tasks","filename":".eval_results/claw_eval.yaml","parameters":123611012096},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"MiniMaxAI/MiniMax-M3","value":85.4,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 'VideoMME (w/ sub)'. Mapped to the closest registered benchmark on the Hub, Video-MME-v2.","filename":".eval_results/minimax-m3.yaml","parameters":427040140160},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound","value":85.4,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 'VideoMME (w/ sub)'. Mapped to the closest registered benchmark on the Hub, Video-MME-v2.","filename":".eval_results/minimax-m3.yaml","parameters":233489984384},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"INCModelSharing/MiniMax-M3-MXFP4-Mixed-MXFP8-Attn-CT-AutoRound","value":85.4,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":75,"sourceName":"MiniMax-M3 model card","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","sourceClass":"self-reported","sourceConfidence":0.52,"verified":false,"notes":"Model card reports 'VideoMME (w/ sub)'. Mapped to the closest registered benchmark on the Hub, Video-MME-v2.","filename":".eval_results/minimax-m3.yaml","parameters":233690524544},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"moonshotai/Kimi-K2.5","value":61.1,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":25,"sourceName":"VideoMMEv2 leaderboard","sourceUrl":"https://video-mme-v2.netlify.app/#leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"512 frames","filename":".eval_results/videomme_v2.yaml","parameters":1058589420528},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"Qwen/Qwen3.5-397B-A17B","value":55.9,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":0,"sourceName":"VideoMMEv2 leaderboard","sourceUrl":"https://video-mme-v2.netlify.app/#leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"512 frames","filename":".eval_results/videomme_v2.yaml","parameters":403397928944},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"moonshotai/Kimi-K2.5","value":54.4,"lowerIsBetter":false,"registryRank":6,"selected":false,"percentile":null,"sourceName":"VideoMMEv2 leaderboard","sourceUrl":"https://video-mme-v2.netlify.app/#leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"64 frames","filename":".eval_results/videomme_v2.yaml","parameters":1058589420528},{"benchmarkId":"MME-Benchmarks/Video-MME-v2","modelId":"Qwen/Qwen3.5-397B-A17B","value":48.9,"lowerIsBetter":false,"registryRank":7,"selected":false,"percentile":null,"sourceName":"VideoMMEv2 leaderboard","sourceUrl":"https://video-mme-v2.netlify.app/#leaderboard","sourceClass":"benchmark-operator","sourceConfidence":0.9,"verified":false,"notes":"64 frames","filename":".eval_results/videomme_v2.yaml","parameters":403397928944},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"crosbylegal/gpt-5.5","value":50.5,"lowerIsBetter":false,"registryRank":1,"selected":true,"percentile":100,"sourceName":"RedlineBench report","sourceUrl":"https://intelligence.crosby.ai/benchmark/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"agent=claude-code; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); published report figure","filename":".eval_results/redlinebench.yaml","parameters":null},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"crosbylegal/claude-fable-5","value":47.3,"lowerIsBetter":false,"registryRank":2,"selected":true,"percentile":75,"sourceName":"RedlineBench report","sourceUrl":"https://intelligence.crosby.ai/benchmark/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"agent=claude-code; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); published report figure","filename":".eval_results/redlinebench.yaml","parameters":null},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"zai-org/GLM-5.2","value":45.7,"lowerIsBetter":false,"registryRank":3,"selected":true,"percentile":50,"sourceName":"Model Card","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2","sourceClass":"self-reported","sourceConfidence":0.58,"verified":false,"notes":"agent=glm-5.2; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); post-publication run","filename":".eval_results/redlinebench.yaml","parameters":753329940480},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"crosbylegal/gemini-3.5-flash","value":45.1,"lowerIsBetter":false,"registryRank":4,"selected":true,"percentile":25,"sourceName":"RedlineBench report","sourceUrl":"https://intelligence.crosby.ai/benchmark/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"agent=opencode; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); published report figure","filename":".eval_results/redlinebench.yaml","parameters":null},{"benchmarkId":"crosbylegal/RedlineBench","modelId":"crosbylegal/claude-opus-4-8","value":44.4,"lowerIsBetter":false,"registryRank":5,"selected":true,"percentile":0,"sourceName":"RedlineBench report","sourceUrl":"https://intelligence.crosby.ai/benchmark/","sourceClass":"unclassified","sourceConfidence":0.46,"verified":false,"notes":"agent=claude-code; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); published report figure","filename":".eval_results/redlinebench.yaml","parameters":null}]}
