{"dataset":{"version":"effort-benchmarks-1","collectedOn":"2026-09-12","id":"sha256-1f186994047883a45f76e96fbce2f07320baf4f104506414be2bba69a334a02f+sha256-2bc644d4e2fb34bd4fecd1ef0a2a50302a9d18f3b8cd3aa0e6dfc487669f5146+sha256-b6d2e58f71798704ee9f3e6b341e3627e6b0dc1caef890fc1e08b62a226e3f36+sha256-7a7d95c40c608cc28483fb5cef9007da8c102f1e7278882ccbcc02a16078607d+sha256-99e5ccb2eac4abb63cc6d9823b591f2ffac992cdee03ac725f66bd8a5ec086a3+sha256-9fbe9729fecc9cf9232f3292684307ba1a85d69beff3920a2a7ed9e2c77bf7ef+sha256-7e00d90a437b5a33e79607a04b57b10dc14322bbaa63ce8bbe9ce1338eaf26f5","benchmarks":[{"id":"aa-aa-analyst-agent","title":"AA-AnalystAgent","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Share of tasks solved on all 5 of 5 attempts · 80 tasks, 5 attempts per task · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-aa-briefcase","title":"AA-Briefcase Elo","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"elo"},{"id":"aa-aime-2025","title":"AIME 2025","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-apex-agents-aa","title":"APEX-Agents-AA","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-artificial-analysis-long-context-reasoning","title":"AA-LCR v1.1","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-automationbench-aa","title":"AutomationBench-AA","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-critpt","title":"CritPt","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-enterprise-ops-gym-aa","title":"EnterpriseOps-Gym-AA","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Overall task success rate across all eight enterprise domains (oracle tool mode) · Benchmark developed by ServiceNow Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-gdp-pdf","title":"GDP.pdf: All-pass","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-gdpval-aa","title":"GDPval-AA v2 Leaderboard","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Elo rating for performance on real-world work tasks · Anchored to a human baseline of 1,000 · Higher is better · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"elo"},{"id":"aa-global-mmlu-lite","title":"Global-MMLU-Lite","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-gpqa-diamond","title":"GPQA Diamond","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-harvey-lab-aa","title":"Harvey LAB-AA: Criterion Pass Rate","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Share of atomic pass/fail rubric criteria the deliverables satisfy, graded by a single LLM judge · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-humanitys-last-exam","title":"Humanity's Last Exam","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-ifbench","title":"IFBench","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-itbench-aa","title":"ITBench-AA","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Combined public and private Site Reliability Engineering (SRE) tasks · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-livecodebench","title":"LiveCodeBench","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-math-500","title":"MATH-500","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-mlcr-aa","title":"MLCR-AA","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Share of tasks judged accurate, complete, and concise · Expert + compound (hard) sets · Benchmark developed by Wisedocs · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-mmlu-pro","title":"MMLU-Pro","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-mmmu-pro","title":"MMMU-Pro","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-omniscience","title":"AA-Omniscience Index","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"index"},{"id":"aa-omniscience-accuracy","title":"AA-Omniscience Accuracy","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis","harness":"6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader","unit":"percent"},{"id":"aa-scicode","title":"SciCode","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-tau2-bench","title":"𝜏²-Bench Telecom","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-tau3-banking","title":"𝜏³-Banking","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-terminalbench-hard","title":"Terminal-Bench Hard","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-terminalbench-v2-1","title":"Terminal-Bench v2.1","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"Artificial Analysis published evaluation; see source for benchmark-specific settings","unit":"percent"},{"id":"aa-terminalbench-v4-0","title":"Terminal-Bench v4.0","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","sourceName":"Artificial Analysis","sourceHash":"9dd065fba187e818380d30ab89b06224f882e92b24b4bddf2e2d409e424477f2","description":"Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis","harness":"mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours","unit":"percent"},{"id":"arc-v2semiprivate","title":"ARC-AGI-2","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","sourceName":"ARC Prize","sourceHash":"b5cb5ec6e8c7547c4f11a4e61e5ed7e0f28a26208f87bd16c83d1703777a2627","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"v2 Semi-Private","unit":"percent"},{"id":"deepswe-minisweagent","title":"DeepSWE v1.1","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","sourceName":"Datacurve","sourceHash":"005cbedb49f988ba3f0d9636300862ad7ace93ce1992b37faf9945fe5b383415","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"mini-swe-agent","unit":"percent"},{"id":"livecode-generationpass1","title":"LiveCodeBench","sourceUrl":"https://livecodebench.github.io/performances_generation.json","sourceName":"LiveCodeBench","sourceHash":"17f9a1d69e3f6290fc8b967a4dd13fbb46e34dd05716fdee793780a1cfadd0c1","description":"Evaluation window 2024-08-01 to 2025-05-01; 454 shared tasks.","harness":"generation pass@1","unit":"percent"},{"id":"swepro-minisweagentstarredrows","title":"SWE-bench Pro public","sourceUrl":"https://labs.scale.com/leaderboard/swe_bench_pro_public","sourceName":"Scale","sourceHash":"4b6853a6d7d94241522ea2ae53bc46d73ffdf19a35874f8f7c464e5b11efdad6","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"mini-swe-agent starred rows","unit":"percent"},{"id":"terminal-claudecode","title":"Terminal-Bench 2.1","sourceUrl":"https://www.tbench.ai/?version=2.1","sourceName":"Terminal-Bench","sourceHash":"a03472372fd4cbf34bd7f344ec2d593e27c2147c00cb3170d898afb07711c1c2","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"Claude Code","unit":"percent"},{"id":"terminal-codex","title":"Terminal-Bench 2.1","sourceUrl":"https://www.tbench.ai/?version=2.1","sourceName":"Terminal-Bench","sourceHash":"a03472372fd4cbf34bd7f344ec2d593e27c2147c00cb3170d898afb07711c1c2","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"Codex","unit":"percent"},{"id":"terminal-cursorcli","title":"Terminal-Bench 2.1","sourceUrl":"https://www.tbench.ai/?version=2.1","sourceName":"Terminal-Bench","sourceHash":"a03472372fd4cbf34bd7f344ec2d593e27c2147c00cb3170d898afb07711c1c2","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"Cursor CLI","unit":"percent"},{"id":"terminal-geminicli","title":"Terminal-Bench 2.1","sourceUrl":"https://www.tbench.ai/?version=2.1","sourceName":"Terminal-Bench","sourceHash":"a03472372fd4cbf34bd7f344ec2d593e27c2147c00cb3170d898afb07711c1c2","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"Gemini CLI","unit":"percent"},{"id":"terminal-minisweagent","title":"Terminal-Bench 2.1","sourceUrl":"https://www.tbench.ai/?version=2.1","sourceName":"Terminal-Bench","sourceHash":"a03472372fd4cbf34bd7f344ec2d593e27c2147c00cb3170d898afb07711c1c2","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"mini-SWE-agent","unit":"percent"},{"id":"terminal-terminus2","title":"Terminal-Bench 2.1","sourceUrl":"https://www.tbench.ai/?version=2.1","sourceName":"Terminal-Bench","sourceHash":"a03472372fd4cbf34bd7f344ec2d593e27c2147c00cb3170d898afb07711c1c2","description":"Original public board. Configuration and task coverage may differ; inspect source.","harness":"Terminus 2","unit":"percent"},{"id":"vulcanbench-v3-07-grok-fable-sol","title":"VulcanBench v3 · Report 07","sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","sourceName":"VulcanBench","sourceHash":"c02b713dd3b1561d3784f7fa9d591ccb5742e713de6777de7b0a806929e48577","description":"Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.","harness":"VulcanBench bare-bones API loop, deterministic hidden tests in Docker","unit":"percent"},{"id":"vulcanbench-v3-08-kimi-k3","title":"VulcanBench v3 · Report 08","sourceUrl":"https://vulcanbench.com/benchmarks/08-kimi-k3.html","sourceName":"VulcanBench","sourceHash":"6a02cea1d1d113406e931a44ed2090f8c86e5a971a95b0b8ae769f56af7edd6a","description":"Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.","harness":"VulcanBench bare-bones API loop, deterministic hidden tests in Docker","unit":"percent"},{"id":"vulcanbench-v3-10-opus5-effort","title":"VulcanBench v3 · Report 10","sourceUrl":"https://vulcanbench.com/benchmarks/10-opus5-effort.html","sourceName":"VulcanBench","sourceHash":"a2cc19b85aa2f19dbf6f2046de41a3622b0a192da35ee3cc321add789c2c62ba","description":"Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.","harness":"VulcanBench bare-bones API loop, deterministic hidden tests in Docker","unit":"percent"},{"id":"vulcanbench-v3-12-qwen38-max","title":"VulcanBench v3 · Report 12","sourceUrl":"https://vulcanbench.com/benchmarks/12-qwen38-max.html","sourceName":"VulcanBench","sourceHash":"93348a3b444e8ab773f6d83e154e2e9e7ff0bfa21e8d1c366e8ee77c9dd33ec4","description":"Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.","harness":"VulcanBench bare-bones API loop, deterministic hidden tests in Docker","unit":"percent"},{"id":"vulcanbench-v3-14-grok-46-effort","title":"VulcanBench v3 · Report 14","sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","sourceName":"VulcanBench","sourceHash":"b3f58f4ab2d2bb721eceb54ae478c7d1c0641d3d0fbd9da3756ee186c473851b","description":"Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.","harness":"VulcanBench bare-bones API loop, deterministic hidden tests in Docker","unit":"percent"},{"id":"vulcanbench-v3-17-qwen38-27b-effort","title":"VulcanBench v3 · Report 17","sourceUrl":"https://vulcanbench.com/benchmarks/17-qwen38-27b-effort.html","sourceName":"VulcanBench","sourceHash":"d1444b1c955c76826e2f4303935c56f94d1ce0dd8982605b90c90baed0276983","description":"Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.","harness":"VulcanBench bare-bones API loop, deterministic hidden tests in Docker","unit":"percent"},{"id":"vulcanbench-v3-18-glm53-zcode-harness","title":"VulcanBench v3 · Report 18","sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","sourceName":"VulcanBench","sourceHash":"a12deea4cd99312c139e72d69e626eb4cd98ddbdc11e0e873dbb123f4e7d2ab5","description":"Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.","harness":"VulcanBench bare-bones API loop, deterministic hidden tests in Docker","unit":"percent"},{"id":"vulcanbench-v3-19-musespark-effort","title":"VulcanBench v3 · Report 19","sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","sourceName":"VulcanBench","sourceHash":"cede0d29ef0808139f63002e08808b9ece833ea8d33f8bf12859af35f19be11c","description":"Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.","harness":"VulcanBench bare-bones API loop, deterministic hidden tests in Docker","unit":"percent"},{"id":"arc3-provider-adapter","title":"ARC-AGI-3 · provider-adapter","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","sourceName":"ARC Prize","sourceHash":"7b7a34fc13e0f695ae542715c2e00326a68f648ca893d26eaf3379cd3bdca55c","description":"ARC-AGI-3; Provider Adapter. Open each result for its exact effort, task subset, metric and protocol details.","harness":"Provider Adapter","unit":"percent"},{"id":"arc3-standard","title":"ARC-AGI-3 · standard","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","sourceName":"ARC Prize","sourceHash":"7b7a34fc13e0f695ae542715c2e00326a68f648ca893d26eaf3379cd3bdca55c","description":"ARC-AGI-3; Standard. Open each result for its exact effort, task subset, metric and protocol details.","harness":"Standard","unit":"percent"},{"id":"frontiercode-1.1-extended-chisel","title":"FrontierCode 1.1 · extended-chisel","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; chisel. Open each result for its exact effort, task subset, metric and protocol details.","harness":"chisel","unit":"percent"},{"id":"frontiercode-1.1-extended-claude-code","title":"FrontierCode 1.1 · extended-claude-code","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; claude-code. Open each result for its exact effort, task subset, metric and protocol details.","harness":"claude-code","unit":"percent"},{"id":"frontiercode-1.1-extended-codex","title":"FrontierCode 1.1 · extended-codex","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; codex. Open each result for its exact effort, task subset, metric and protocol details.","harness":"codex","unit":"percent"},{"id":"frontiercode-1.1-extended-grok-build","title":"FrontierCode 1.1 · extended-grok-build","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; grok-build. Open each result for its exact effort, task subset, metric and protocol details.","harness":"grok-build","unit":"percent"},{"id":"frontiercode-1.1-extended-mini-swe-agent","title":"FrontierCode 1.1 · extended-mini-swe-agent","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; mini-swe-agent. Open each result for its exact effort, task subset, metric and protocol details.","harness":"mini-swe-agent","unit":"percent"},{"id":"frontiercode-1.1-main-chisel","title":"FrontierCode 1.1 · main-chisel","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; chisel. Open each result for its exact effort, task subset, metric and protocol details.","harness":"chisel","unit":"percent"},{"id":"frontiercode-1.1-main-claude-code","title":"FrontierCode 1.1 · main-claude-code","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; claude-code. Open each result for its exact effort, task subset, metric and protocol details.","harness":"claude-code","unit":"percent"},{"id":"frontiercode-1.1-main-codex","title":"FrontierCode 1.1 · main-codex","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; codex. Open each result for its exact effort, task subset, metric and protocol details.","harness":"codex","unit":"percent"},{"id":"frontiercode-1.1-main-grok-build","title":"FrontierCode 1.1 · main-grok-build","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; grok-build. Open each result for its exact effort, task subset, metric and protocol details.","harness":"grok-build","unit":"percent"},{"id":"frontiercode-1.1-main-mini-swe-agent","title":"FrontierCode 1.1 · main-mini-swe-agent","sourceUrl":"https://cognition.com/frontiercode","sourceName":"Cognition","sourceHash":"124169fc88fe23ad8be831bc6746003ecd3c872308ba50ea713ee30c7de5064a","description":"FrontierCode 1.1; mini-swe-agent. Open each result for its exact effort, task subset, metric and protocol details.","harness":"mini-swe-agent","unit":"percent"},{"id":"terminal4-claudecode","title":"Terminal-Bench 4.0 · claudecode","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","sourceName":"Terminal-Bench","sourceHash":"030c8fd63dbc353eab1c2a464e47c36f3b138df2c5f3df1643e9acd0c2319910","description":"Terminal-Bench 4.0; Claude Code. Open each result for its exact effort, task subset, metric and protocol details.","harness":"Claude Code","unit":"percent"},{"id":"terminal4-codex","title":"Terminal-Bench 4.0 · codex","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","sourceName":"Terminal-Bench","sourceHash":"030c8fd63dbc353eab1c2a464e47c36f3b138df2c5f3df1643e9acd0c2319910","description":"Terminal-Bench 4.0; Codex. Open each result for its exact effort, task subset, metric and protocol details.","harness":"Codex","unit":"percent"},{"id":"terminal4-grokbuild","title":"Terminal-Bench 4.0 · grokbuild","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","sourceName":"Terminal-Bench","sourceHash":"030c8fd63dbc353eab1c2a464e47c36f3b138df2c5f3df1643e9acd0c2319910","description":"Terminal-Bench 4.0; Grok Build. Open each result for its exact effort, task subset, metric and protocol details.","harness":"Grok Build","unit":"percent"},{"id":"terminal4-minisweagent","title":"Terminal-Bench 4.0 · minisweagent","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","sourceName":"Terminal-Bench","sourceHash":"030c8fd63dbc353eab1c2a464e47c36f3b138df2c5f3df1643e9acd0c2319910","description":"Terminal-Bench 4.0; mini-SWE-agent. Open each result for its exact effort, task subset, metric and protocol details.","harness":"mini-SWE-agent","unit":"percent"},{"id":"scale-enigma_eval-scaleofficialevaluation","title":"EnigmaEval · Scale official evaluation","sourceUrl":"https://labs.scale.com/leaderboard/enigma_eval","sourceName":"Scale","sourceHash":"7daddc90766c35bf4c23ba7ff57ed56f62cfad2b1ac098826bcde15ac7704bd5","description":"Scale EnigmaEval puzzle-hunt accuracy; source-reported reasoning effort.","harness":"Scale official evaluation","unit":"percent"},{"id":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","title":"HLE · text only · Scale official evaluation","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","sourceName":"Scale","sourceHash":"ca0970fe64e066a1362adfeb89a6009abdead9a74034b8cc7775a1c476d1ef30","description":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.","harness":"Scale official evaluation","unit":"percent"},{"id":"scale-humanitys_last_exam-scaleofficialevaluation","title":"HLE · full · Scale official evaluation","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","sourceName":"Scale","sourceHash":"62ccf731d82da5d08b18f9180b7355383a185e5fb584be78e762b39014020cda","description":"Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.","harness":"Scale official evaluation","unit":"percent"},{"id":"scale-sweatlas-qna-claudecode","title":"SWE Atlas · QnA · claude code","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","sourceName":"Scale","sourceHash":"07a3cc8d0a5f863450b783df7790473b9c40cfba4260b2814e1cd2ea160a7235","description":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.","harness":"claude code","unit":"percent"},{"id":"scale-sweatlas-qna-codex","title":"SWE Atlas · QnA · codex","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","sourceName":"Scale","sourceHash":"07a3cc8d0a5f863450b783df7790473b9c40cfba4260b2814e1cd2ea160a7235","description":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.","harness":"codex","unit":"percent"},{"id":"scale-sweatlas-qna-miniswe","title":"SWE Atlas · QnA · mini-swe","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","sourceName":"Scale","sourceHash":"07a3cc8d0a5f863450b783df7790473b9c40cfba4260b2814e1cd2ea160a7235","description":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.","harness":"mini-swe","unit":"percent"},{"id":"scale-sweatlas-refactoring-claudecode","title":"SWE Atlas · Refactoring · claude code","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-refactoring","sourceName":"Scale","sourceHash":"f9e7a0518addada659d655ed5f1b5160163a3e9a410d6fcc151ba01a6c9d5d1b","description":"70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.","harness":"claude code","unit":"percent"},{"id":"scale-sweatlas-refactoring-codex","title":"SWE Atlas · Refactoring · codex","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-refactoring","sourceName":"Scale","sourceHash":"f9e7a0518addada659d655ed5f1b5160163a3e9a410d6fcc151ba01a6c9d5d1b","description":"70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.","harness":"codex","unit":"percent"},{"id":"scale-sweatlas-tw-claudecode","title":"SWE Atlas · Test Writing · claude code","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","sourceName":"Scale","sourceHash":"69d8837fd0c09fcf1b056c6203c8f533d7b548196ced027ca4091e9763090cdb","description":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.","harness":"claude code","unit":"percent"},{"id":"scale-sweatlas-tw-codex","title":"SWE Atlas · Test Writing · codex","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","sourceName":"Scale","sourceHash":"69d8837fd0c09fcf1b056c6203c8f533d7b548196ced027ca4091e9763090cdb","description":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.","harness":"codex","unit":"percent"},{"id":"scale-sweatlas-tw-miniswe","title":"SWE Atlas · Test Writing · mini-swe","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","sourceName":"Scale","sourceHash":"69d8837fd0c09fcf1b056c6203c8f533d7b548196ced027ca4091e9763090cdb","description":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.","harness":"mini-swe","unit":"percent"},{"id":"livebench-2026-06-25-AMPS_Hard","title":"LiveBench · AMPS Hard · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-code_completion","title":"LiveBench · code completion · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-code_generation","title":"LiveBench · code generation · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-connections","title":"LiveBench · connections · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-consecutive_events","title":"LiveBench · consecutive events · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-integrals_with_game","title":"LiveBench · integrals with game · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-javascript","title":"LiveBench · javascript · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench Mini-SWE-Agent, 250-step limit","unit":"percent"},{"id":"livebench-2026-06-25-logic_with_navigation","title":"LiveBench · logic with navigation · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-math_comp","title":"LiveBench · math comp · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-olympiad","title":"LiveBench · olympiad · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-paraphrase","title":"LiveBench · paraphrase · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-plot_unscrambling","title":"LiveBench · plot unscrambling · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-python","title":"LiveBench · python · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench Mini-SWE-Agent, 250-step limit","unit":"percent"},{"id":"livebench-2026-06-25-simplify","title":"LiveBench · simplify · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-spatial","title":"LiveBench · spatial · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-story_generation","title":"LiveBench · story generation · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-summarize","title":"LiveBench · summarize · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-tablejoin","title":"LiveBench · tablejoin · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-tablereformat","title":"LiveBench · tablereformat · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-theory_of_mind","title":"LiveBench · theory of mind · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-typescript","title":"LiveBench · typescript · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench Mini-SWE-Agent, 250-step limit","unit":"percent"},{"id":"livebench-2026-06-25-typos","title":"LiveBench · typos · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"livebench-2026-06-25-zebra_puzzle","title":"LiveBench · zebra puzzle · 2026-06-25","sourceUrl":"https://livebench.ai/","sourceName":"LiveBench","sourceHash":"186ca65e7bb3a07aa26875eb3c45bfbe4e22d1ef36165cdaa11ad1a58087817c","description":"LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only.","harness":"LiveBench official task evaluation","unit":"percent"},{"id":"swe-rebench-2025-08-tools","title":"SWE-rebench · 2025-08 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2025-09-tools","title":"SWE-rebench · 2025-09 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2025-10-tools","title":"SWE-rebench · 2025-10 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2025-11-tools","title":"SWE-rebench · 2025-11 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2025-12-tools","title":"SWE-rebench · 2025-12 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2026-01-tools","title":"SWE-rebench · 2026-01 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2026-02-tools","title":"SWE-rebench · 2026-02 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2026-03-tools","title":"SWE-rebench · 2026-03 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2026-04-tools","title":"SWE-rebench · 2026-04 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2026-05-tools","title":"SWE-rebench · 2026-05 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"swe-rebench-2026-06-tools","title":"SWE-rebench · 2026-06 · tools","sourceUrl":"https://swe-rebench.com/","sourceName":"SWE-rebench","sourceHash":"fbb1b659562843da266aa20ec2295253d727ccd9b9469c78ab32df6fad1fffed","description":"Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set.","harness":"SWE-rebench standardized ReAct tools","unit":"percent"},{"id":"epoch-chess-puzzles-1-0-0-model-extracted-exact-match","title":"Epoch · Chess Puzzles · v1.0.0","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-chess-puzzles-1-0-1-model-extracted-exact-match","title":"Epoch · Chess Puzzles · v1.0.1","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.1; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-chess-puzzles-1-0-2-model-extracted-exact-match","title":"Epoch · Chess Puzzles · v1.0.2","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-chess-puzzles-1-1-1-model-extracted-exact-match","title":"Epoch · Chess Puzzles · v1.1.1","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.1; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-chess-puzzles-1-1-4-model-extracted-exact-match","title":"Epoch · Chess Puzzles · v1.1.4","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.4; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-chess-puzzles-1-1-5-model-extracted-exact-match","title":"Epoch · Chess Puzzles · v1.1.5","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.5; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","title":"Epoch · Chess Puzzles · v1.1.6","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","title":"Epoch · FrontierMath Tier 4 · v2.0.0","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation.","harness":"Epoch AI Inspect; task 2.0.0; scorer verification_code","unit":"percent"},{"id":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","title":"Epoch · FrontierMath Tiers 1–3 · v2.0.0","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation.","harness":"Epoch AI Inspect; task 2.0.0; scorer verification_code","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-0-choice","title":"Epoch · GPQA diamond · v1.0.0","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.0; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-1-choice","title":"Epoch · GPQA diamond · v1.0.1","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.1; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-10-choice","title":"Epoch · GPQA diamond · v1.0.10","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.10; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-11-choice","title":"Epoch · GPQA diamond · v1.0.11","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.11; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-2-choice","title":"Epoch · GPQA diamond · v1.0.2","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.2; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-3-choice","title":"Epoch · GPQA diamond · v1.0.3","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.3; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-4-choice","title":"Epoch · GPQA diamond · v1.0.4","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.4; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-5-choice","title":"Epoch · GPQA diamond · v1.0.5","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.5; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-6-choice","title":"Epoch · GPQA diamond · v1.0.6","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.6; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-7-choice","title":"Epoch · GPQA diamond · v1.0.7","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.7; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-8-choice","title":"Epoch · GPQA diamond · v1.0.8","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.8; scorer choice","unit":"percent"},{"id":"epoch-gpqa-diamond-1-0-9-choice","title":"Epoch · GPQA diamond · v1.0.9","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.9; scorer choice","unit":"percent"},{"id":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","title":"Epoch · Mystery Game Puzzles · v1.0.4 · Tool submission","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer","unit":"percent"},{"id":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","title":"Epoch · Mystery Game Puzzles · v1.0.4 · Exact move","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-0-0-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.0.0","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.0.0","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.0; scorer model_graded","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-0-2-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.0.2","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-0-3-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.0.3","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.3; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-0-4-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.0.4","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.4; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-0-5-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.0.5","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.5; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-1-2-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.1.2","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.2; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-1-3-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.1.3","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.3; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-1-4-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.1.4","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.4; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-1-5-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.1.5","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.5; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","title":"Epoch · OTIS Mock AIME 2024-2025 · v1.1.6","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match","unit":"percent"},{"id":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","title":"Epoch · SimpleQA Verified · v1.0.0","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer","unit":"percent"},{"id":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","title":"Epoch · SimpleQA Verified · v1.2.0","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","sourceName":"Epoch AI","sourceHash":"655324afe0316bda074bcec4e373f5cb5c447c413f61bd43249dcd2b265dc47d","description":"Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY.","harness":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer","unit":"percent"},{"id":"vals-finance-agent-v2","title":"Vals AI · Finance Agent v2","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","sourceName":"Vals AI","sourceHash":"f03f7d8de61ffce65e47d79c08e5a05ae6b34e3ff9f48e61659fb347fb79bc58","description":"Overall weighted rubric accuracy, averaged over three runs on 450 tasks. Dealbreaker failures and timeouts score zero. Related categories and all-pass scores are not additional votes. Three-model judge panel; private test set.","harness":"Vals FAB v2 shared six-tool harness; two-hour task limit","unit":"percent"},{"id":"vals-code-migration-v1","title":"Vals AI · Code Migration v1","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","sourceName":"Vals AI","sourceHash":"653a333d3b444113ab7d6428f29d87ef5ed0525a0333aa9021c375d152fb6b41","description":"Hidden behavior-test pass rate, equally weighted across 40 repositories (30 CLI and 10 COBOL-to-Java). Anti-cheat failures score zero. Code-quality ratings and language splits are not additional votes.","harness":"Vals Code Migration shared agent harness","unit":"percent"},{"id":"vals-legal-research-v1","title":"Vals AI · Legal Research Bench v1","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","sourceName":"Vals AI","sourceHash":"3cf0516c0b0cbb541bea69ddf0fe6bf822d8e71f302d86d663098926008746cd","description":"All-pass accuracy on 208 private legal research tasks. Every expert rubric check must pass; GPT-5.4 judges responses. Partial-credit scores and practice-area splits are not additional votes.","harness":"Vals Legal Research shared five-tool harness; three-hour task limit","unit":"percent"},{"id":"vals-emb-v1","title":"Vals AI · Excel Modeling Benchmark v1","sourceUrl":"https://www.vals.ai/benchmarks/emb","sourceName":"Vals AI","sourceHash":"a7c6d5391b17d5c96b6e1da22b17d412c0faa1ff7362ee408a5c06372f237975","description":"Mean of seven equally weighted task categories. Template submissions use recalculated Excel cell accuracy; scratch submissions use rubric checks judged by GPT-5.4 Mini XHigh. Partial credit does not mean task completion.","harness":"Vals EMB shared workbook agent harness; 3.5-hour task limit","unit":"percent"},{"id":"vals-mmlu-pro-v1","title":"Vals AI · MMLU-Pro v1","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","sourceName":"Vals AI","sourceHash":"c65dbe60dbbf1f509a2596609354a38a0ecb2500dcece523945280d70ca50fb4","description":"Mean accuracy across 14 subjects under Vals five-shot prompting. Subject splits share one family and are not additional votes. Vals labels this benchmark archived; it is historical corroboration, not ongoing frontier evaluation.","harness":"Vals MMLU-Pro five-shot chain-of-thought; regex answer grading","unit":"percent"},{"id":"vals-terminal-bench-2-1-v2.1","title":"Vals AI · Terminal-Bench 2.1","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","sourceName":"Vals AI","sourceHash":"689e2a932e2b5c488057f98cca732eb21bd8060ee40276d13ba01ef91758f8c2","description":"Overall task pass rate under the shared Terminus 2 configuration. All task tests must pass. Difficulty splits share one family. Fable 5 and Opus 5 mixed-checkpoint fallback runs are excluded.","harness":"Vals Terminus 2 harness; pass@1 on 89 tasks","unit":"percent"},{"id":"vals-vibe-code-bench-v1.1","title":"Vals AI · Vibe Code Bench v1.1","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","sourceName":"Vals AI","sourceHash":"cf3a7c72930b2fe205a640ad5e71a2612a9b5f085288a72e0c863b72df668488","description":"Mean app test pass rate on the canonical v1.1 test set. Browser Use executes workflow tests; each test requires at least 90% of its substeps. Automated judging can introduce error. Alternate agents are excluded.","harness":"Vals modified OpenHands harness; five hours or 1,000 turns per app","unit":"percent"},{"id":"vals-legal-agent-benchmark-v1","title":"Vals AI · Harvey Legal Agent Benchmark v1","sourceUrl":"https://www.vals.ai/benchmarks/hlab","sourceName":"Vals AI","sourceHash":"acc305672041f9677540397c257f96b7b84700be764aba1778538fdc58bbdce5","description":"Mean task resolution across two judges (GPT-5.5 Medium and Sonnet 4.6), requiring every criterion to pass. Criteria pass rates and practice-area splits do not add votes. Shared Harvey family; Fable 5 fallback run excluded.","harness":"Vals Harvey held-out legal file-work protocol; internet disabled","unit":"percent"}],"results":[{"id":"ad37bcc3a2f8fbe16d11bf28","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":1195.25,"warning":null},{"id":"53d28fbb092f0489790e15af","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.6666666666667,"warning":null},{"id":"cfda8506d8f2f566c79b7f13","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.43295195770323,"warning":null},{"id":"fe901ec4d3a93de8dca353cd","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.8571428571429,"warning":null},{"id":"3451d3b73f08ab58971036d1","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":9,"warning":null},{"id":"252993f87b0a46d83c161b41","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":1087.81,"warning":null},{"id":"4e7d0cd968f12fcd6837a961","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":87.57575757575759,"warning":null},{"id":"d22306241e32f3b35c337299","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.595922150139,"warning":null},{"id":"5eca0b0dc509f3d924e864a1","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":-25.1,"warning":null},{"id":"83831ab910de6136f183d0f6","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.483333333333334,"warning":null},{"id":"3d2ba4d99bd8f7a014e1bc82","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.939814814814795,"warning":null},{"id":"125887c34f0290cf5cb09b60","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.3711340206186,"warning":null},{"id":"1a8bae15560fd5c9da384d6e","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.0411985018727,"warning":null},{"id":"b41b48e6be3dfa1ef6d8980d","modelId":"agnes-2.5-pro-alpha","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Agnes 2.5 Pro Alpha","configuration":"Agnes 2.5 Pro Alpha; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/agnes-2-5-pro-alpha; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.03030303030303,"warning":null},{"id":"14d799d1a84fa43e5418d7b3","modelId":"amazon-nova-2-lite","benchmarkId":"aa-aime-2025","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":94.3333333333333,"warning":null},{"id":"77a00d93b0f5ef316bc0a1d8","modelId":"amazon-nova-2-lite","benchmarkId":"aa-aime-2025","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":46.6666666666667,"warning":null},{"id":"b2a0105959356ea86cbdc800","modelId":"amazon-nova-2-lite","benchmarkId":"aa-aime-2025","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":88.6666666666667,"warning":null},{"id":"64756b2e556ca7f8a17d562d","modelId":"amazon-nova-2-lite","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":33.6666666666667,"warning":null},{"id":"0c3fb19ff79ef2b89ad8b459","modelId":"amazon-nova-2-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":60.33333333333331,"warning":null},{"id":"d76da886e62765c45f4009d7","modelId":"amazon-nova-2-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":54.3333333333333,"warning":null},{"id":"43c45983fe0fb2950ee9e471","modelId":"amazon-nova-2-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":60,"warning":null},{"id":"0751248f0bb7ed65861e7389","modelId":"amazon-nova-2-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":18.6666666666667,"warning":null},{"id":"3ec7663d5fc9ea3c3a9845c7","modelId":"amazon-nova-2-lite","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":0.28571428571428603,"warning":null},{"id":"87be9250018af73102dd2d5f","modelId":"amazon-nova-2-lite","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":0,"warning":null},{"id":"31ecbdac99d99d717eb4b69e","modelId":"amazon-nova-2-lite","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":0,"warning":null},{"id":"ee6d3dc313301dfa2d7580f1","modelId":"amazon-nova-2-lite","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":0,"warning":null},{"id":"4993197d550d0437d05637f2","modelId":"amazon-nova-2-lite","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":535.99,"warning":null},{"id":"e0cbb3c39f8958e73c8b93c4","modelId":"amazon-nova-2-lite","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":78.17424242424241,"warning":null},{"id":"77f69a1006c2ef2b6abd62bd","modelId":"amazon-nova-2-lite","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":81.1111111111111,"warning":null},{"id":"1aea748fca8ce6be15473ca6","modelId":"amazon-nova-2-lite","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":69.7979797979798,"warning":null},{"id":"8b42bcc7d72018b481f9d6c8","modelId":"amazon-nova-2-lite","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":76.76767676767679,"warning":null},{"id":"341be8170b3f5df517a7b9f0","modelId":"amazon-nova-2-lite","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":60.303030303030305,"warning":null},{"id":"9adff1036db8300025ee8851","modelId":"amazon-nova-2-lite","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":11.631139944393,"warning":null},{"id":"a898268580591f6bc1b5017b","modelId":"amazon-nova-2-lite","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":4.03151065801668,"warning":null},{"id":"0d1e0d12a0e2697685e738b4","modelId":"amazon-nova-2-lite","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":8.98980537534754,"warning":null},{"id":"bb07aadd4166403d7629e25e","modelId":"amazon-nova-2-lite","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":2.87303058387396,"warning":null},{"id":"617a75985f9d2bf4173a41f9","modelId":"amazon-nova-2-lite","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":70.7482993197279,"warning":null},{"id":"f3e8d9bb698a5328e7da979c","modelId":"amazon-nova-2-lite","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":61.2244897959184,"warning":null},{"id":"26aa72ea349d3636c0c207d2","modelId":"amazon-nova-2-lite","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":68.5034013605442,"warning":null},{"id":"49a7a5a737f5b970e9b48dc4","modelId":"amazon-nova-2-lite","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":40.5442176870748,"warning":null},{"id":"60e3e99d7079c86ec8901d6a","modelId":"amazon-nova-2-lite","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":71.1111111111111,"warning":null},{"id":"880b196d9ae0044312f5f0b0","modelId":"amazon-nova-2-lite","benchmarkId":"aa-livecodebench","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":46.8783068783069,"warning":null},{"id":"7b7053d76bf32edf1ce36ca6","modelId":"amazon-nova-2-lite","benchmarkId":"aa-livecodebench","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":66.3492063492063,"warning":null},{"id":"81d6342d15ab0e2f8e535ccd","modelId":"amazon-nova-2-lite","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":34.6031746031746,"warning":null},{"id":"8e87f48fb86040e2c58054ee","modelId":"amazon-nova-2-lite","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":81.8234707446808,"warning":null},{"id":"f7325ca2c64074f1d8d7a2c6","modelId":"amazon-nova-2-lite","benchmarkId":"aa-mmlu-pro","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":78.7815824468085,"warning":null},{"id":"6f3218cb03af524271bbe7b0","modelId":"amazon-nova-2-lite","benchmarkId":"aa-mmlu-pro","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":81.31648936170211,"warning":null},{"id":"3af2c688d4c527bc96bdfee4","modelId":"amazon-nova-2-lite","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":74.3351063829787,"warning":null},{"id":"3a4fea5769cd4ea595e3f20e","modelId":"amazon-nova-2-lite","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":63.757225433526,"warning":null},{"id":"275519f4bf513ae6169d9b06","modelId":"amazon-nova-2-lite","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":57.976878612716796,"warning":null},{"id":"ff7874fe6f63e29676c8c47a","modelId":"amazon-nova-2-lite","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":62.5433526011561,"warning":null},{"id":"971a463f2747f1886585e328","modelId":"amazon-nova-2-lite","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":49.0173410404624,"warning":null},{"id":"dbcffb6add1d04899e8b3269","modelId":"amazon-nova-2-lite","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":-54.9833333333333,"warning":null},{"id":"83d446faabe43549fc8be324","modelId":"amazon-nova-2-lite","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":-54.1,"warning":null},{"id":"05bbf3b36c46a5d97b7af99f","modelId":"amazon-nova-2-lite","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":-56.9666666666667,"warning":null},{"id":"5b5db7acabdd817b3e7dd73e","modelId":"amazon-nova-2-lite","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":-59.8166666666667,"warning":null},{"id":"afb57bb88ef56dd427661b2d","modelId":"amazon-nova-2-lite","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":19.03333333333333,"warning":null},{"id":"6c6d58f64d07be8bd8224d07","modelId":"amazon-nova-2-lite","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":17.65,"warning":null},{"id":"d9230424096816687b209590","modelId":"amazon-nova-2-lite","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":18.166666666666668,"warning":null},{"id":"3e84abbf7f996ec789cd2885","modelId":"amazon-nova-2-lite","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":14.016666666666666,"warning":null},{"id":"71c943ab8c5eab00a4c30043","modelId":"amazon-nova-2-lite","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":72.8070175438596,"warning":null},{"id":"450be57bac445f754df60261","modelId":"amazon-nova-2-lite","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":71.92982456140349,"warning":null},{"id":"4061e9966b4ff81008aa5344","modelId":"amazon-nova-2-lite","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":75.7309941520468,"warning":null},{"id":"04fb036f055cd49b327a6ded","modelId":"amazon-nova-2-lite","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":61.9883040935672,"warning":null},{"id":"7e343ed4dd2e1401efdacad3","modelId":"amazon-nova-2-lite","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":16.6666666666667,"warning":null},{"id":"e5dfd55398cbbd3eae5a8ccb","modelId":"amazon-nova-2-lite","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"Nova 2.0 Lite (low)","configuration":"Nova 2.0 Lite (low); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low","score":3.78787878787879,"warning":null},{"id":"8eaa999820b9e6805a4b51bf","modelId":"amazon-nova-2-lite","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"Nova 2.0 Lite (medium)","configuration":"Nova 2.0 Lite (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium","score":17.4242424242424,"warning":null},{"id":"eb49445c621170b904099ffd","modelId":"amazon-nova-2-lite","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Nova 2.0 Lite (Non-reasoning)","configuration":"Nova 2.0 Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-lite","score":6.81818181818182,"warning":null},{"id":"c9703171c0c398856408c474","modelId":"amazon-nova-2-lite","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Nova 2.0 Lite (high)","configuration":"Nova 2.0 Lite (high); Model source: https://artificialanalysis.ai/models/nova-2-0-lite-reasoning","score":16.1048689138577,"warning":null},{"id":"aa4583be3fa22d830b8f8f25","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-aime-2025","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":63.3333333333333,"warning":null},{"id":"3846226f9a4f5dd9d89d3dd1","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-aime-2025","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":89,"warning":null},{"id":"6175ce4adc218cc2822fcbf9","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":30.666666666666696,"warning":null},{"id":"f9ff4d8772bb55e2ef2ddcb7","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":64.6666666666667,"warning":null},{"id":"de4a8f08e90e822753707555","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":64,"warning":null},{"id":"27dd6af97bc82a3f33e9bbb4","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":30,"warning":null},{"id":"163665ac054efd9d9a38517d","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":0,"warning":null},{"id":"576f4f9c9b1effaaed221378","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":0,"warning":null},{"id":"0dde0536564f2839a2ce52d8","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":0,"warning":null},{"id":"e64b707ff2d699c4ecab8798","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":600.77,"warning":null},{"id":"633313af7ea748295dbcd2a8","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":629.57,"warning":null},{"id":"06219722cf816fd5e2329eb6","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":508.59,"warning":null},{"id":"a696000446e4a94aada1fdcb","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-global-mmlu-lite","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":87.6,"warning":null},{"id":"7292759b8cb168b50cfc12a5","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":78.625,"warning":null},{"id":"31db5b88eadca6dc97116930","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":75.0505050505051,"warning":null},{"id":"ee7d2db9b09a1f2983f7db7b","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":78.4848484848485,"warning":null},{"id":"38aa2e7ea58f399abf54de70","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":63.636363636363605,"warning":null},{"id":"9b1f0df1aefef1081c703ec3","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":5.18999073215941,"warning":null},{"id":"209c17d4d5266a21ce2de7df","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":9.40685820203892,"warning":null},{"id":"b14ffa0e6e2c2eaae9e72551","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":3.93883225208526,"warning":null},{"id":"822022aa52507b9b3001d3c1","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":79.5918367346939,"warning":null},{"id":"b8a630ac2b0ff385963c2da4","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":79.0476190476191,"warning":null},{"id":"9fe32683ff453994e752cf0b","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":52.0408163265306,"warning":null},{"id":"5653889b31519d66e60b5b3c","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-livecodebench","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":63.8095238095238,"warning":null},{"id":"143991a4a457eea92fe5171c","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-livecodebench","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":73.015873015873,"warning":null},{"id":"bd2de967d5e4ceefd8d21f5f","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":47.3015873015873,"warning":null},{"id":"4d03bd7f7196acd07f6a41e5","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-mlcr-aa","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":3.88888888888889,"warning":null},{"id":"ce55605faf854659ff0fe76f","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-mmlu-pro","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":82.16422872340429,"warning":null},{"id":"fc95d33f7ca12e3fd5fe88fc","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-mmlu-pro","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":82.953789893617,"warning":null},{"id":"b491e7d678f7eb03aa97fe4f","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":77.1609042553192,"warning":null},{"id":"485ff3ed3089d2ec72eb65fb","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":62.71676300578039,"warning":null},{"id":"5f803a4fc980517eb71432d0","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":64.5086705202312,"warning":null},{"id":"5e48ea7bbae50fbfc4709191","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":-40.5333333333333,"warning":null},{"id":"f918288816d545d015333d7a","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":-49.05,"warning":null},{"id":"83c3679cc2593a1416e8ece0","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":-49.5,"warning":null},{"id":"25293590da29402fbd862593","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":17.1,"warning":null},{"id":"c1cb257283aefcb143faca8c","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":21.96666666666667,"warning":null},{"id":"e507780d68e9a88b3fe816c3","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":16.916666666666664,"warning":null},{"id":"d8fa487d441e2a3bff731883","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":90.6432748538012,"warning":null},{"id":"a17ba591cb2cb5153c9a6064","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":92.6900584795322,"warning":null},{"id":"073593c114d374a6b5814324","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":71.6374269005848,"warning":null},{"id":"d67198df6216e3d8b684dfaa","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":17.4242424242424,"warning":null},{"id":"4f88cd83a215ca158a04fc06","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":24.2424242424242,"warning":null},{"id":"77e985c0ed8b2995e6b8a80d","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":16.6666666666667,"warning":null},{"id":"b46dbb37766de1e2ef10d6de","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"Nova 2.0 Pro Preview (low)","configuration":"Nova 2.0 Pro Preview (low); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low","score":19.4756554307116,"warning":null},{"id":"366ec0058521e2c38f0622be","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"Nova 2.0 Pro Preview (medium)","configuration":"Nova 2.0 Pro Preview (medium); Model source: https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium","score":29.588014981273396,"warning":null},{"id":"f56f639149bec0565169758c","modelId":"amazon-nova-2-pro-preview","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Nova 2.0 Pro Preview (Non-reasoning)","configuration":"Nova 2.0 Pro Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/nova-2-0-pro","score":17.2284644194757,"warning":null},{"id":"50e4adca8e5e54dc5a129468","modelId":"amazon-nova-lite","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.000000000000001,"warning":null},{"id":"adf5df0b30d27f83e52f2b51","modelId":"amazon-nova-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":19,"warning":null},{"id":"ff486d9ba46adad27a1b6fe4","modelId":"amazon-nova-lite","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"dbd1d83f7580735392e6f6a7","modelId":"amazon-nova-lite","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.3333333333333,"warning":null},{"id":"981168cc7575baa0277b03a4","modelId":"amazon-nova-lite","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.29,"warning":null},{"id":"6feffecc4d281a47d9a8c63c","modelId":"amazon-nova-lite","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.149659863945594,"warning":null},{"id":"dbdd0586ea1c53079fda7843","modelId":"amazon-nova-lite","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.7195767195767,"warning":null},{"id":"7dd1a3d260f548765e07a7db","modelId":"amazon-nova-lite","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.46666666666671,"warning":null},{"id":"c8e86b20efeee800f08898bd","modelId":"amazon-nova-lite","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"c3a7675bf193929b296e1238","modelId":"amazon-nova-lite","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.959441489361694,"warning":null},{"id":"fd3e68f24b42e3314808e348","modelId":"amazon-nova-lite","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.8034682080925,"warning":null},{"id":"ed17e3be2f9a297198964c70","modelId":"amazon-nova-lite","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":-42.1666666666667,"warning":null},{"id":"c810f78cb4cfe1a60c148b93","modelId":"amazon-nova-lite","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.8,"warning":null},{"id":"02860b6478118aafcbe8cda2","modelId":"amazon-nova-lite","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.5438596491228,"warning":null},{"id":"69ddc6a403ed9b335c7c7e51","modelId":"amazon-nova-lite","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Nova Lite","configuration":"Nova Lite; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.757575757575758,"warning":null},{"id":"c395cbf5898af86d26300d73","modelId":"amazon-nova-micro","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":6,"warning":null},{"id":"cfcec14d811a655ca4726508","modelId":"amazon-nova-micro","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":13,"warning":null},{"id":"db9b99c98dd617c9ca05910d","modelId":"amazon-nova-micro","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"696c084e4d6c62ab15b53492","modelId":"amazon-nova-micro","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.7575757575758,"warning":null},{"id":"f8a60f4c48d2cf35f26ad74c","modelId":"amazon-nova-micro","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.6339202965709,"warning":null},{"id":"7e8455203b39b886b2967732","modelId":"amazon-nova-micro","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.387755102040803,"warning":null},{"id":"aef838f6a1d2eca33b5a1e33","modelId":"amazon-nova-micro","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.968253968253999,"warning":null},{"id":"ffa04be81f3227c6f19350f1","modelId":"amazon-nova-micro","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.3333333333333,"warning":null},{"id":"35e37d3045a2a291273b84f1","modelId":"amazon-nova-micro","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":53.083444148936195,"warning":null},{"id":"03faabf6a483486fa063a636","modelId":"amazon-nova-micro","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":-48.5166666666667,"warning":null},{"id":"abebfd3cf4beb6117af462cc","modelId":"amazon-nova-micro","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.033333333333333,"warning":null},{"id":"88ec995dfbbdc4b5240ddad1","modelId":"amazon-nova-micro","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.0350877192982,"warning":null},{"id":"19d78b7b4a3613704624e4c9","modelId":"amazon-nova-micro","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Nova Micro","configuration":"Nova Micro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-micro; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.51515151515152,"warning":null},{"id":"ce9a2089796d737603a17e0b","modelId":"amazon-nova-premier","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.3333333333333,"warning":null},{"id":"f2f040f4479911816988b68b","modelId":"amazon-nova-premier","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.3333333333333,"warning":null},{"id":"56f117757019799897341310","modelId":"amazon-nova-premier","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"0e3b171515df1dcd1001b493","modelId":"amazon-nova-premier","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.64583333333334,"warning":null},{"id":"6a6eaae484ab8fcb709d1c0f","modelId":"amazon-nova-premier","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":56.8686868686869,"warning":null},{"id":"5f0a56bbcc02e28b010b7360","modelId":"amazon-nova-premier","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.17052826691381,"warning":null},{"id":"8be501c4015a8228e5bf59d1","modelId":"amazon-nova-premier","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.190476190476204,"warning":null},{"id":"63e379977a372098a782ec00","modelId":"amazon-nova-premier","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.7460317460317,"warning":null},{"id":"9c279ec3f04cf3fdc739c887","modelId":"amazon-nova-premier","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":83.93333333333331,"warning":null},{"id":"354ff394a1c479d16d1ff096","modelId":"amazon-nova-premier","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.3460771276596,"warning":null},{"id":"9ba3c2f0a8977ad288a8f0ec","modelId":"amazon-nova-premier","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":-35.3833333333333,"warning":null},{"id":"fe566bdc8b0fe8917d76032e","modelId":"amazon-nova-premier","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.25,"warning":null},{"id":"0bfbe8f57f24704b45f141ff","modelId":"amazon-nova-premier","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.3040935672515,"warning":null},{"id":"3abff7933c0a42c95c4f53c9","modelId":"amazon-nova-premier","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Nova Premier","configuration":"Nova Premier; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-premier; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.81818181818182,"warning":null},{"id":"541b9cd8656670591c6a1d18","modelId":"amazon-nova-pro","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.000000000000001,"warning":null},{"id":"9a068df3721adea27be27ecf","modelId":"amazon-nova-pro","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":21,"warning":null},{"id":"d4896e593ff5512235c65933","modelId":"amazon-nova-pro","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"fca9c963afc237552313f230","modelId":"amazon-nova-pro","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":49.898989898989896,"warning":null},{"id":"3b7c848ef0c5b4072692c53a","modelId":"amazon-nova-pro","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.19,"warning":null},{"id":"1718757623befb2b04cdffa0","modelId":"amazon-nova-pro","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.0952380952381,"warning":null},{"id":"7a72aadc62751bdabe32c810","modelId":"amazon-nova-pro","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.2804232804233,"warning":null},{"id":"fc2fc962c57c7a95ec0f5ab6","modelId":"amazon-nova-pro","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.60000000000001,"warning":null},{"id":"2b21dffdfeaeb4feaa7217c7","modelId":"amazon-nova-pro","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.0990691489362,"warning":null},{"id":"99044be57784aba47c270823","modelId":"amazon-nova-pro","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.3352601156069,"warning":null},{"id":"ffd340540d54b4c2be0c4e29","modelId":"amazon-nova-pro","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":-47.7333333333333,"warning":null},{"id":"0050677da9a66bbd582ceef2","modelId":"amazon-nova-pro","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.866666666666667,"warning":null},{"id":"180bc2e6c945ab26a8631548","modelId":"amazon-nova-pro","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.0350877192982,"warning":null},{"id":"d8eefcfd98bc646739e26568","modelId":"amazon-nova-pro","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Nova Pro","configuration":"Nova Pro; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/nova-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.06060606060606,"warning":null},{"id":"5222e61d0123ece9278f23ce","modelId":"claude-fable-5","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":48.75,"warning":null},{"id":"19d3225518b4ccc8a6be41a6","modelId":"claude-fable-5","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":1529.62,"warning":null},{"id":"0ee4fa47e6674b3096c09c9e","modelId":"claude-fable-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":82.3333333333333,"warning":null},{"id":"680b64b696a83786a6320608","modelId":"claude-fable-5","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":54.071301140653816,"warning":null},{"id":"54215a497f41ddcb020ffe22","modelId":"claude-fable-5","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":28.571428570000002,"warning":null},{"id":"8d97f93bf22fc4c9fca52916","modelId":"claude-fable-5","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":51.11906893464637,"warning":null},{"id":"de3bcc367e4e2ad72d9e19cd","modelId":"claude-fable-5","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":24,"warning":null},{"id":"428780032df0d32274761c4c","modelId":"claude-fable-5","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":1631.46,"warning":null},{"id":"3c449154a748a844ff65a5ae","modelId":"claude-fable-5","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":92.6262626262626,"warning":null},{"id":"1ad95d72f436373a20ff679a","modelId":"claude-fable-5","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":93.55912577797079,"warning":null},{"id":"b5d9558a6fc07487bf1ba370","modelId":"claude-fable-5","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":55.468025949953706,"warning":null},{"id":"1463611e4689ae0b5f7fe952","modelId":"claude-fable-5","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":63.469387755102005,"warning":null},{"id":"744e2629ba0b96b375ed57e4","modelId":"claude-fable-5","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":64.4444444444444,"warning":null},{"id":"9966b462b29331ecbde42490","modelId":"claude-fable-5","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":43.3,"warning":null},{"id":"577b7d5cb453524e4357e7a2","modelId":"claude-fable-5","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":65.35,"warning":null},{"id":"1b65a404336eb24164c2e979","modelId":"claude-fable-5","benchmarkId":"aa-scicode","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":60.9953703703704,"warning":null},{"id":"605ea36789b69436cd8ec072","modelId":"claude-fable-5","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":98.5380116959064,"warning":null},{"id":"d0061ee612fdeb8168aa309b","modelId":"claude-fable-5","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":38.144329896907195,"warning":null},{"id":"2a12cb0123ccdceb07c3e79b","modelId":"claude-fable-5","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":62.878787878787904,"warning":null},{"id":"f1d9353cb007b83474b87e3c","modelId":"claude-fable-5","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":84.6441947565543,"warning":null},{"id":"9601059aaf11a654942910e5","modelId":"claude-fable-5","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)","configuration":"Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5","score":42.4242424242424,"warning":null},{"id":"28d5bc6a86675295d42cb6c0","modelId":"claude-fable-5","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Claude Fable 5 (High)","configuration":"Claude Fable 5 (High); Source model ID: anthropic-claude-fable-5-high; 120 tasks","score":87.5,"warning":null},{"id":"6f9372a183ee68e6b48bb18c","modelId":"claude-fable-5","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Claude Fable 5 (Low)","configuration":"Claude Fable 5 (Low); Source model ID: anthropic-claude-fable-5-low; 120 tasks","score":76.80555555555554,"warning":null},{"id":"332952f68252290ee6a5a920","modelId":"claude-fable-5","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"Claude Fable 5 (Max)","configuration":"Claude Fable 5 (Max); Source model ID: anthropic-claude-fable-5-max; 120 tasks","score":89.16666666666667,"warning":null},{"id":"47f74dad473d960addbaf5cd","modelId":"claude-fable-5","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Claude Fable 5 (Medium)","configuration":"Claude Fable 5 (Medium); Source model ID: anthropic-claude-fable-5-medium; 120 tasks","score":82.5,"warning":null},{"id":"fd5f5a2e4f7c743ac93db432","modelId":"claude-fable-5","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"Claude Fable 5 (XHigh)","configuration":"Claude Fable 5 (XHigh); Source model ID: anthropic-claude-fable-5-xhigh; 120 tasks","score":88.33333333333333,"warning":null},{"id":"557dcb6d136782df1d6e3170","modelId":"claude-fable-5","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"claude-fable-5","configuration":"claude-fable-5; Reported effort: high; 113 unique tasks; 430 attempts; 4 runs","score":68.6,"warning":null},{"id":"59377a8e5a165f1e29a9f170","modelId":"claude-fable-5","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"claude-fable-5","configuration":"claude-fable-5; Reported effort: low; 113 unique tasks; 433 attempts; 4 runs","score":59.6,"warning":null},{"id":"3efb0703151365e0a5c57ad7","modelId":"claude-fable-5","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"claude-fable-5","configuration":"claude-fable-5; Reported effort: max; 113 unique tasks; 436 attempts; 4 runs","score":69.7,"warning":null},{"id":"9eade32ea719c5f0ba716c1d","modelId":"claude-fable-5","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"claude-fable-5","configuration":"claude-fable-5; Reported effort: medium; 113 unique tasks; 436 attempts; 4 runs","score":65.4,"warning":null},{"id":"2c326836891084fe24c0ed23","modelId":"claude-fable-5","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"claude-fable-5","configuration":"claude-fable-5; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs","score":69.9,"warning":null},{"id":"c44bf1486b2f7dadbe84989a","modelId":"claude-fable-5","benchmarkId":"terminal-claudecode","level":"xhigh","sourceLabel":"Fable 5","configuration":"Fable 5; Reported effort: xhigh; 445 trials; recorded 2026-06-09","score":83.82,"warning":null},{"id":"667b208122296e70c88bf453","modelId":"claude-fable-5","benchmarkId":"terminal-terminus2","level":"high","sourceLabel":"Fable 5","configuration":"Fable 5; Reported effort: high; 445 trials; recorded 2026-06-09","score":80.45,"warning":null},{"id":"8c767d5ab6384b96f9010a82","modelId":"claude-fable-5-1","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":57.49999999999999,"warning":null},{"id":"50b1ef50758cbe6e3e7b2670","modelId":"claude-fable-5-1","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":1578.19,"warning":null},{"id":"0db58b309bd9c9bcf504997e","modelId":"claude-fable-5-1","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":1483.73,"warning":null},{"id":"b3e19c0045c0eaec856209c2","modelId":"claude-fable-5-1","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":1661.82,"warning":null},{"id":"4cff675467f54077a118366b","modelId":"claude-fable-5-1","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":1531.2,"warning":null},{"id":"706f331d94b42da72a1e1201","modelId":"claude-fable-5-1","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":1650.01,"warning":null},{"id":"598af2bd77d73da5cec3e552","modelId":"claude-fable-5-1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":83.6666666666667,"warning":null},{"id":"f8523e5443d536bd47fd6505","modelId":"claude-fable-5-1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":82.3333333333333,"warning":null},{"id":"5f4ffc277e559a8291b00d73","modelId":"claude-fable-5-1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":85.3333333333333,"warning":null},{"id":"843c626e866362d8cd87a028","modelId":"claude-fable-5-1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":84.6666666666667,"warning":null},{"id":"399a2b5e968764b4790f969c","modelId":"claude-fable-5-1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":83,"warning":null},{"id":"31bfa9b9f74ca86a50b0156c","modelId":"claude-fable-5-1","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":55.323097464639794,"warning":null},{"id":"0f39111d381d1364e81a542b","modelId":"claude-fable-5-1","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":52.2404059498186,"warning":null},{"id":"eacb51c8e87a7c410276ba17","modelId":"claude-fable-5-1","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":59.37591715646424,"warning":null},{"id":"45fa7394cbd38c801f20474a","modelId":"claude-fable-5-1","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":54.661034656728845,"warning":null},{"id":"618d9e76b6eb57ca3bcfb5b1","modelId":"claude-fable-5-1","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":57.77242508489599,"warning":null},{"id":"67e728b27e7cac9181b83ed6","modelId":"claude-fable-5-1","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":30.2857142857143,"warning":null},{"id":"4e8acabfa89f8d0bb6a4cea8","modelId":"claude-fable-5-1","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":27.7142857142857,"warning":null},{"id":"ca8f62d35b4afeef27e6ccdb","modelId":"claude-fable-5-1","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":29.714285714285698,"warning":null},{"id":"d38118e2ffb318c2aa3e3814","modelId":"claude-fable-5-1","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":29.1428571428571,"warning":null},{"id":"833da61d17bd29175043cf58","modelId":"claude-fable-5-1","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":31.1428571428571,"warning":null},{"id":"c85fa539e15511983dd0461c","modelId":"claude-fable-5-1","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":26.8,"warning":null},{"id":"7495dc8ba744e6c00403ec2c","modelId":"claude-fable-5-1","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":28.000000000000004,"warning":null},{"id":"2fab1974add12bcdedee8d5f","modelId":"claude-fable-5-1","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":26.200000000000003,"warning":null},{"id":"7c48a3bf4d6b9ee989cb4301","modelId":"claude-fable-5-1","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":26.8,"warning":null},{"id":"b4fb4fe89df5d58f1d649e5a","modelId":"claude-fable-5-1","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":26.200000000000003,"warning":null},{"id":"22a61bb91a2a848a7aaa01f4","modelId":"claude-fable-5-1","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":1649.77,"warning":null},{"id":"56cf34e23d01d54673edd390","modelId":"claude-fable-5-1","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":1503.72,"warning":null},{"id":"4dd9ffce8af725c94fc62c52","modelId":"claude-fable-5-1","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":1763.64,"warning":null},{"id":"f5e184202558abc3af535731","modelId":"claude-fable-5-1","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":1579.31,"warning":null},{"id":"960305805fd5bd6c6dd4f56b","modelId":"claude-fable-5-1","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":1745.29,"warning":null},{"id":"4ecc02773bd7ff3ec9c0186b","modelId":"claude-fable-5-1","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":90.6060606060606,"warning":null},{"id":"a28c83371bfa7c7f4036bb38","modelId":"claude-fable-5-1","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":88.0808080808081,"warning":null},{"id":"56e19612c165fd00da95d347","modelId":"claude-fable-5-1","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":93.7373737373737,"warning":null},{"id":"68b36c309fc71fc38607f10d","modelId":"claude-fable-5-1","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":88.5858585858586,"warning":null},{"id":"7ffc561cd3a97d25c4d83e56","modelId":"claude-fable-5-1","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":93.4343434343434,"warning":null},{"id":"82a94f00f660b6b69c560e78","modelId":"claude-fable-5-1","benchmarkId":"aa-harvey-lab-aa","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":92.9512230424084,"warning":null},{"id":"01584fe92740dab26d1a82cb","modelId":"claude-fable-5-1","benchmarkId":"aa-harvey-lab-aa","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":92.3288464321899,"warning":null},{"id":"cb980b508bb7de6e8a60602e","modelId":"claude-fable-5-1","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":93.0235924156897,"warning":null},{"id":"c93a148cc00a00c4296dd23e","modelId":"claude-fable-5-1","benchmarkId":"aa-harvey-lab-aa","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":92.64727167462729,"warning":null},{"id":"09418514956dfe8150fe5db8","modelId":"claude-fable-5-1","benchmarkId":"aa-harvey-lab-aa","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":93.2696482848459,"warning":null},{"id":"1b1a819b085a3ec294c7e8de","modelId":"claude-fable-5-1","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":55.9314179796108,"warning":null},{"id":"3e98323dba07921b9c5c62e1","modelId":"claude-fable-5-1","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":48.887859128823,"warning":null},{"id":"e48dbc098b0fb31a3a874828","modelId":"claude-fable-5-1","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":59.1288229842447,"warning":null},{"id":"f04626f3b72848c21148576e","modelId":"claude-fable-5-1","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":53.79981464318811,"warning":null},{"id":"f2a4d9bd93f2fc6f534b5fe9","modelId":"claude-fable-5-1","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":58.7117701575533,"warning":null},{"id":"6495b66e8d711ccf1b3b50cd","modelId":"claude-fable-5-1","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":71.1111111111111,"warning":null},{"id":"35674df3f02b7941e8620349","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":40.8,"warning":null},{"id":"597a3f60fc7069ecd1b62427","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":34.1333333333333,"warning":null},{"id":"58328d3a42b280731f127b87","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":43.45,"warning":null},{"id":"37d9e698a4a4cb9b195ba794","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":37.6,"warning":null},{"id":"896645ed1ede361c8c0efe9a","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":42.3833333333333,"warning":null},{"id":"28a67006474651e3423b9c3a","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":64.93333333333334,"warning":null},{"id":"e923688d79048f36fcbf5cf8","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":60.23333333333334,"warning":null},{"id":"4a9b48125a7a12fa9c2ed18f","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":67.23333333333333,"warning":null},{"id":"d7f05e3e2a9ec8e6cd3fcc35","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":63.1,"warning":null},{"id":"f7800dd959c9c9c332f79e99","modelId":"claude-fable-5-1","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":66.21666666666667,"warning":null},{"id":"b8b018762a29006e12d9587b","modelId":"claude-fable-5-1","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":58.6805555555556,"warning":null},{"id":"67cf4f284cf9fea377b8405b","modelId":"claude-fable-5-1","benchmarkId":"aa-scicode","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":56.712962962963,"warning":null},{"id":"559bdd63a6706d0f6fee9a81","modelId":"claude-fable-5-1","benchmarkId":"aa-scicode","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":63.078703703703695,"warning":null},{"id":"1ca32c0218ee7be58ce7af69","modelId":"claude-fable-5-1","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":56.3657407407407,"warning":null},{"id":"9483878dd9257fc729ce79af","modelId":"claude-fable-5-1","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":60.8796296296296,"warning":null},{"id":"f5b00c8a4cdf9cbf28308958","modelId":"claude-fable-5-1","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":43.0927835051546,"warning":null},{"id":"11fec5746028caad463b6b63","modelId":"claude-fable-5-1","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":38.9690721649485,"warning":null},{"id":"d93eaf0e3e460c62a67ccf6a","modelId":"claude-fable-5-1","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":47.2164948453608,"warning":null},{"id":"152c5a0d427284e3b05fd5c7","modelId":"claude-fable-5-1","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":41.0309278350515,"warning":null},{"id":"0bee8344681eb6c5aba76cc3","modelId":"claude-fable-5-1","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":45.7731958762887,"warning":null},{"id":"c63a5aa101c5042ae00499a8","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":89.8876404494382,"warning":null},{"id":"6843d8f13eb32f436251813d","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":85.0187265917603,"warning":null},{"id":"17776df89fd155c5eb6e37a5","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":91.3857677902622,"warning":null},{"id":"003769ec709037bb79e89924","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":88.0149812734082,"warning":null},{"id":"8258b5f53b25da1e19eacdc4","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":91.01123595505621,"warning":null},{"id":"25ed925d0c2280f2ed57c925","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high","score":52.020202020202,"warning":null},{"id":"65ecf25aa32fe1f6291195b4","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low","score":40.4040404040404,"warning":null},{"id":"f2f7245010569d80dd44161a","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1","score":52.020202020202,"warning":null},{"id":"352aaae7d9ca1a02b8614131","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium","score":44.949494949495,"warning":null},{"id":"dca6ae59f27fcd98e0970afa","modelId":"claude-fable-5-1","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)","configuration":"Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","score":55.050505050505,"warning":null},{"id":"ed1a32448622df1b6e6a2c76","modelId":"claude-fable-5-1","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Claude Fable 5.1 (High)","configuration":"Claude Fable 5.1 (High); Source model ID: anthropic-claude-fable-5-1-high; 120 tasks","score":88.75,"warning":null},{"id":"e32cbb2b2e540c705e2682f4","modelId":"claude-fable-5-1","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Claude Fable 5.1 (Low)","configuration":"Claude Fable 5.1 (Low); Source model ID: anthropic-claude-fable-5-1-low; 120 tasks","score":78.33333333333333,"warning":null},{"id":"29140dd5416b42ea788cab53","modelId":"claude-fable-5-1","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"Claude Fable 5.1 (Max)","configuration":"Claude Fable 5.1 (Max); Source model ID: anthropic-claude-fable-5-1-max; 120 tasks","score":90,"warning":null},{"id":"07f22f183aad2883655252ba","modelId":"claude-fable-5-1","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Claude Fable 5.1 (Medium)","configuration":"Claude Fable 5.1 (Medium); Source model ID: anthropic-claude-fable-5-1-medium; 120 tasks","score":86.25,"warning":null},{"id":"01e39ca976d82e99ab3b9be8","modelId":"claude-fable-5-1","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"Claude Fable 5.1 (XHigh)","configuration":"Claude Fable 5.1 (XHigh); Source model ID: anthropic-claude-fable-5-1-xhigh; 120 tasks","score":90,"warning":null},{"id":"12613d0c4a993819d4dbdce2","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":15,"warning":null},{"id":"7818278bf3f2e55b20200337","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":614.13,"warning":null},{"id":"3c47d4da68b5bf084c0e9f76","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":39,"warning":null},{"id":"d6f6b975bd6c103d42d44df7","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":83.6666666666667,"warning":null},{"id":"2705174dc70afd80971d2f06","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":49.6666666666667,"warning":null},{"id":"468ce6503360afbf169e36d2","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":74.3333333333333,"warning":null},{"id":"bea6cc2230d015678cd7aa2a","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":3.248631462547438,"warning":null},{"id":"5791f8e4e8fde45e7fb66886","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":0,"warning":null},{"id":"b99ba0207b1b453a50cc06f6","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":0,"warning":null},{"id":"db86f964ce75806a4ed189c1","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":29.3942106833781,"warning":null},{"id":"2806b54519e581523aedfb18","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":3.8,"warning":null},{"id":"fcc39bdab94bc050439a0683","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":854.45,"warning":null},{"id":"d65a5ce38f7183b304600ef1","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":83.40625,"warning":null},{"id":"4d49a8d283248db5fd5e0e34","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":64.6464646464646,"warning":null},{"id":"509191a186cf539ad56147b5","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":67.1717171717172,"warning":null},{"id":"3486d7ce6fefedd596a57fcc","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":61.0508033000434,"warning":null},{"id":"ffb8c6eaab9ce5c0d4156a57","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":4.21686746987952,"warning":null},{"id":"f4ba8ec0f816cf38c66148d7","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":10.3799814643188,"warning":null},{"id":"cf094d38468fec8c0e27adb0","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":42.0408163265306,"warning":null},{"id":"4261bc632ec7f2d41fba238e","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":54.285714285714306,"warning":null},{"id":"b93459d07cc3fd00f317e844","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":27.3069679849341,"warning":null},{"id":"77e2abafe21efe47759564a5","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":51.11111111111109,"warning":null},{"id":"ad5e1bd45ba3b1854e2f521b","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":61.4814814814815,"warning":null},{"id":"6f10d5c0ef1a592623e7cd20","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":4.444444444444439,"warning":null},{"id":"0905c2c3dc408b46b86803cb","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":6.11111111111111,"warning":null},{"id":"fc24d97f80cf49b75640cc90","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":80.01163563829789,"warning":null},{"id":"acf88c56fae018e5c7c5ee48","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":75.9890292553192,"warning":null},{"id":"23ecbd3ca8a4df7f15ba1758","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":55.144508670520196,"warning":null},{"id":"aacbc7330857d739a0430710","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":58.55491329479769,"warning":null},{"id":"6cbf4db0f85b1a9026199f02","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":-7.56666666666667,"warning":null},{"id":"2da4c6c978b2c7fcd202e37f","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":-4.36666666666667,"warning":null},{"id":"e9c6fcae19f0b875efc5d431","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":14.433333333333334,"warning":null},{"id":"8862c4640b472096ac1a95b1","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":18.016666666666666,"warning":null},{"id":"a4ab94d87626afc466c301f6","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":42.2453703703704,"warning":null},{"id":"cb4ff6598c0f6e58acbeb5e6","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":32.4561403508772,"warning":null},{"id":"5067c956bfdd13d3de44ff4f","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":54.678362573099406,"warning":null},{"id":"a14c2426307d122868a12c50","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":9.27835051546392,"warning":null},{"id":"d76d253d766085ae9b980404","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Claude 4.5 Haiku (Non-reasoning)","configuration":"Claude 4.5 Haiku (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku","score":27.2727272727273,"warning":null},{"id":"d18cf2172a3d45ea811b2610","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":27.2727272727273,"warning":null},{"id":"2c85fcef255e2897eb9b9056","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":44.194756554307105,"warning":null},{"id":"64b4f035f94e078ac148dbd9","modelId":"claude-haiku-4-5-20251001","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Claude 4.5 Haiku (Reasoning)","configuration":"Claude 4.5 Haiku (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning","score":0,"warning":null},{"id":"95e92e71b76ea62d02ca6cd4","modelId":"claude-haiku-4-5-20251001","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Claude Haiku 4.5 (Thinking 32K)","configuration":"Claude Haiku 4.5 (Thinking 32K); Source model ID: claude-haiku-4-5-20251001-thinking-32k; 120 tasks","score":4.03,"warning":null},{"id":"ba3f20c5292fdd48682b2099","modelId":"claude-haiku-4-5-20251001","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Claude Haiku 4.5 (Thinking 1K)","configuration":"Claude Haiku 4.5 (Thinking 1K); Source model ID: claude-haiku-4-5-20251001-thinking-1k; 120 tasks","score":1.25,"warning":null},{"id":"e2c60a47ba43609d5f7802f0","modelId":"claude-haiku-4-5-20251001","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Claude Haiku 4.5 (Thinking 8K)","configuration":"Claude Haiku 4.5 (Thinking 8K); Source model ID: claude-haiku-4-5-20251001-thinking-8k; 120 tasks","score":1.67,"warning":null},{"id":"f4fbbe2e4e16767233d36d08","modelId":"claude-haiku-4-5-20251001","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Claude Haiku 4.5 (Thinking 16K)","configuration":"Claude Haiku 4.5 (Thinking 16K); Source model ID: claude-haiku-4-5-20251001-thinking-16k; 120 tasks","score":2.78,"warning":null},{"id":"777d836c2aab8b1a753b4fe5","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":62.66666666666671,"warning":null},{"id":"0f517ae1f51f86c35cfb0be4","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":91.3333333333333,"warning":null},{"id":"364e593f02f62ed75fd18066","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":70.6666666666667,"warning":null},{"id":"85c81b940cce2a4e217f39f1","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":77.3333333333333,"warning":null},{"id":"108fba49cb2e133b5c3292c6","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":0.28571428571428603,"warning":null},{"id":"1958b99c15a27c0d8d0aba84","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":4.57142857142857,"warning":null},{"id":"a1db7ea0ee512320711194d0","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":90.58854166666666,"warning":null},{"id":"a0e35583919bfa925e3253c4","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":91.27604166666666,"warning":null},{"id":"1db3648c4fe84e124fa696fc","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":81.010101010101,"warning":null},{"id":"ea5097c6ae66554091a20a26","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":86.5656565656566,"warning":null},{"id":"be7e6806ef9ffabbe47660e5","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":13.1603336422614,"warning":null},{"id":"c8afa47b2b589899209075fd","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":30.120481927710802,"warning":null},{"id":"555c0f000e8ee371e88e57a2","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":42.9931972789116,"warning":null},{"id":"321deea5aaf37c3322817314","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":57.959183673469404,"warning":null},{"id":"fa884eeb86cb180cbd489bac","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":73.7566137566138,"warning":null},{"id":"3b0e8231a510903a76fb9715","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":87.08994708994709,"warning":null},{"id":"5314fc9ebb9ae8bcdf75b98e","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":88.921210106383,"warning":null},{"id":"6d150283271e045da32ceab8","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":89.453125,"warning":null},{"id":"34e7fcfb97c55289d0bf4b48","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":71.2138728323699,"warning":null},{"id":"46aff7e0e196660d8e321636","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":74.0462427745665,"warning":null},{"id":"299cfb2488b1b12fb8bae121","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":-4.13333333333333,"warning":null},{"id":"06bc173078345ce534aba7f3","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":14,"warning":null},{"id":"313fe229263c5d3be7780b9b","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":40.91666666666667,"warning":null},{"id":"8667c79135a6fbe7cc5fa1e4","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":46.58333333333333,"warning":null},{"id":"993af034623aaedde3a3de9b","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":86.2573099415205,"warning":null},{"id":"08adca9aa4e2043174db9373","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":89.4736842105263,"warning":null},{"id":"42a28e056d264ff2cdaead6f","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Claude Opus 4.5 (Non-reasoning)","configuration":"Claude Opus 4.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5","score":40.9090909090909,"warning":null},{"id":"87149dbfd56c9450a6af41d4","modelId":"claude-opus-4-5-20251101","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Claude Opus 4.5 (Reasoning)","configuration":"Claude Opus 4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/claude-opus-4-5-thinking","score":46.969696969697,"warning":null},{"id":"883c249929e963c72cf44009","modelId":"claude-opus-4-6","benchmarkId":"aa-apex-agents-aa","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":33.03834808259587,"warning":null},{"id":"1df24d4a693777637b218ad1","modelId":"claude-opus-4-6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":78,"warning":null},{"id":"edea07f755a646e80b59fc5c","modelId":"claude-opus-4-6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":67,"warning":null},{"id":"1079b6e09e35fc3bf7181c3d","modelId":"claude-opus-4-6","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":12.5714285714286,"warning":null},{"id":"82d31085d8e7dd2df2cd8276","modelId":"claude-opus-4-6","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":2.84081632653061,"warning":null},{"id":"67dabb07507f3af6b80f475b","modelId":"claude-opus-4-6","benchmarkId":"aa-global-mmlu-lite","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":92.15104166666667,"warning":null},{"id":"b7837606fc0dd1e1d67c4be7","modelId":"claude-opus-4-6","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":90.64062500000001,"warning":null},{"id":"d3c5440c1476d374192760b2","modelId":"claude-opus-4-6","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":89.5959595959596,"warning":null},{"id":"3c7a4e4716cfa28abfd88e18","modelId":"claude-opus-4-6","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":84.040404040404,"warning":null},{"id":"08cc9eb85e32224bc1421970","modelId":"claude-opus-4-6","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":39.9443929564411,"warning":null},{"id":"01eba8e6568c716b434ceb9a","modelId":"claude-opus-4-6","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":19.0917516218721,"warning":null},{"id":"a199353fd286c627af757e1a","modelId":"claude-opus-4-6","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":53.1292517006803,"warning":null},{"id":"819fa99734059e55c305dfb1","modelId":"claude-opus-4-6","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":44.6258503401361,"warning":null},{"id":"3f8d701703320627812d694d","modelId":"claude-opus-4-6","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":75.4335260115607,"warning":null},{"id":"97a5c4bf360e00751e6fa217","modelId":"claude-opus-4-6","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":72.5433526011561,"warning":null},{"id":"67766ea16f853c7ff84a817a","modelId":"claude-opus-4-6","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":13.6666666666667,"warning":null},{"id":"46b85c1426a94560e8491464","modelId":"claude-opus-4-6","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":2.36666666666667,"warning":null},{"id":"668e62a5d42e2bef73937cce","modelId":"claude-opus-4-6","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":46.983333333333334,"warning":null},{"id":"baa04b456361440058325f0b","modelId":"claude-opus-4-6","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":45.78333333333333,"warning":null},{"id":"63d40fb93f723399e39df0a3","modelId":"claude-opus-4-6","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":92.1052631578947,"warning":null},{"id":"b9a0b73f4ddc5a887e70736a","modelId":"claude-opus-4-6","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":84.7953216374269,"warning":null},{"id":"c239c04b17c69baedb9f629a","modelId":"claude-opus-4-6","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6-adaptive","score":46.2121212121212,"warning":null},{"id":"e3fe5100a1b70dc45580f44b","modelId":"claude-opus-4-6","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Claude Opus 4.6 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-6","score":48.4848484848485,"warning":null},{"id":"3da84ad297936aa3afed7671","modelId":"claude-opus-4-6","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Claude Opus 4.6 (120K, High)","configuration":"Claude Opus 4.6 (120K, High); Source model ID: claude-opus-4-6-thinking-120K-high; 120 tasks","score":69.17,"warning":null},{"id":"cc808875c949319a9c28aeb4","modelId":"claude-opus-4-6","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Claude Opus 4.6 (120K, Low)","configuration":"Claude Opus 4.6 (120K, Low); Source model ID: claude-opus-4-6-thinking-120K-low; 120 tasks","score":64.58,"warning":null},{"id":"d89c7fdc274f08893e4629d1","modelId":"claude-opus-4-6","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"Claude Opus 4.6 (120K, Max)","configuration":"Claude Opus 4.6 (120K, Max); Source model ID: claude-opus-4-6-thinking-120K-max; 120 tasks","score":68.75,"warning":null},{"id":"06f217cc8cc75c7a1ed581a5","modelId":"claude-opus-4-6","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Claude Opus 4.6 (120K, Medium)","configuration":"Claude Opus 4.6 (120K, Medium); Source model ID: claude-opus-4-6-thinking-120K-medium; 120 tasks","score":66.25,"warning":null},{"id":"f95de089dfd26220d76b06bd","modelId":"claude-opus-4-6","benchmarkId":"swepro-minisweagentstarredrows","level":"thinking","sourceLabel":"claude-opus-4-6 (thinking)*","configuration":"claude-opus-4-6 (thinking)*; 731 tasks; source date 2026-04-08","score":51.9,"warning":null},{"id":"3d191d0319c4a21ff3c9f3e0","modelId":"claude-opus-4-7","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":43.75,"warning":null},{"id":"d97fa34c6d74197e5651c44d","modelId":"claude-opus-4-7","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":1251.5,"warning":null},{"id":"091e5cb1037fed300fe45855","modelId":"claude-opus-4-7","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":1071.03,"warning":null},{"id":"b0cb265c650fe3cdc983ffe8","modelId":"claude-opus-4-7","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":78.6666666666667,"warning":null},{"id":"d44e895b9101241914947dee","modelId":"claude-opus-4-7","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":75.6666666666667,"warning":null},{"id":"2683b9293f59efe8aa064de8","modelId":"claude-opus-4-7","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":12,"warning":null},{"id":"89994a0a4f9540721a978124","modelId":"claude-opus-4-7","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":5.14285714285714,"warning":null},{"id":"c8ead59f49e97a9f171599fc","modelId":"claude-opus-4-7","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":1395.78,"warning":null},{"id":"9c82836191e21678e7e1d886","modelId":"claude-opus-4-7","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":91.4141414141414,"warning":null},{"id":"dddb3b75d1a29c96c9cd5fab","modelId":"claude-opus-4-7","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":88.4848484848485,"warning":null},{"id":"af98b790618965ff81b8c93c","modelId":"claude-opus-4-7","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":42.3076923076923,"warning":null},{"id":"05438d532cb2f9dd8da92413","modelId":"claude-opus-4-7","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":33.3178869323448,"warning":null},{"id":"af7b2396e18ba580ebda89a3","modelId":"claude-opus-4-7","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":58.6394557823129,"warning":null},{"id":"7a319b3c96aa5cc4abdee521","modelId":"claude-opus-4-7","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":43.6054421768707,"warning":null},{"id":"8700e3e2f9d7fafb7c78712f","modelId":"claude-opus-4-7","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":46.6572504708098,"warning":null},{"id":"f6035dc69613ed9a74dd7118","modelId":"claude-opus-4-7","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":28.888888888888896,"warning":null},{"id":"f1ea4bf0714b2256e0cabb78","modelId":"claude-opus-4-7","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":78.8439306358382,"warning":null},{"id":"26ce26f97e9518e71d17a846","modelId":"claude-opus-4-7","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":76.35838150289021,"warning":null},{"id":"032009afa3dbd206c24621a1","modelId":"claude-opus-4-7","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":27.2666666666667,"warning":null},{"id":"0fec6d78078202d2ff626c29","modelId":"claude-opus-4-7","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":14.8333333333333,"warning":null},{"id":"ef24af42f560d182356c45d7","modelId":"claude-opus-4-7","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":48.88333333333333,"warning":null},{"id":"78c91c33a4b44b6c86d050ba","modelId":"claude-opus-4-7","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":44.733333333333334,"warning":null},{"id":"154a39d23fcfec07f4dba3e9","modelId":"claude-opus-4-7","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":88.59649122807019,"warning":null},{"id":"9e814f42f29863fa0d0aafd9","modelId":"claude-opus-4-7","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":73.9766081871345,"warning":null},{"id":"227305481fdd337950a1ec37","modelId":"claude-opus-4-7","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":34.639175257732,"warning":null},{"id":"bbf9b4814fb13eef00b601a7","modelId":"claude-opus-4-7","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":51.5151515151515,"warning":null},{"id":"99a7a4ac71a72c0520740983","modelId":"claude-opus-4-7","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Claude Opus 4.7 (Non-reasoning, High Effort)","configuration":"Claude Opus 4.7 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning","score":54.5454545454545,"warning":null},{"id":"0461d2eb2969cf81f0a93ea2","modelId":"claude-opus-4-7","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.7 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-7","score":83.1460674157303,"warning":null},{"id":"da713bbecda4ed9bb6e4575a","modelId":"claude-opus-4-7","benchmarkId":"terminal-claudecode","level":"max","sourceLabel":"Opus 4.7","configuration":"Opus 4.7; Reported effort: max; 447 trials; recorded 2026-04-16","score":68.9,"warning":null},{"id":"f1a9e8085f72db6bccf6962b","modelId":"claude-opus-4-7","benchmarkId":"terminal-terminus2","level":"max","sourceLabel":"Opus 4.7","configuration":"Opus 4.7; Reported effort: max; 445 trials; recorded 2026-04-16","score":66.07,"warning":null},{"id":"38bd39336f87942a65930af7","modelId":"claude-opus-4-8","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":45,"warning":null},{"id":"96e07d2acdac72606809adc6","modelId":"claude-opus-4-8","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":1315.95,"warning":null},{"id":"396c304045bfd21fed6494cd","modelId":"claude-opus-4-8","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":77.6666666666667,"warning":null},{"id":"55ab6f2bb1306e9de5b5cf55","modelId":"claude-opus-4-8","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":45.59343691527719,"warning":null},{"id":"9baeb1c807742dfa60b68f32","modelId":"claude-opus-4-8","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":20.8571428571429,"warning":null},{"id":"dbd34afbb3a236f1e52c05d8","modelId":"claude-opus-4-8","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":43.957027752909575,"warning":null},{"id":"67f24e326dc157af68bba59f","modelId":"claude-opus-4-8","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":22.8,"warning":null},{"id":"2d430d708739c1838a86ee01","modelId":"claude-opus-4-8","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":1489.04,"warning":null},{"id":"19d5c01029e87cfc22eb0792","modelId":"claude-opus-4-8","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":92.020202020202,"warning":null},{"id":"9e9513aec83ed5c426771c7a","modelId":"claude-opus-4-8","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":91.0840932117528,"warning":null},{"id":"837eed14d5abe653526f9c1e","modelId":"claude-opus-4-8","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":48.6561631139944,"warning":null},{"id":"f68d5f7125d6078981d1cdc8","modelId":"claude-opus-4-8","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":62.244897959183696,"warning":null},{"id":"d4440269bce8cda5310d406c","modelId":"claude-opus-4-8","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":45.5555555555556,"warning":null},{"id":"e2f0cc5a86febfa51defe5db","modelId":"claude-opus-4-8","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":28.75,"warning":null},{"id":"1e3ca5abae432a2e5870be34","modelId":"claude-opus-4-8","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":48.833333333333336,"warning":null},{"id":"fa9718cf977935383075b2e2","modelId":"claude-opus-4-8","benchmarkId":"aa-scicode","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":54.398148148148195,"warning":null},{"id":"5e87020b9d0c264608d5c3e5","modelId":"claude-opus-4-8","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":94.4444444444445,"warning":null},{"id":"02cceeaa14a76c764ac377f1","modelId":"claude-opus-4-8","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":34.226804123711304,"warning":null},{"id":"3ee92943d34643e7c8109127","modelId":"claude-opus-4-8","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":58.3333333333333,"warning":null},{"id":"09b44ba8a082ec541fdf76c6","modelId":"claude-opus-4-8","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":84.6441947565543,"warning":null},{"id":"e6bc38ad1655069ba484c206","modelId":"claude-opus-4-8","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 4.8 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-4-8","score":21.7171717171717,"warning":null},{"id":"b5c453e45d5a65111bf8c8fc","modelId":"claude-opus-4-8","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Claude Opus 4.8 (High)","configuration":"Claude Opus 4.8 (High); Source model ID: anthropic-opus-4-8-high; 120 tasks","score":72.08,"warning":null},{"id":"7609122fbb5f21e0336fd79d","modelId":"claude-opus-4-8","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Claude Opus 4.8 (Low)","configuration":"Claude Opus 4.8 (Low); Source model ID: anthropic-opus-4-8-low; 120 tasks","score":62.22,"warning":null},{"id":"099afb744367e0027cb4beb0","modelId":"claude-opus-4-8","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Claude Opus 4.8 (Medium)","configuration":"Claude Opus 4.8 (Medium); Source model ID: anthropic-opus-4-8-medium; 120 tasks","score":71.67,"warning":null},{"id":"3ed225cfbd8da4a68cb773eb","modelId":"claude-opus-4-8","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"claude-opus-4-8","configuration":"claude-opus-4-8; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":51.8,"warning":null},{"id":"6529363c938719d7a1e4c752","modelId":"claude-opus-4-8","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"claude-opus-4-8","configuration":"claude-opus-4-8; Reported effort: low; 113 unique tasks; 451 attempts; 4 runs","score":40.8,"warning":null},{"id":"8158b49aa1444c7311339716","modelId":"claude-opus-4-8","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"claude-opus-4-8","configuration":"claude-opus-4-8; Reported effort: max; 111 unique tasks; 429 attempts; 4 runs","score":59,"warning":"Incomplete task coverage: 111 of 113 tasks. A common task set is required for ranking."},{"id":"00b724564a3c562424e7d7ee","modelId":"claude-opus-4-8","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"claude-opus-4-8","configuration":"claude-opus-4-8; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs","score":48.7,"warning":null},{"id":"c0c9ff5a707bf93dda7c0ef5","modelId":"claude-opus-4-8","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"claude-opus-4-8","configuration":"claude-opus-4-8; Reported effort: xhigh; 113 unique tasks; 447 attempts; 4 runs","score":54.4,"warning":null},{"id":"766dde2b58473794011e3786","modelId":"claude-opus-4-8","benchmarkId":"terminal-claudecode","level":"high","sourceLabel":"Opus 4.8","configuration":"Opus 4.8; Reported effort: high; 445 trials; recorded 2026-05-28","score":78.88,"warning":null},{"id":"5c56287d7e5765c02c88c155","modelId":"claude-opus-5","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":53.75,"warning":null},{"id":"2acbc319f9ca38c18ec3a259","modelId":"claude-opus-5","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":1556.66,"warning":null},{"id":"1414f305685da0868a45a66a","modelId":"claude-opus-5","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":1215.73,"warning":null},{"id":"6ccf007b68cbfb59bf9c8252","modelId":"claude-opus-5","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":1644.9,"warning":null},{"id":"442707c1f2c89460f6d3ca4a","modelId":"claude-opus-5","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":1439.04,"warning":null},{"id":"0d9fc3bf92bd9d13a3f094ea","modelId":"claude-opus-5","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":1624.56,"warning":null},{"id":"5b22e582a3c8e14d92be4915","modelId":"claude-opus-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":79,"warning":null},{"id":"e5132af703da957e07672d06","modelId":"claude-opus-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":81.3333333333333,"warning":null},{"id":"24a003a38836b7cca709a4c0","modelId":"claude-opus-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":79.3333333333333,"warning":null},{"id":"2570efa51639dcd9b893a408","modelId":"claude-opus-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":82,"warning":null},{"id":"bc4f79530a6ea4de4924d3bf","modelId":"claude-opus-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":80.3333333333333,"warning":null},{"id":"a177fa122a0704fa26e22ecf","modelId":"claude-opus-5","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":53.56401051539629,"warning":null},{"id":"ae356140a8fb0176655f86d3","modelId":"claude-opus-5","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":51.79066298700786,"warning":null},{"id":"c74b70fe0573557faa90b030","modelId":"claude-opus-5","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":56.57355576493251,"warning":null},{"id":"5c641df41d523e8929af62e4","modelId":"claude-opus-5","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":54.33925431990897,"warning":null},{"id":"172013119105d4051f909884","modelId":"claude-opus-5","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":53.21919210948297,"warning":null},{"id":"1f8ef1151d05deff6991bece","modelId":"claude-opus-5","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":28.2857142857143,"warning":null},{"id":"b4d4ab463a8327175663102e","modelId":"claude-opus-5","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":23.1428571428571,"warning":null},{"id":"11e328c7711c66ea215224ef","modelId":"claude-opus-5","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":29.1428571428571,"warning":null},{"id":"62da1cce8a6cf73f3672b9e9","modelId":"claude-opus-5","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":26.8571428571429,"warning":null},{"id":"2c36f895ea5cbdcebdf9c59d","modelId":"claude-opus-5","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":27.7142857142857,"warning":null},{"id":"f0bc6fe30fabbdc0ca3994ed","modelId":"claude-opus-5","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":47.4783646672635,"warning":null},{"id":"e2c1cac9115a42116304eb4f","modelId":"claude-opus-5","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":19.6,"warning":null},{"id":"3596daa06314edef2be5527a","modelId":"claude-opus-5","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":17.2,"warning":null},{"id":"c151f6e613c9f67b13f406ab","modelId":"claude-opus-5","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":21.6,"warning":null},{"id":"291f2f1bdb22c81ab94d05b1","modelId":"claude-opus-5","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":20,"warning":null},{"id":"4e9076fe72580ca484849f73","modelId":"claude-opus-5","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":21,"warning":null},{"id":"dcd761cff60d797b91471d68","modelId":"claude-opus-5","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":1628.94,"warning":null},{"id":"e48970372d521599be694114","modelId":"claude-opus-5","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":1371.52,"warning":null},{"id":"2ee14965b98c9860ecdfda01","modelId":"claude-opus-5","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":1735.09,"warning":null},{"id":"f05f223070de2c4dc322b132","modelId":"claude-opus-5","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":1524.87,"warning":null},{"id":"c8dd90d8b9eba1233eda9dcc","modelId":"claude-opus-5","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":1708.14,"warning":null},{"id":"006b1964b4c677ae98cd2b1a","modelId":"claude-opus-5","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":93.7373737373737,"warning":null},{"id":"8dcd39578d24b8c83c91a5fd","modelId":"claude-opus-5","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":88.8888888888889,"warning":null},{"id":"1e79f74f121b0c6c0e762121","modelId":"claude-opus-5","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":93.2323232323232,"warning":null},{"id":"1f113838bc0b1f8c607b1a4b","modelId":"claude-opus-5","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":91.9191919191919,"warning":null},{"id":"b2626ffcb9a36bdfd69bb332","modelId":"claude-opus-5","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":93.7373737373737,"warning":null},{"id":"190d3154d65bcd070a046533","modelId":"claude-opus-5","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":93.457808655377,"warning":null},{"id":"36dff2620079957f2cf44006","modelId":"claude-opus-5","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":52.8266913809083,"warning":null},{"id":"0a3a02e52af1195826001ee7","modelId":"claude-opus-5","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":43.4198331788693,"warning":null},{"id":"6ea79ab29bbd3b2b3a79eb04","modelId":"claude-opus-5","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":54.8656163113994,"warning":null},{"id":"c6fa27919bb5bb2fad17c59d","modelId":"claude-opus-5","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":51.29749768303981,"warning":null},{"id":"b4e0fe498e9b3dfbf28688c0","modelId":"claude-opus-5","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":54.40222428174239,"warning":null},{"id":"efca67f8cab27166f2aca5bc","modelId":"claude-opus-5","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":59.4444444444444,"warning":null},{"id":"6111e4573ab8476970cca681","modelId":"claude-opus-5","benchmarkId":"aa-mlcr-aa","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":53.8888888888889,"warning":null},{"id":"14e148b786d25d0b58bdc6e0","modelId":"claude-opus-5","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":55.5555555555556,"warning":null},{"id":"1085b20d5dbf474ef852eea7","modelId":"claude-opus-5","benchmarkId":"aa-mlcr-aa","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":56.1111111111111,"warning":null},{"id":"0f5d2c4f3fe25d144e09034d","modelId":"claude-opus-5","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":58.3333333333333,"warning":null},{"id":"4c5638fe71f88682a29658e9","modelId":"claude-opus-5","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":82.4277456647399,"warning":null},{"id":"d2aac50aef97fb04e4297e03","modelId":"claude-opus-5","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":79.8265895953757,"warning":null},{"id":"47c3aa23cc920ea643f444d8","modelId":"claude-opus-5","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":84.7398843930636,"warning":null},{"id":"efef35ac11fb92942609d0d0","modelId":"claude-opus-5","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":81.6184971098266,"warning":null},{"id":"7e96ad605e9106c9bdf8db4f","modelId":"claude-opus-5","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":83.9884393063584,"warning":null},{"id":"6142b61150b247770757b261","modelId":"claude-opus-5","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":33.7166666666667,"warning":null},{"id":"ca4fe51d6a460da93435b44d","modelId":"claude-opus-5","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":28.55,"warning":null},{"id":"8aebe6222eb321d01c1e6248","modelId":"claude-opus-5","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":37.0666666666667,"warning":null},{"id":"95767f397055c93498b7aab3","modelId":"claude-opus-5","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":31.0166666666667,"warning":null},{"id":"87c811d366c5fbaaaa3975bc","modelId":"claude-opus-5","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":35.3833333333333,"warning":null},{"id":"6d975dae9df671005980ecfe","modelId":"claude-opus-5","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":58.88333333333333,"warning":null},{"id":"adb649862ee1cae5791cabe7","modelId":"claude-opus-5","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":55.95,"warning":null},{"id":"edcfcac8042bda56dd69b89d","modelId":"claude-opus-5","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":60.86666666666667,"warning":null},{"id":"e4650a9f4c7f76ae664f13c2","modelId":"claude-opus-5","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":57.06666666666666,"warning":null},{"id":"1dda745c989251a13a81b6fc","modelId":"claude-opus-5","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":59.5,"warning":null},{"id":"40cdc1072dabab9b4c857204","modelId":"claude-opus-5","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":55.4398148148148,"warning":null},{"id":"36099057e38dc95fa8ab5f47","modelId":"claude-opus-5","benchmarkId":"aa-scicode","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":49.189814814814795,"warning":null},{"id":"dbede154e31777d84a3eb6e1","modelId":"claude-opus-5","benchmarkId":"aa-scicode","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":56.3657407407407,"warning":null},{"id":"1acb4b14ade97952b30ef0ce","modelId":"claude-opus-5","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":51.5046296296296,"warning":null},{"id":"807a399d7233df30a7358e46","modelId":"claude-opus-5","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":55.671296296296305,"warning":null},{"id":"1b768b05eb73f6ddd5a4b833","modelId":"claude-opus-5","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":44.7422680412371,"warning":null},{"id":"9632912356d7829b44d8bc4d","modelId":"claude-opus-5","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":30.309278350515502,"warning":null},{"id":"b0193783b1bb63fe4754172d","modelId":"claude-opus-5","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":42.0618556701031,"warning":null},{"id":"d9b5f13b89dbfd47519f2e2f","modelId":"claude-opus-5","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":38.5567010309278,"warning":null},{"id":"0dd542a8bb903e6ff2c5502f","modelId":"claude-opus-5","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":43.298969072165,"warning":null},{"id":"a1d00a56700fde6178cfc616","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":87.6404494382023,"warning":null},{"id":"bc03dd79445442141592d089","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":76.4044943820225,"warning":null},{"id":"3d3ed199a4eea5302ce0af04","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":89.1385767790262,"warning":null},{"id":"c3200a107ccc03d4b7807ba8","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":86.1423220973783,"warning":null},{"id":"5818ec32a44269e63adf0105","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":88.0149812734082,"warning":null},{"id":"ed71d135daea16e33ab93a9f","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-high","score":45.959595959596,"warning":null},{"id":"bdc81d0dc6d9e8e2e5473d75","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-low","score":26.2626262626263,"warning":null},{"id":"b1ddf5e6fac2438349cc72b8","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5","score":48.989898989899,"warning":null},{"id":"d7f1b2b1e77d957a1e5dc41d","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-medium","score":34.343434343434296,"warning":null},{"id":"1e93aba2ffcc3b81a912dc2c","modelId":"claude-opus-5","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-opus-5-xhigh","score":46.4646464646465,"warning":null},{"id":"ee2fdd53366196c1c9cdaf3a","modelId":"claude-opus-5","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Claude Opus 5 (High)","configuration":"Claude Opus 5 (High); Source model ID: anthropic-claude-opus-5-high; 120 tasks","score":88.33,"warning":null},{"id":"48b4a19317b73c4a3f407097","modelId":"claude-opus-5","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"Claude Opus 5 (Max)","configuration":"Claude Opus 5 (Max); Source model ID: anthropic-claude-opus-5-max; 120 tasks","score":90.42,"warning":null},{"id":"e57e43848926eef736a897ba","modelId":"claude-opus-5","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"claude-opus-5","configuration":"claude-opus-5; Reported effort: high; 113 unique tasks; 449 attempts; 4 runs","score":72.8,"warning":null},{"id":"f6a6f991a9a99441b39a26ca","modelId":"claude-opus-5","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"claude-opus-5","configuration":"claude-opus-5; Reported effort: low; 113 unique tasks; 449 attempts; 4 runs","score":58.1,"warning":null},{"id":"a0003347b8421c764d77ca4a","modelId":"claude-opus-5","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"claude-opus-5","configuration":"claude-opus-5; Reported effort: max; 113 unique tasks; 444 attempts; 4 runs","score":73.6,"warning":null},{"id":"0298f83d2256dcf2b5ed6e3f","modelId":"claude-opus-5","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"claude-opus-5","configuration":"claude-opus-5; Reported effort: medium; 113 unique tasks; 447 attempts; 4 runs","score":68.9,"warning":null},{"id":"d138eb10af8dd2cacd7a504a","modelId":"claude-opus-5","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"claude-opus-5","configuration":"claude-opus-5; Reported effort: xhigh; 113 unique tasks; 447 attempts; 4 runs","score":73.2,"warning":null},{"id":"e11780747804a9ec05171e61","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":711.96,"warning":null},{"id":"8a159d4fef16041d56762dd8","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":37,"warning":null},{"id":"de1e01647292e9102ed45aa0","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":88,"warning":null},{"id":"674b1c581fa7dd12ee0b66cc","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":54,"warning":null},{"id":"db806a12c42b98a164ee977d","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":72.3333333333333,"warning":null},{"id":"1774a54d662320565d170e76","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":14.075743049062714,"warning":null},{"id":"34d2f64ecde456514b2e2710","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":0,"warning":null},{"id":"4a36ccc9c0f665a4b53b1d6b","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":1.1428571428571401,"warning":null},{"id":"1016ec1494cf8458139671e2","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":5.2,"warning":null},{"id":"82cb4bb8edab7333e450a2c5","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":989.26,"warning":null},{"id":"8f403f5bd47ca2833fc80bf0","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":89.25520833333334,"warning":null},{"id":"2b31de44a316fc16fda8177e","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":72.72727272727269,"warning":null},{"id":"df5144f0bc3dfefc0a136256","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":83.4343434343434,"warning":null},{"id":"f783eb29b70679064120eaa9","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":7.228915662650599,"warning":null},{"id":"c60e757ef68afcde43a56bc8","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":17.7942539388323,"warning":null},{"id":"e9b0ce7d16a5006a78eca66c","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":42.653061224489804,"warning":null},{"id":"752154fc7bb6ab5b9437f3c3","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":57.2789115646258,"warning":null},{"id":"7076314c6b18338bfa363af1","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":59.047619047619,"warning":null},{"id":"6c9293e23e64f29131b3d278","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":71.4285714285714,"warning":null},{"id":"40bbe6df11b8de4e7657ecca","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":85.9873670212766,"warning":null},{"id":"266d8dc9f86ccb95c6645fa9","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":87.4501329787234,"warning":null},{"id":"b3c0845808f574dbc704d157","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":65.2023121387283,"warning":null},{"id":"3e0d99a12bb7de08ad26556c","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":68.728323699422,"warning":null},{"id":"c712e425b0902b25a4bca75e","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":-9.36666666666667,"warning":null},{"id":"3efd3c04564d707cb7af0c5c","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":-0.0833333333333333,"warning":null},{"id":"5d5aed22ee29eec8262d15fa","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":28.383333333333333,"warning":null},{"id":"9e508c8c6b578671ad893039","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":32.86666666666667,"warning":null},{"id":"843d8eff7e70d1387558ec55","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":45.717592592592595,"warning":null},{"id":"d0a93edeaedf53b41d00dbd3","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":70.4678362573099,"warning":null},{"id":"6722be7d2b55c374d9bb637c","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":78.07017543859651,"warning":null},{"id":"f9f243e03759b358a57a4007","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":24.5360824742268,"warning":null},{"id":"6535f19e64380503ae7e87fe","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Claude 4.5 Sonnet (Non-reasoning)","configuration":"Claude 4.5 Sonnet (Non-reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet","score":28.7878787878788,"warning":null},{"id":"4e1797d1fb9ba82a6999f801","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":35.6060606060606,"warning":null},{"id":"bac4143f9a745d98bfeb22e4","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":55.805243445692895,"warning":null},{"id":"1f78303c3188cf807ba58ec0","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Claude 4.5 Sonnet (Reasoning)","configuration":"Claude 4.5 Sonnet (Reasoning); Model source: https://artificialanalysis.ai/models/claude-4-5-sonnet-thinking","score":0,"warning":null},{"id":"3f070c56f3e96293b3502873","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Claude Sonnet 4.5 (Thinking 32K)","configuration":"Claude Sonnet 4.5 (Thinking 32K); Source model ID: claude-sonnet-4-5-20250929-thinking-32k; 120 tasks","score":13.61,"warning":null},{"id":"54de588ab99dc61e79aad8e5","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Claude Sonnet 4.5 (Thinking 16K)","configuration":"Claude Sonnet 4.5 (Thinking 16K); Source model ID: claude-sonnet-4-5-20250929-thinking-16k; 120 tasks","score":6.94,"warning":null},{"id":"e513347234a010f067c79909","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Claude Sonnet 4.5 (Thinking 1K)","configuration":"Claude Sonnet 4.5 (Thinking 1K); Source model ID: claude-sonnet-4-5-20250929-thinking-1k; 120 tasks","score":5.83,"warning":null},{"id":"e78c77d5cf9767ea4f53df60","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Claude Sonnet 4.5 (Thinking 8K)","configuration":"Claude Sonnet 4.5 (Thinking 8K); Source model ID: claude-sonnet-4-5-20250929-thinking-8k; 120 tasks","score":6.94,"warning":null},{"id":"e332f1b2228e9266a71d05ad","modelId":"claude-sonnet-4-6","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":20,"warning":null},{"id":"d3ee41fb89c6ccb1e66adf8f","modelId":"claude-sonnet-4-6","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":1065.11,"warning":null},{"id":"2b93039d4563fe3b157d15d5","modelId":"claude-sonnet-4-6","benchmarkId":"aa-apex-agents-aa","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":28.023598820058996,"warning":null},{"id":"2d8faf0c2e0685f2c87902f3","modelId":"claude-sonnet-4-6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":80,"warning":null},{"id":"95567387bc84bd43e2e17443","modelId":"claude-sonnet-4-6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":68.3333333333333,"warning":null},{"id":"eeca2c029f49887d2f8de42c","modelId":"claude-sonnet-4-6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":69.3333333333333,"warning":null},{"id":"8fec0dac751edaf179a65615","modelId":"claude-sonnet-4-6","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":20.098073664518367,"warning":null},{"id":"5f405b80c050b037ebb56264","modelId":"claude-sonnet-4-6","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":3.14285714285714,"warning":null},{"id":"2a850dc6ae782aabcb69a92e","modelId":"claude-sonnet-4-6","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":0.857142857142857,"warning":null},{"id":"754ae6038c192fcc20e15317","modelId":"claude-sonnet-4-6","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":0.857142857142857,"warning":null},{"id":"dab21af4216ac279722b33bf","modelId":"claude-sonnet-4-6","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":15.8,"warning":null},{"id":"aa8db74b95a531e6228d4cdb","modelId":"claude-sonnet-4-6","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":1295.41,"warning":null},{"id":"8d6261c518f3a5cb2d3aa799","modelId":"claude-sonnet-4-6","benchmarkId":"aa-global-mmlu-lite","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":90.484375,"warning":null},{"id":"68cd3fa6809265041ab4e058","modelId":"claude-sonnet-4-6","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":88.23958333333333,"warning":null},{"id":"bac7982cd94b783ce9937b37","modelId":"claude-sonnet-4-6","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":89.23958333333334,"warning":null},{"id":"6ee50ff3940f843b316a11ca","modelId":"claude-sonnet-4-6","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":87.4747474747475,"warning":null},{"id":"9faede113e168f7e102e28b7","modelId":"claude-sonnet-4-6","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":79.8989898989899,"warning":null},{"id":"bd9dc8c11e74dcf4d21c0355","modelId":"claude-sonnet-4-6","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":79.6969696969697,"warning":null},{"id":"451dd11af5aa03b51c7df735","modelId":"claude-sonnet-4-6","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":85.97481545809809,"warning":null},{"id":"0e5f7bf21fd13c70b5963400","modelId":"claude-sonnet-4-6","benchmarkId":"aa-harvey-lab-aa","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":84.4405847445361,"warning":null},{"id":"b7ef923a70da041c042f467c","modelId":"claude-sonnet-4-6","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":33.595922150139,"warning":null},{"id":"08964d53879fda33454d92be","modelId":"claude-sonnet-4-6","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":13.3456904541242,"warning":null},{"id":"fbaf3e468a069edc24595e53","modelId":"claude-sonnet-4-6","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":11.2140871177016,"warning":null},{"id":"5802b72f96fd2bc36b68b3b6","modelId":"claude-sonnet-4-6","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":56.5986394557823,"warning":null},{"id":"7b9a5ed9afd89f3d3dc7c7d9","modelId":"claude-sonnet-4-6","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":41.156462585034,"warning":null},{"id":"cb52c6337e6d1ca83f782771","modelId":"claude-sonnet-4-6","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":42.3809523809524,"warning":null},{"id":"e75ab74cf5a997095d1f3380","modelId":"claude-sonnet-4-6","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":39.8022598870057,"warning":null},{"id":"a7f4aba36323901ba9da5ab4","modelId":"claude-sonnet-4-6","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":24.4444444444444,"warning":null},{"id":"53a70f8e8f39a9bf4b309039","modelId":"claude-sonnet-4-6","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":20.5555555555556,"warning":null},{"id":"b302bedcd3669528b4703126","modelId":"claude-sonnet-4-6","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":20,"warning":null},{"id":"2753a36a2d9898ee83a2c7e0","modelId":"claude-sonnet-4-6","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":73.2947976878613,"warning":null},{"id":"0eab8dfd0579ff09141f58f1","modelId":"claude-sonnet-4-6","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":70.5780346820809,"warning":null},{"id":"c9790672cda25468a59d855a","modelId":"claude-sonnet-4-6","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":69.19075144508669,"warning":null},{"id":"2b79a8be3c4816ae5e4126d1","modelId":"claude-sonnet-4-6","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":12.2166666666667,"warning":null},{"id":"3c8824c30ba25df9377473e9","modelId":"claude-sonnet-4-6","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":-2.1,"warning":null},{"id":"8ff03bd6cf18ff4fdd035fca","modelId":"claude-sonnet-4-6","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":-3.55,"warning":null},{"id":"cef67cc03b37e5d955687879","modelId":"claude-sonnet-4-6","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":40.86666666666667,"warning":null},{"id":"089295a829a4b2eea0c45567","modelId":"claude-sonnet-4-6","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":36.516666666666666,"warning":null},{"id":"524488ae2a2507b68ea71d3d","modelId":"claude-sonnet-4-6","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":38.550000000000004,"warning":null},{"id":"af900336d45849b431b9cad3","modelId":"claude-sonnet-4-6","benchmarkId":"aa-scicode","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":50.1157407407407,"warning":null},{"id":"b286a9e0d17ba5da81669d3e","modelId":"claude-sonnet-4-6","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":75.7309941520468,"warning":null},{"id":"4f4c2f07253b00381b8a7e93","modelId":"claude-sonnet-4-6","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":79.5321637426901,"warning":null},{"id":"687f063bf51789c89c7d6efd","modelId":"claude-sonnet-4-6","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":78.9473684210526,"warning":null},{"id":"3f305729d1c2d29db2f9101c","modelId":"claude-sonnet-4-6","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":34.4329896907216,"warning":null},{"id":"0e7ecd187c6d64aaaf7a121c","modelId":"claude-sonnet-4-6","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":53.030303030303,"warning":null},{"id":"382f610161294070630b7fc4","modelId":"claude-sonnet-4-6","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, Low Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort","score":42.4242424242424,"warning":null},{"id":"cb333ca12130594126273d1d","modelId":"claude-sonnet-4-6","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Claude Sonnet 4.6 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 4.6 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6","score":46.2121212121212,"warning":null},{"id":"e9118d28b3767fb3d536c9bc","modelId":"claude-sonnet-4-6","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":71.1610486891386,"warning":null},{"id":"87726611ca55ead407ddd84c","modelId":"claude-sonnet-4-6","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-4-6-adaptive","score":3.03030303030303,"warning":null},{"id":"3fc5dd5ad41a965cc918cdf2","modelId":"claude-sonnet-4-6","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Claude Sonnet 4.6 (High)","configuration":"Claude Sonnet 4.6 (High); Source model ID: claude_sonnet_4_6_high; 120 tasks","score":60.419999999999995,"warning":null},{"id":"d1a628a019bde02cfbdacf5e","modelId":"claude-sonnet-4-6","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"Claude Sonnet 4.6 (Max)","configuration":"Claude Sonnet 4.6 (Max); Source model ID: claude_sonnet_4_6_max; 120 tasks","score":58.330000000000005,"warning":null},{"id":"46adf8595dc3ea458bbcbb0e","modelId":"claude-sonnet-4-6","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"claude-sonnet-4-6","configuration":"claude-sonnet-4-6; Reported effort: high; 113 unique tasks; 451 attempts; 4 runs","score":29.9,"warning":null},{"id":"6347d0311c4338a42a89d14a","modelId":"claude-sonnet-5","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":46.25,"warning":null},{"id":"104c2fa41680303d6bba8b0c","modelId":"claude-sonnet-5","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":1177.84,"warning":null},{"id":"a6f2b88cedc6459b29218831","modelId":"claude-sonnet-5","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":927.41,"warning":null},{"id":"a8e9b0de20e17f4fd8b19fbd","modelId":"claude-sonnet-5","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":1355.19,"warning":null},{"id":"a721729fc0a05c76dba80f20","modelId":"claude-sonnet-5","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":1053.88,"warning":null},{"id":"c7f24f53024297ef7abf92a3","modelId":"claude-sonnet-5","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":1273.41,"warning":null},{"id":"5bb50542a24a257e4eb3f124","modelId":"claude-sonnet-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":76.6666666666667,"warning":null},{"id":"c33097b0dfb2fdab394c3c95","modelId":"claude-sonnet-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":67.3333333333333,"warning":null},{"id":"02ea645c2f24a2c80752751f","modelId":"claude-sonnet-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":82,"warning":null},{"id":"db04c5bca2ef3de0f3a096e1","modelId":"claude-sonnet-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":73.6666666666667,"warning":null},{"id":"3360c18e5bed782425bb787c","modelId":"claude-sonnet-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":70,"warning":null},{"id":"9fd4bde44ff9666411635d25","modelId":"claude-sonnet-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":76.6666666666667,"warning":null},{"id":"d8b899f7952e43c80d07ab79","modelId":"claude-sonnet-5","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":32.0966388143804,"warning":null},{"id":"85c0183e354cdd4caf89d750","modelId":"claude-sonnet-5","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":19.90193656897387,"warning":null},{"id":"99219b85ea67436dd032d3d6","modelId":"claude-sonnet-5","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":36.51267571703639,"warning":null},{"id":"e4bdad75574e83880be115a9","modelId":"claude-sonnet-5","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":27.872150606397167,"warning":null},{"id":"6e8ce6b0ae75bb9042940f8d","modelId":"claude-sonnet-5","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":34.47626889062095,"warning":null},{"id":"cbbde4b95b5a21deb83b2a0b","modelId":"claude-sonnet-5","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":15.1428571428571,"warning":null},{"id":"a2530a99738d53ca6decd46f","modelId":"claude-sonnet-5","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":4.57142857142857,"warning":null},{"id":"e0678b0119462d76644a10ce","modelId":"claude-sonnet-5","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":16.8571428571429,"warning":null},{"id":"d3787d1b957fcfa3c684c083","modelId":"claude-sonnet-5","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":8.57142857142857,"warning":null},{"id":"0b8fa8daa2c88b443a7449aa","modelId":"claude-sonnet-5","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":1.1428571428571401,"warning":null},{"id":"72851189e89b18b175a34279","modelId":"claude-sonnet-5","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":15.4285714285714,"warning":null},{"id":"cd5da788354923633e1ff1d8","modelId":"claude-sonnet-5","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":44.67323187108326,"warning":null},{"id":"6065d3f4174954a37c01d1c7","modelId":"claude-sonnet-5","benchmarkId":"aa-enterprise-ops-gym-aa","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":43.86750223813787,"warning":null},{"id":"d987d8372c351824904eb80d","modelId":"claude-sonnet-5","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":9.4,"warning":null},{"id":"4325cbb6bcba32969d52bf18","modelId":"claude-sonnet-5","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":9.4,"warning":null},{"id":"7f5707f08e154826e63e8800","modelId":"claude-sonnet-5","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":13.200000000000001,"warning":null},{"id":"8cec453083c2b2c64dd64b8c","modelId":"claude-sonnet-5","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":11.600000000000001,"warning":null},{"id":"15587f3af3fa9e59ff755686","modelId":"claude-sonnet-5","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":12.6,"warning":null},{"id":"0b119aa5c97483db76e43f40","modelId":"claude-sonnet-5","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":1308.45,"warning":null},{"id":"0842fefee8fdb0f5ea919705","modelId":"claude-sonnet-5","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":1145.04,"warning":null},{"id":"0557b2c900b2d809263a81ff","modelId":"claude-sonnet-5","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":1500.86,"warning":null},{"id":"b7fd469141573e139e6dc01b","modelId":"claude-sonnet-5","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":1222.52,"warning":null},{"id":"a335f96e4904dd7731faeb36","modelId":"claude-sonnet-5","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":1283.47,"warning":null},{"id":"26b7ce6d0eddb010907edcff","modelId":"claude-sonnet-5","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":1400.77,"warning":null},{"id":"3fa3149554f3d1c058930336","modelId":"claude-sonnet-5","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":91.1111111111111,"warning":null},{"id":"a1987b1a28ab21f28696cf3f","modelId":"claude-sonnet-5","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":80,"warning":null},{"id":"c2ed28284e20ee8b8775ef5a","modelId":"claude-sonnet-5","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":90.0709219858156,"warning":null},{"id":"b359ab1fc0dbf5ab7fa628df","modelId":"claude-sonnet-5","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":35.7275254865616,"warning":null},{"id":"938293264816e12f768d2599","modelId":"claude-sonnet-5","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":21.9184430027804,"warning":null},{"id":"9f4ce5dcb90a73c1df4002f2","modelId":"claude-sonnet-5","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":41.2882298424467,"warning":null},{"id":"d82c20bf270d1a9536b1eae7","modelId":"claude-sonnet-5","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":29.9814643188137,"warning":null},{"id":"21139124a37a09effadf4583","modelId":"claude-sonnet-5","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":19.0454124189064,"warning":null},{"id":"60c78fa2ce7f6be78df1e264","modelId":"claude-sonnet-5","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":39.017608897127,"warning":null},{"id":"d43d5179fd12d01362a07e0c","modelId":"claude-sonnet-5","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":55.00000000000001,"warning":null},{"id":"21b4d6e29173c4e8a4a46a74","modelId":"claude-sonnet-5","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":77.28323699421969,"warning":null},{"id":"737ea32644d6db0a08c42ad1","modelId":"claude-sonnet-5","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":71.90751445086701,"warning":null},{"id":"c21f43cdc9b325847d265d03","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":-3.68333333333333,"warning":null},{"id":"c121d252aead88218ae94083","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":-8.23333333333333,"warning":null},{"id":"9421851310be4d5cc39103da","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":16.45,"warning":null},{"id":"26874b9f4b82ced0f4d4b331","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":-6.86666666666667,"warning":null},{"id":"d7cff7448ac9d293e5b872bd","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":-0.65,"warning":null},{"id":"1df0b890fcab062c13afeeda","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":3.18333333333333,"warning":null},{"id":"d5a99932e01192bf9d1c479f","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":37.43333333333334,"warning":null},{"id":"ae1bcc5e1967bce93138e279","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":37.35,"warning":null},{"id":"b6ffc71819c6232475ebfe2b","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":40.050000000000004,"warning":null},{"id":"92a6cf69529cf4d7779e63ca","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":37.1,"warning":null},{"id":"2c000a3056d5754838032631","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":33.800000000000004,"warning":null},{"id":"b7b652686b8bd48c14a72ba2","modelId":"claude-sonnet-5","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":38.96666666666667,"warning":null},{"id":"63d2d77f1bf4eb85e55eebc1","modelId":"claude-sonnet-5","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":54.2824074074074,"warning":null},{"id":"a1bc9299f4da293519040ae3","modelId":"claude-sonnet-5","benchmarkId":"aa-scicode","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":50.1157407407407,"warning":null},{"id":"4bb4682135688e4351c6d658","modelId":"claude-sonnet-5","benchmarkId":"aa-scicode","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":54.2824074074074,"warning":null},{"id":"23b87b7836cba38b9e707f76","modelId":"claude-sonnet-5","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":51.6203703703704,"warning":null},{"id":"fa57c67e5f6863724b91bb55","modelId":"claude-sonnet-5","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":54.050925925925895,"warning":null},{"id":"f862c5e3a18f6a6c8fe36819","modelId":"claude-sonnet-5","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":37.319587628866,"warning":null},{"id":"7aa7cb43d88f63979741acd9","modelId":"claude-sonnet-5","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":15.6701030927835,"warning":null},{"id":"f92691ca7303d9bd88dddc12","modelId":"claude-sonnet-5","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":80.5243445692884,"warning":null},{"id":"73e34cbb98b30940b928c16c","modelId":"claude-sonnet-5","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Claude Sonnet 5 (Non-reasoning, High Effort)","configuration":"Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning","score":75.2808988764045,"warning":null},{"id":"a4418309697991f74b90a896","modelId":"claude-sonnet-5","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, High Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high","score":5.05050505050505,"warning":null},{"id":"2b6129afe9abbb202c5c701d","modelId":"claude-sonnet-5","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low","score":2.52525252525253,"warning":null},{"id":"926ad37100a0ae2005b7a705","modelId":"claude-sonnet-5","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5","score":14.1414141414141,"warning":null},{"id":"813ecd8b037459b829944c25","modelId":"claude-sonnet-5","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium","score":2.02020202020202,"warning":null},{"id":"a4c869fc652332f41bd59474","modelId":"claude-sonnet-5","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)","configuration":"Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh","score":7.07070707070707,"warning":null},{"id":"52163093753564a0e2539873","modelId":"claude-sonnet-5","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"claude-sonnet-5","configuration":"claude-sonnet-5; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":48.2,"warning":null},{"id":"11a57984aea1a8da93db31c3","modelId":"claude-sonnet-5","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"claude-sonnet-5","configuration":"claude-sonnet-5; Reported effort: low; 113 unique tasks; 449 attempts; 4 runs","score":30.5,"warning":null},{"id":"9fd633042f2f5198fccbe085","modelId":"claude-sonnet-5","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"claude-sonnet-5","configuration":"claude-sonnet-5; Reported effort: max; 113 unique tasks; 442 attempts; 4 runs","score":53.8,"warning":null},{"id":"a42f15ae42cd5b945a0d0f4f","modelId":"claude-sonnet-5","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"claude-sonnet-5","configuration":"claude-sonnet-5; Reported effort: medium; 113 unique tasks; 450 attempts; 4 runs","score":39.8,"warning":null},{"id":"856339a53bf647f60852283a","modelId":"claude-sonnet-5","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"claude-sonnet-5","configuration":"claude-sonnet-5; Reported effort: xhigh; 113 unique tasks; 451 attempts; 4 runs","score":49.7,"warning":null},{"id":"aaae9fdfb56cae71deebae41","modelId":"claude-sonnet-5","benchmarkId":"terminal-claudecode","level":"high","sourceLabel":"Sonnet 5","configuration":"Sonnet 5; Reported effort: high; 445 trials; recorded 2026-06-30","score":74.61,"warning":null},{"id":"5d2b209a9235ccebdbdd2320","modelId":"command-a-plus-05-2026","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":366.16,"warning":null},{"id":"e21fc7e41b06c5f966ba5005","modelId":"command-a-plus-05-2026","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.66666666666669,"warning":null},{"id":"201b76826240a98b3cc2f619","modelId":"command-a-plus-05-2026","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.8104537047977383,"warning":null},{"id":"2ccdbb5004b77a13dc61b015","modelId":"command-a-plus-05-2026","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"c284b9431d0d16bbad751202","modelId":"command-a-plus-05-2026","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":1,"warning":null},{"id":"765497434c3a092fe1716fc2","modelId":"command-a-plus-05-2026","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":658.08,"warning":null},{"id":"10229395b4f5570e9e94c618","modelId":"command-a-plus-05-2026","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.06060606060609,"warning":null},{"id":"0b91e3c66e0cbd10f89c4adf","modelId":"command-a-plus-05-2026","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.9555143651529,"warning":null},{"id":"79f1835a76a8ef96e8c7db02","modelId":"command-a-plus-05-2026","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.9455782312925,"warning":null},{"id":"641499b97a2b15845679955b","modelId":"command-a-plus-05-2026","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.555555555555556,"warning":null},{"id":"ec037f6ae1a0299e9e2a7784","modelId":"command-a-plus-05-2026","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.2369942196532,"warning":null},{"id":"9fe83ac17762f2d5b91590ca","modelId":"command-a-plus-05-2026","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":-4.01666666666667,"warning":null},{"id":"26670e73b2cc07d434922fd0","modelId":"command-a-plus-05-2026","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.883333333333333,"warning":null},{"id":"5ab70dacb88f83e57d5e2076","modelId":"command-a-plus-05-2026","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.5416666666667,"warning":null},{"id":"45dbb1834092da47ce482a2c","modelId":"command-a-plus-05-2026","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.7017543859649,"warning":null},{"id":"12d6380c2e451719a74ba2ee","modelId":"command-a-plus-05-2026","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.97938144329897,"warning":null},{"id":"b428a724421ec67f5d001f52","modelId":"command-a-plus-05-2026","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":25,"warning":null},{"id":"e07117252be6e1880685c4d4","modelId":"command-a-plus-05-2026","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.8464419475655,"warning":null},{"id":"b4b54c7c7c50aac1e09c9338","modelId":"command-a-plus-05-2026","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Command A+","configuration":"Command A+; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/command-a-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.505050505050505,"warning":null},{"id":"0f2099408e3868dd3f5bbd0d","modelId":"command-r-03-2024","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Command-R+ (Apr '24)","configuration":"Command-R+ (Apr '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-plus-04-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.3232323232323,"warning":null},{"id":"e7b2966cb801f40d53a63d0d","modelId":"command-r-03-2024","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Command-R (Mar '24)","configuration":"Command-R (Mar '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-03-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.383838383838402,"warning":null},{"id":"78c2d72883d8472bf84bb942","modelId":"command-r-03-2024","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Command-R (Mar '24)","configuration":"Command-R (Mar '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-03-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.79,"warning":null},{"id":"c51be1971aa7732d0e3c9dec","modelId":"command-r-03-2024","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Command-R+ (Apr '24)","configuration":"Command-R+ (Apr '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-plus-04-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.63,"warning":null},{"id":"8738d7c5dfd75c32c1227708","modelId":"command-r-03-2024","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Command-R (Mar '24)","configuration":"Command-R (Mar '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-03-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.76190476190476,"warning":null},{"id":"f43c9503098639be7baabd71","modelId":"command-r-03-2024","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Command-R+ (Apr '24)","configuration":"Command-R+ (Apr '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-plus-04-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.169312169312201,"warning":null},{"id":"14c3bdfd1b0511c0d8bd8d7b","modelId":"command-r-03-2024","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Command-R (Mar '24)","configuration":"Command-R (Mar '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-03-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.400000000000002,"warning":null},{"id":"9fd73563f403665e135e24bc","modelId":"command-r-03-2024","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Command-R+ (Apr '24)","configuration":"Command-R+ (Apr '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-plus-04-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.8666666666667,"warning":null},{"id":"2deb81947d71e3f165d2316b","modelId":"command-r-03-2024","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Command-R+ (Apr '24)","configuration":"Command-R+ (Apr '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-plus-04-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.1765292553192,"warning":null},{"id":"bfe86af3326b7bb69930545c","modelId":"command-r-03-2024","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Command-R (Mar '24)","configuration":"Command-R (Mar '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/command-r-03-2024; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.843085106383,"warning":null},{"id":"28154d8ea2e87ddacaa50495","modelId":"deepseek-r1-0528","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":76,"warning":null},{"id":"d1f9132429ab5fb1330d2974","modelId":"deepseek-r1-0528","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":55.6666666666667,"warning":null},{"id":"d457e9fe5dc1d1849bde49ee","modelId":"deepseek-r1-0528","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.42857142857143,"warning":null},{"id":"89c583f754304a1af65e90d8","modelId":"deepseek-r1-0528","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":85.97916666666667,"warning":null},{"id":"89234d302d97c8daf59156c8","modelId":"deepseek-r1-0528","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.31313131313131,"warning":null},{"id":"2894a03cfe0dd1c35eb63b61","modelId":"deepseek-r1-0528","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.8480074142725,"warning":null},{"id":"51289684897e664af54a05d2","modelId":"deepseek-r1-0528","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.5918367346939,"warning":null},{"id":"f3bf8f6694da5448f8d82c11","modelId":"deepseek-r1-0528","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.03703703703701,"warning":null},{"id":"10731a3c1d964999d4ff6598","modelId":"deepseek-r1-0528","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":98.26666666666671,"warning":null},{"id":"ac159579de0c6415663fa834","modelId":"deepseek-r1-0528","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.8570478723404,"warning":null},{"id":"da46f877760d8faa5938e0c0","modelId":"deepseek-r1-0528","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":-27.4333333333333,"warning":null},{"id":"b93f0ed6713171396a82dc72","modelId":"deepseek-r1-0528","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.533333333333335,"warning":null},{"id":"18a2418d73fee9d97b9e6213","modelId":"deepseek-r1-0528","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.5497076023392,"warning":null},{"id":"91a19a0300fec337c23eaa24","modelId":"deepseek-r1-0528","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"DeepSeek R1 0528 (May '25)","configuration":"DeepSeek R1 0528 (May '25); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.909090909090901,"warning":null},{"id":"58ce3731b6917805aad4c062","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.66666666666671,"warning":null},{"id":"08fd0fb9fdd7b4017f5af622","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":15,"warning":null},{"id":"2258149dfb5467587a60f57e","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"30fce54c7ca06f7f9c3150ac","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":61.2121212121212,"warning":null},{"id":"502b0514328b85336c43b79d","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.9314179796107505,"warning":null},{"id":"278e99ccd1bf0c3c5d492f6c","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.863945578231302,"warning":null},{"id":"6a61d3d8a1884f195532baf1","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.3227513227513,"warning":null},{"id":"50f9af8abf72ce37fba0fb3a","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":93.2,"warning":null},{"id":"752650e6b94ff2d88f9139d6","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.8779920212766,"warning":null},{"id":"dfd5bf4e982521e955c382fc","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-63.6166666666667,"warning":null},{"id":"dcaa7d394803f4ee83bee90f","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.2,"warning":null},{"id":"5fbc7e5ecd7f934aed6ef04d","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"29dfea68f2a7733cb8a8cecb","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"DeepSeek R1 0528 Qwen3 8B","configuration":"DeepSeek R1 0528 Qwen3 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-qwen3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.51515151515152,"warning":null},{"id":"243c60a86656d1595c85745b","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":53.66666666666669,"warning":null},{"id":"8dd78fb19901b64635db44f7","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10,"warning":null},{"id":"2db469a257b0c3f2f9b40bfd","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"e6222d4f378654bfa05436ac","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.2020202020202,"warning":null},{"id":"17ee47efdbcf843333a4b243","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.13,"warning":null},{"id":"ae831c640f2a28b64b82e0c4","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.5510204081633,"warning":null},{"id":"b9505e9c34edbb45f0c1117f","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.560846560846603,"warning":null},{"id":"6fc19818675129310568bb8b","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":93.4666666666667,"warning":null},{"id":"01313163168fd0c915717c34","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.4797207446808,"warning":null},{"id":"c8e893e3e38807fa7c5bc79c","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-46.3833333333333,"warning":null},{"id":"2f9d19dbc5ed104d40cdfb95","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.166666666666668,"warning":null},{"id":"4b37220933b4b948d9b751ff","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.9298245614035,"warning":null},{"id":"63f152f6d7e4690aaad8b67a","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 70B","configuration":"DeepSeek R1 Distill Llama 70B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-70b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.51515151515152,"warning":null},{"id":"717d45d07de6c052364ae732","modelId":"deepseek-r1-distill-llama-8b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 8B","configuration":"DeepSeek R1 Distill Llama 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.3333333333333,"warning":null},{"id":"0411fa720378242cd32f3640","modelId":"deepseek-r1-distill-llama-8b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 8B","configuration":"DeepSeek R1 Distill Llama 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"202acf3ea41812346b29502c","modelId":"deepseek-r1-distill-llama-8b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 8B","configuration":"DeepSeek R1 Distill Llama 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.2020202020202,"warning":null},{"id":"28f69c15c898a22e11d5c5c4","modelId":"deepseek-r1-distill-llama-8b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 8B","configuration":"DeepSeek R1 Distill Llama 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.5510204081633,"warning":null},{"id":"0ea361c2d08a7937fde27b2c","modelId":"deepseek-r1-distill-llama-8b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 8B","configuration":"DeepSeek R1 Distill Llama 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.2804232804233,"warning":null},{"id":"9dead492c7767af300580f03","modelId":"deepseek-r1-distill-llama-8b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 8B","configuration":"DeepSeek R1 Distill Llama 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":85.26666666666671,"warning":null},{"id":"36c671e4534c9ff66d2efdea","modelId":"deepseek-r1-distill-llama-8b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Llama 8B","configuration":"DeepSeek R1 Distill Llama 8B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-llama-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.255319148936195,"warning":null},{"id":"a116bf871d78b619440a0d27","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 1.5B","configuration":"DeepSeek R1 Distill Qwen 1.5B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-1-5b; Mode from evaluator isReasoning metadata; effort budget not specified","score":22,"warning":null},{"id":"3732ec9546845932aab5bfbe","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 1.5B","configuration":"DeepSeek R1 Distill Qwen 1.5B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-1-5b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.66666666666667,"warning":null},{"id":"9e90674679d47770bee4c60f","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 1.5B","configuration":"DeepSeek R1 Distill Qwen 1.5B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-1-5b; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.7979797979798,"warning":null},{"id":"055397757bbab069a14a098c","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 1.5B","configuration":"DeepSeek R1 Distill Qwen 1.5B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-1-5b; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.08,"warning":null},{"id":"fa0a9617f5d6b929618a9d65","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 1.5B","configuration":"DeepSeek R1 Distill Qwen 1.5B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-1-5b; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.1972789115646,"warning":null},{"id":"967ea0ca7b70675dd27176b0","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 1.5B","configuration":"DeepSeek R1 Distill Qwen 1.5B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-1-5b; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.98412698412698,"warning":null},{"id":"b6a1f34951caea6c3455f61b","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 1.5B","configuration":"DeepSeek R1 Distill Qwen 1.5B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-1-5b; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.7333333333333,"warning":null},{"id":"78dda2ed784ee488b907a8a8","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 1.5B","configuration":"DeepSeek R1 Distill Qwen 1.5B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-1-5b; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.9198803191489,"warning":null},{"id":"df13747a2c4fb0617b290384","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 14B","configuration":"DeepSeek R1 Distill Qwen 14B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":55.6666666666667,"warning":null},{"id":"f6729439534a49931b93c6d3","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 14B","configuration":"DeepSeek R1 Distill Qwen 14B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.3333333333333,"warning":null},{"id":"5a99dc39b2489e5491d366a7","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 14B","configuration":"DeepSeek R1 Distill Qwen 14B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.3838383838384,"warning":null},{"id":"5db07063f3dc97fd82ec4610","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 14B","configuration":"DeepSeek R1 Distill Qwen 14B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.130000000000001,"warning":null},{"id":"f0f8badfdf79f42dbd45cc88","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 14B","configuration":"DeepSeek R1 Distill Qwen 14B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.108843537414998,"warning":null},{"id":"b88a2bb503c88bf49553b4e1","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 14B","configuration":"DeepSeek R1 Distill Qwen 14B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.5661375661376,"warning":null},{"id":"664755cb2071b85ced978db3","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 14B","configuration":"DeepSeek R1 Distill Qwen 14B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":94.8666666666667,"warning":null},{"id":"8c5936db8bc598b54ecd95b9","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 14B","configuration":"DeepSeek R1 Distill Qwen 14B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.0026595744681,"warning":null},{"id":"36958495a1c3cc263aa8ca57","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 32B","configuration":"DeepSeek R1 Distill Qwen 32B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-32b; Mode from evaluator isReasoning metadata; effort budget not specified","score":63,"warning":null},{"id":"48284251b9eed81c130233ab","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 32B","configuration":"DeepSeek R1 Distill Qwen 32B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-32b; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.66666666666667,"warning":null},{"id":"ad1db369c6baf73ac00539d7","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 32B","configuration":"DeepSeek R1 Distill Qwen 32B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-32b; Mode from evaluator isReasoning metadata; effort budget not specified","score":61.5151515151515,"warning":null},{"id":"88242b8c0ec5a510a77d7f1d","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 32B","configuration":"DeepSeek R1 Distill Qwen 32B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-32b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.58,"warning":null},{"id":"a99251c3bb7ceba3f13ebc1d","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 32B","configuration":"DeepSeek R1 Distill Qwen 32B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-32b; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.9251700680272,"warning":null},{"id":"833ffe1e8e5b5830b4a596e2","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 32B","configuration":"DeepSeek R1 Distill Qwen 32B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-32b; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.984126984127,"warning":null},{"id":"5e67615c87f9dbb2127e0805","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 32B","configuration":"DeepSeek R1 Distill Qwen 32B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-32b; Mode from evaluator isReasoning metadata; effort budget not specified","score":94.06666666666669,"warning":null},{"id":"9efc3ef712c44c990e27aaa1","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek R1 Distill Qwen 32B","configuration":"DeepSeek R1 Distill Qwen 32B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-r1-distill-qwen-32b; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.936170212766,"warning":null},{"id":"51db25dec7dd9b6ee1af0a92","modelId":"deepseek-v3.2","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":59,"warning":null},{"id":"27b5897f1b8a957838bd8cd2","modelId":"deepseek-v3.2","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":92,"warning":null},{"id":"55fd90923f763bdbaf99506b","modelId":"deepseek-v3.2","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":14.5280235988201,"warning":null},{"id":"7bb7a5261517f9b7393edbbf","modelId":"deepseek-v3.2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":45.6666666666667,"warning":null},{"id":"509e652963248d4d5fb3d747","modelId":"deepseek-v3.2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":73.3333333333333,"warning":null},{"id":"257d1e613d6552d3fb81fcd4","modelId":"deepseek-v3.2","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":0.857142857142857,"warning":null},{"id":"ca37adba46b2003742a66663","modelId":"deepseek-v3.2","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":2.85714285714286,"warning":null},{"id":"9c849784c994c92d82594642","modelId":"deepseek-v3.2","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":810.24,"warning":null},{"id":"406b55d44096c3fc11bd6e0e","modelId":"deepseek-v3.2","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":82.67708333333333,"warning":null},{"id":"c3e8ddd7c4d1151df0f2e9b5","modelId":"deepseek-v3.2","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":86.54166666666667,"warning":null},{"id":"95ce60be501a5563083110d5","modelId":"deepseek-v3.2","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":75.0505050505051,"warning":null},{"id":"078e78833b376471c91df11e","modelId":"deepseek-v3.2","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":84.040404040404,"warning":null},{"id":"aa22308da67df2bbc79a5257","modelId":"deepseek-v3.2","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":11.2140871177016,"warning":null},{"id":"375a2df992ecb3932c79a0a9","modelId":"deepseek-v3.2","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":24.5597775718258,"warning":null},{"id":"91a9cfa474cd837eb548b3df","modelId":"deepseek-v3.2","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":49.0476190476191,"warning":null},{"id":"0258d20c0150addb336ab7da","modelId":"deepseek-v3.2","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":60.6802721088435,"warning":null},{"id":"2e55950f34a54a20d60015ea","modelId":"deepseek-v3.2","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":59.2592592592593,"warning":null},{"id":"abafce31201ae669660cbac9","modelId":"deepseek-v3.2","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":86.2433862433862,"warning":null},{"id":"cd243264a418b155eec7573d","modelId":"deepseek-v3.2","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":83.7101063829787,"warning":null},{"id":"b7211928466c4d961deff26b","modelId":"deepseek-v3.2","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":86.2117686170213,"warning":null},{"id":"ad70fb15b77d81ac74c0ce38","modelId":"deepseek-v3.2","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":-46.8833333333333,"warning":null},{"id":"9bdadba43260d89af264c859","modelId":"deepseek-v3.2","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":-22.4833333333333,"warning":null},{"id":"560f2b6ebb5e7968026d533c","modelId":"deepseek-v3.2","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":24,"warning":null},{"id":"7560286cbd56eaed8556521b","modelId":"deepseek-v3.2","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":32.96666666666667,"warning":null},{"id":"9f6e7bb623a6f650fd1e7a7f","modelId":"deepseek-v3.2","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":78.9473684210526,"warning":null},{"id":"b1cdb72f437d4c38c7e68f79","modelId":"deepseek-v3.2","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":90.6432748538012,"warning":null},{"id":"c6d9bb636099f72e73c8f57f","modelId":"deepseek-v3.2","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"DeepSeek V3.2 (Non-reasoning)","configuration":"DeepSeek V3.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2","score":32.5757575757576,"warning":null},{"id":"54cd965a443d2ae081646656","modelId":"deepseek-v3.2","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":35.6060606060606,"warning":null},{"id":"7fa83144d986891b98ca55e1","modelId":"deepseek-v3.2","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"DeepSeek V3.2 (Reasoning)","configuration":"DeepSeek V3.2 (Reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v3-2-reasoning","score":46.8164794007491,"warning":null},{"id":"5de71161ca30dde6ea78d6e2","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":96.6666666666667,"warning":null},{"id":"edc9ec337f8ec9c00318a38f","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":70,"warning":null},{"id":"da1da6326a1c6365f377d1b3","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.428571428571431,"warning":null},{"id":"19939f3f32bedc31c6f2e423","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.36979166666667,"warning":null},{"id":"40fac96214150f7c9055b2f8","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":87.0707070707071,"warning":null},{"id":"934f82bf796a5f145286aefa","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.7303058387396,"warning":null},{"id":"0d6fbc4c2f6e63c01d55902c","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.8775510204082,"warning":null},{"id":"d7a6befd16d9965c0f855044","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":89.6296296296296,"warning":null},{"id":"841d60685fb658fe47a7ef71","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":86.3115026595745,"warning":null},{"id":"f6d49d36dd36d19e284b4d40","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":-17.7166666666667,"warning":null},{"id":"9e9c78a7ffb2a500222ed9aa","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.766666666666666,"warning":null},{"id":"866f5d18b5c5f028af163a6c","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"bd04ee261df4be08b3396245","modelId":"deepseek-v3.2-speciale","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"DeepSeek V3.2 Speciale","configuration":"DeepSeek V3.2 Speciale; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/deepseek-v3-2-speciale; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.8484848484849,"warning":null},{"id":"a45c68223e1ae374ae76da31","modelId":"deepseek-v4-flash","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":1256.72,"warning":null},{"id":"1a7f324185d4152bcefff6a8","modelId":"deepseek-v4-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":79.6666666666667,"warning":null},{"id":"198c518ceb539e173702fd0e","modelId":"deepseek-v4-flash","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":53.96771855133674,"warning":null},{"id":"7f80aa4cb8ac1c1539ed4751","modelId":"deepseek-v4-flash","benchmarkId":"aa-critpt","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":16.5714285714286,"warning":null},{"id":"5034155f9f373466e08a2796","modelId":"deepseek-v4-flash","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":11,"warning":null},{"id":"7aef406561c55abab75d5692","modelId":"deepseek-v4-flash","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":1456.09,"warning":null},{"id":"407f6ccc80858a01c74fe91a","modelId":"deepseek-v4-flash","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":90.8080808080808,"warning":null},{"id":"3f1a652d223fdc1a82c7a442","modelId":"deepseek-v4-flash","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":38.5542168674699,"warning":null},{"id":"7e9a79f5ae68e547841899c9","modelId":"deepseek-v4-flash","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":13.3333333333333,"warning":null},{"id":"35b25adff9293e9983993576","modelId":"deepseek-v4-flash","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":-14.2833333333333,"warning":null},{"id":"40312e88cf305dbd9f804e18","modelId":"deepseek-v4-flash","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":40.38333333333333,"warning":null},{"id":"9ac03d02aab2b66b5ec98d6a","modelId":"deepseek-v4-flash","benchmarkId":"aa-scicode","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":50.3472222222222,"warning":null},{"id":"06b57055d7bf20ee8731a0c4","modelId":"deepseek-v4-flash","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":39.381443298969096,"warning":null},{"id":"c415823cdba1670ec1db8602","modelId":"deepseek-v4-flash","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":78.65168539325839,"warning":null},{"id":"b00c6e5708fb4aa9f02984e9","modelId":"deepseek-v4-flash","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash","score":12.1212121212121,"warning":null},{"id":"39a7bed5705711ac27a52863","modelId":"deepseek-v4-flash","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (High)","configuration":"DeepSeek V4 Flash 0731 (High); Source model ID: deepseek-v4-flash-0731-high; 120 tasks","score":55.972222222222214,"warning":null},{"id":"c846403c911a1743e84cc3c3","modelId":"deepseek-v4-flash","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"DeepSeek V4 Flash 0731 (Low)","configuration":"DeepSeek V4 Flash 0731 (Low); Source model ID: deepseek-v4-flash-0731-low; 120 tasks","score":45.97222222222222,"warning":null},{"id":"bcce4d406862908e10d2d67e","modelId":"deepseek-v4-flash","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"DeepSeek V4 Flash 0731 (Max)","configuration":"DeepSeek V4 Flash 0731 (Max); Source model ID: deepseek-v4-flash-0731-max; 120 tasks","score":61.38888888888888,"warning":null},{"id":"1a96e7a8059bfa86f6a2589c","modelId":"deepseek-v4-flash","benchmarkId":"arc-v2semiprivate","level":"none","sourceLabel":"DeepSeek V4 Flash 0731 (None)","configuration":"DeepSeek V4 Flash 0731 (None); Source model ID: deepseek-v4-flash-0731-none; 120 tasks","score":2.083333333333333,"warning":null},{"id":"8b3518db91f03758794ffbbc","modelId":"deepseek-v4-flash","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"deepseek-v4-flash","configuration":"deepseek-v4-flash; Reported effort: max; 113 unique tasks; 452 attempts; 4 runs","score":53.3,"warning":null},{"id":"30359f55b56cbb7fa8922b58","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":25,"warning":null},{"id":"04d5f243dcc96f6864df12d3","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":1052.09,"warning":null},{"id":"7498f18a3d7a0d6e3a8c05dd","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":833.07,"warning":null},{"id":"7d8304ff46ff8c93cd730c9e","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":72,"warning":null},{"id":"af09aabfadc9e1d549b0ee1b","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":74.3333333333333,"warning":null},{"id":"c765bd4f69aafe0eeb5740cf","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":41.6666666666667,"warning":null},{"id":"d2d91e73f95d13125116701e","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":28.504323745973586,"warning":null},{"id":"45b5b005e82df984c4754e26","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":27.985986830616554,"warning":null},{"id":"211a4875f6e5efce7a1f4c6b","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-critpt","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":3.42857142857143,"warning":null},{"id":"f4fd006a2f22c61ad3ad7809","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-critpt","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":7.14285714285714,"warning":null},{"id":"ddad624429ab904ea43be527","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":0.28571428571428603,"warning":null},{"id":"0d11f93766b03fd342fcc0ed","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":39.57027752909579,"warning":null},{"id":"3c50f6d99203b49ecc762174","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":10.4,"warning":null},{"id":"1267a54ee820ffa75fa16b94","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":10.8,"warning":null},{"id":"647f5ed4f8ac819f8a92f455","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":1082.61,"warning":null},{"id":"00586cea2fa92d2e78ddc42a","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":1115.64,"warning":null},{"id":"5f021e7500c5cfd741f9d8fe","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":86.6666666666667,"warning":null},{"id":"0aabb05540f7cd3d2c0492e8","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":89.3939393939394,"warning":null},{"id":"35d6e01923cb4fad3f436062","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":71.6161616161616,"warning":null},{"id":"022b14ca345d31ca271e5300","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":81.32870169344329,"warning":null},{"id":"a981a043ab444538f1dce56b","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":30.259499536607997,"warning":null},{"id":"181336fde2158d3a0c42459a","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":34.8470806302132,"warning":null},{"id":"0a96281f88d8d9d3e8d7ff8d","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":7.784986098239111,"warning":null},{"id":"8b31df469403ec55b09e81e8","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":73.4693877551021,"warning":null},{"id":"64f11a73331e262497eae162","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":79.1836734693877,"warning":null},{"id":"d9cb1689f0757af2acb41929","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":47.2108843537415,"warning":null},{"id":"a1274257605774c664bc3b62","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":31.516007532956703,"warning":null},{"id":"817e020bab9c448974914094","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":6.66666666666667,"warning":null},{"id":"439d6981fbfd192fa31d48f6","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":15,"warning":null},{"id":"020337d791c025678d7f669e","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":-23.0833333333333,"warning":null},{"id":"c35fc22fbf62c8255fd2ce70","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":-23.9,"warning":null},{"id":"28f74cffb85616a21ef0466f","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":-43.9666666666667,"warning":null},{"id":"6c0936c5bd19f197b911186a","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":34.86666666666667,"warning":null},{"id":"1c10422e572b9a348a7c9166","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":36.81666666666666,"warning":null},{"id":"80863363a872f8c35502f3f6","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":26,"warning":null},{"id":"e12aeb36a0c85da4ce01c982","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-scicode","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":40.162037037037,"warning":null},{"id":"059689698f8cda55ccba60fa","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-scicode","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":45.2546296296296,"warning":null},{"id":"727778276f17f9a2957761b6","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":95.6140350877193,"warning":null},{"id":"60cff368f41fa32aaf7f4572","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":95.0292397660819,"warning":null},{"id":"e5ca0b9abfade94ff13f824a","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":94.4444444444445,"warning":null},{"id":"d5dd25c29a727154d7b02d62","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":26.185567010309303,"warning":null},{"id":"2876c384840221381c3f43e9","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":30.9278350515464,"warning":null},{"id":"2cc630037385cb4acf65861b","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":38.636363636363605,"warning":null},{"id":"389924a1e46a90f46dcec917","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":35.6060606060606,"warning":null},{"id":"8fd65426eea5292e3162825d","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"DeepSeek V4 Flash (Non-reasoning)","configuration":"DeepSeek V4 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-non-reasoning","score":34.0909090909091,"warning":null},{"id":"522740b9265e00e9395dad06","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":56.9288389513109,"warning":null},{"id":"a287097357e9878ccda9bde0","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":61.797752808988804,"warning":null},{"id":"556c0c748a7ec53b1b4d0120","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"DeepSeek V4 Flash (Reasoning, High Effort)","configuration":"DeepSeek V4 Flash (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","score":3.03030303030303,"warning":null},{"id":"f7000ea0f1210578b91c29b3","modelId":"deepseek-v4-flash-0424","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"DeepSeek V4 Flash (Reasoning, Max Effort)","configuration":"DeepSeek V4 Flash (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-flash-0420","score":2.52525252525253,"warning":null},{"id":"4708dc64616b39f8d34ca8f1","modelId":"deepseek-v4-pro","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":1264.67,"warning":null},{"id":"14e10a95b270ef9d1ae373e7","modelId":"deepseek-v4-pro","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":80.3333333333333,"warning":null},{"id":"6b8d6f24397d8867cf1faec4","modelId":"deepseek-v4-pro","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":56.711655463440025,"warning":null},{"id":"9dd052bf6a4ebf107f6de0da","modelId":"deepseek-v4-pro","benchmarkId":"aa-critpt","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":18,"warning":null},{"id":"09421a76c727dce721916f4d","modelId":"deepseek-v4-pro","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":49.59713518352731,"warning":null},{"id":"43690b5f91d764a37de970d1","modelId":"deepseek-v4-pro","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":11.4,"warning":null},{"id":"bcda011b6a3f738075dafcfd","modelId":"deepseek-v4-pro","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":1493.31,"warning":null},{"id":"3b35b842ffe605a75e112290","modelId":"deepseek-v4-pro","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":92.82828282828281,"warning":null},{"id":"760ef06b17543599268b84e3","modelId":"deepseek-v4-pro","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":41.0101946246525,"warning":null},{"id":"4ba74afd46cc724b0e2b9629","modelId":"deepseek-v4-pro","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":17.7777777777778,"warning":null},{"id":"1556f05dd2908433d9fc662b","modelId":"deepseek-v4-pro","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":0.833333333333333,"warning":null},{"id":"a30393a098bcb7270303b12f","modelId":"deepseek-v4-pro","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":49.1,"warning":null},{"id":"49acabfd6982ca02015ff725","modelId":"deepseek-v4-pro","benchmarkId":"aa-scicode","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":51.0416666666667,"warning":null},{"id":"89082513bd20d1cb04639c1d","modelId":"deepseek-v4-pro","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":39.587628865979404,"warning":null},{"id":"cf40d9275e4b9284715bca88","modelId":"deepseek-v4-pro","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":78.65168539325839,"warning":null},{"id":"cfe21e52f99ab0089cdaebe9","modelId":"deepseek-v4-pro","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro 0813 (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro","score":14.1414141414141,"warning":null},{"id":"c64dd03820fdf345d94145b0","modelId":"deepseek-v4-pro","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"DeepSeek V4 Pro 0813 (High)","configuration":"DeepSeek V4 Pro 0813 (High); Source model ID: deepseek-v4-pro-0813-high; 120 tasks","score":59.72222222222221,"warning":null},{"id":"0f79426f1f5a6b4e49959783","modelId":"deepseek-v4-pro","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"DeepSeek V4 Pro 0813 (Low)","configuration":"DeepSeek V4 Pro 0813 (Low); Source model ID: deepseek-v4-pro-0813-low; 120 tasks","score":56.25,"warning":null},{"id":"25337d15a8b7bed1bf41c830","modelId":"deepseek-v4-pro","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (Max)","configuration":"DeepSeek V4 Pro 0813 (Max); Source model ID: deepseek-v4-pro-0813-max; 120 tasks","score":61.25000000000001,"warning":null},{"id":"d725d4dd6ab63e2174499861","modelId":"deepseek-v4-pro","benchmarkId":"arc-v2semiprivate","level":"none","sourceLabel":"DeepSeek V4 Pro 0813 (None)","configuration":"DeepSeek V4 Pro 0813 (None); Source model ID: deepseek-v4-pro-0813-none; 120 tasks","score":0.8333333333333334,"warning":null},{"id":"ac3167852c54be45702e8943","modelId":"deepseek-v4-pro","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"deepseek-v4-pro","configuration":"deepseek-v4-pro; Reported effort: max; 113 unique tasks; 452 attempts; 4 runs","score":62.8,"warning":"DeepSeek V4 Pro checkpoint is not identified by this source; April and August revisions must not be combined."},{"id":"888bef3b9b0600140e38bce5","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":18.75,"warning":null},{"id":"35054ff738a363369f96e691","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":924.56,"warning":null},{"id":"2dcde6bce83f18724026ee1c","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-apex-agents-aa","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":24.2625368731563,"warning":null},{"id":"832cb2beabefa15c40d173d0","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":70.3333333333333,"warning":null},{"id":"4f853b52424d8b5786669fd6","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":74.6666666666667,"warning":null},{"id":"049ba5aed9de5c9216fbc178","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":53,"warning":null},{"id":"14e10fac21af13eafc4b2bc3","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":56.289685574342705,"warning":null},{"id":"c9c2f626421c5ba55ef64978","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-critpt","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":10,"warning":null},{"id":"f7d837c0d9ee11b205c5c946","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-critpt","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":12.8571428571429,"warning":null},{"id":"36654ea29065ea332b7ef40e","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":0.857142857142857,"warning":null},{"id":"a1d6fa2bfe35f63d8163d16d","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":40.43569083855566,"warning":null},{"id":"d006aa70eb1d30bfd9f518b8","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":13.4,"warning":null},{"id":"6c29eb2b92d9d49bd6170cbf","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":1218.72,"warning":null},{"id":"656be5ab83573c50c309760f","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":1223.37,"warning":null},{"id":"c648452dd378bb0942cbc01b","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":90.5050505050505,"warning":null},{"id":"1d7cbe2d37cb64936c4535d1","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":88.78787878787881,"warning":null},{"id":"9b744d3a7ed205bab6424371","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":71.7171717171717,"warning":null},{"id":"327957a4bb715a26984ff1d6","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":84.3971631205674,"warning":null},{"id":"d7d33629352f4a94fd7b2299","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":35.2177942539388,"warning":null},{"id":"c92b67b826689436a74b727d","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":37.5347544022243,"warning":null},{"id":"c5ab64b1ce76dbc203820b05","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":8.2483781278962,"warning":null},{"id":"73cd0af759c68add3867fd72","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":71.2925170068027,"warning":null},{"id":"5a3ad5acded4b7c851f16171","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":76.4625850340136,"warning":null},{"id":"f08f499efe39fd2ca951eb4f","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":45.782312925170096,"warning":null},{"id":"6af1a2a35becb877bc4e094c","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":38.3239171374765,"warning":null},{"id":"f006e7160beeab0a79c6f970","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":21.1111111111111,"warning":null},{"id":"e2d986dd108115769c871ef2","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":-10.5666666666667,"warning":null},{"id":"daf424f4f812afb14ebb9d27","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":-10.7333333333333,"warning":null},{"id":"cf19915c5fd19c9700e73691","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":-29.8666666666667,"warning":null},{"id":"70c66138b4b47ba2b8c19d8c","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":41.4,"warning":null},{"id":"095fea7e3506c915a48e7c30","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":42.95,"warning":null},{"id":"7984ee407acd3bd66f6db6f9","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":30.866666666666664,"warning":null},{"id":"99ba0a234f4bfecd88b3a019","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-scicode","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":50.8101851851852,"warning":null},{"id":"947e58b0b93edb29c2be18b7","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":94.15204678362569,"warning":null},{"id":"d88ec7d9a63d161519180539","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":96.19883040935669,"warning":null},{"id":"ceaf48b790d6b1c784fdd288","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":91.2280701754386,"warning":null},{"id":"f620bd2cc9ecffb9eea9a636","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":26.185567010309303,"warning":null},{"id":"ecc83bee2883b16c02eb805a","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":30.103092783505197,"warning":null},{"id":"b7c6b737ef04f71916d523a1","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":41.6666666666667,"warning":null},{"id":"a231d0d6923c87e943c7c7cc","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":46.2121212121212,"warning":null},{"id":"0b349b71fdb3781d4f060c93","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"DeepSeek V4 Pro (Non-reasoning)","configuration":"DeepSeek V4 Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-non-reasoning","score":36.363636363636395,"warning":null},{"id":"8f90177da988f2f6b5e5bb5e","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"DeepSeek V4 Pro (Reasoning, High Effort)","configuration":"DeepSeek V4 Pro (Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424-high","score":64.7940074906367,"warning":null},{"id":"86644eda7144d6e39917eabf","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":64.0449438202247,"warning":null},{"id":"044ab93a3e45cd3aff772342","modelId":"deepseek-v4-pro-0424","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"DeepSeek V4 Pro (Reasoning, Max Effort)","configuration":"DeepSeek V4 Pro (Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/deepseek-v4-pro-0424","score":14.6464646464646,"warning":null},{"id":"dcc51f4502c96a31cc744a2a","modelId":"devstral-2512","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":483.02,"warning":null},{"id":"c027bac776af43b4cb938c11","modelId":"devstral-2512","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.6666666666667,"warning":null},{"id":"56b570282eeb2d7f9bc5720b","modelId":"devstral-2512","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.3333333333333,"warning":null},{"id":"f20b6e6193c225e4bde7c4d7","modelId":"devstral-2512","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.106312467124685,"warning":null},{"id":"4818263b0b0cdc6012971d70","modelId":"devstral-2512","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"18a919dc18d96a14e330490f","modelId":"devstral-2512","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.4,"warning":null},{"id":"50ced579c2ddd69ac4ff06ca","modelId":"devstral-2512","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":688.65,"warning":null},{"id":"2b73f3f0e2fb4a983219b412","modelId":"devstral-2512","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.48958333333333,"warning":null},{"id":"6f3c6cbea54937ac773fa184","modelId":"devstral-2512","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":59.3939393939394,"warning":null},{"id":"f67d22c0ec4ea389ca56cbff","modelId":"devstral-2512","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.5681186283595903,"warning":null},{"id":"06996081218bc20d64759001","modelId":"devstral-2512","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.0952380952381,"warning":null},{"id":"0028f41bbd3897a5e62a1019","modelId":"devstral-2512","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.7619047619048,"warning":null},{"id":"b77d44d579e2a5fb4c111b42","modelId":"devstral-2512","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.1635638297872,"warning":null},{"id":"f87d2326544d8fc4fc49d91d","modelId":"devstral-2512","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":-46.7,"warning":null},{"id":"28c7d9bfa5d2fbf77e67a274","modelId":"devstral-2512","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.816666666666666,"warning":null},{"id":"4656ead8373195f1a2848cdd","modelId":"devstral-2512","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.7546296296296,"warning":null},{"id":"8c16d1eb56b6a0b6ad2c7df6","modelId":"devstral-2512","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.8538011695906,"warning":null},{"id":"54bcb36c56b3510fb13024ba","modelId":"devstral-2512","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.5154639175258,"warning":null},{"id":"520f49635049319b43c19aaa","modelId":"devstral-2512","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.939393939393902,"warning":null},{"id":"8338dab33792ea1da2e48ada","modelId":"devstral-2512","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.337078651685403,"warning":null},{"id":"d85460656a5d267173ae81ba","modelId":"devstral-2512","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Devstral 2","configuration":"Devstral 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"4149e6a6efb13371a5919a0a","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.6666666666667,"warning":null},{"id":"16155cc9771f19d724e14d31","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"eb26a8a40cd04f0794905ce4","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":501.29,"warning":null},{"id":"1dd0d4ad446639c8b032f826","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.8686868686869,"warning":null},{"id":"3599b35b722d8252b79f6f35","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.8433734939759,"warning":null},{"id":"d29b6385e38b2fa601e91de5","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":59.4557823129252,"warning":null},{"id":"91892dd7bf1a5f08090f9d9e","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.5317919075144,"warning":null},{"id":"0b3377f33c68c96e20808b3d","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-59.2333333333333,"warning":null},{"id":"0a6b438d49c67c6b0125a1c9","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.583333333333332,"warning":null},{"id":"8e6d3333f88940e6403844c7","modelId":"diffusiongemma-26b-a4b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"DiffusionGemma 26B A4B","configuration":"DiffusionGemma 26B A4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/diffusiongemma-26b-a4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.3595505617978,"warning":null},{"id":"454c740f40aa59103fd640fb","modelId":"doubao-seed-code","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.3333333333333,"warning":null},{"id":"9dda4e6313c33f052ce51f21","modelId":"doubao-seed-code","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.6666666666667,"warning":null},{"id":"93e5d74fa9cd4b8faa10f31c","modelId":"doubao-seed-code","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"d0b2a7f440e8d5397f0978a3","modelId":"doubao-seed-code","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.75520833333334,"warning":null},{"id":"05fc8421995c99a0e7d522af","modelId":"doubao-seed-code","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.3636363636364,"warning":null},{"id":"e5af52daf1449986eaa89dff","modelId":"doubao-seed-code","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.0871177015755,"warning":null},{"id":"b83eea8de1c05302b1b64c2e","modelId":"doubao-seed-code","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.4285714285714,"warning":null},{"id":"e7d99c67e34240e8766aad72","modelId":"doubao-seed-code","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.6137566137566,"warning":null},{"id":"19ea5a48da48057701cfe1cc","modelId":"doubao-seed-code","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":85.3889627659574,"warning":null},{"id":"96e8b68fb86c6c0f5461090a","modelId":"doubao-seed-code","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.092485549133,"warning":null},{"id":"0dbac5be77e69634487925b3","modelId":"doubao-seed-code","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":-35.2,"warning":null},{"id":"111fd2d05544b06f84c1f97c","modelId":"doubao-seed-code","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.883333333333333,"warning":null},{"id":"8f16565827cdaac0168c025b","modelId":"doubao-seed-code","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.187134502923996,"warning":null},{"id":"eab63b4ac56561a7e1509869","modelId":"doubao-seed-code","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Doubao Seed Code","configuration":"Doubao Seed Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/doubao-seed-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.5151515151515,"warning":null},{"id":"ea6dc61a26cd710caaeaa276","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.3333333333333,"warning":null},{"id":"89cb005073731bd86024d136","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"b3ff20db183a764049256077","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.1111111111111,"warning":null},{"id":"03ab887691c2d04305534b99","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.33642261353105,"warning":null},{"id":"a4419233d06025238adf7fc2","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.1156462585034,"warning":null},{"id":"048a4485e7a9a4c8d5650791","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.6666666666667,"warning":null},{"id":"ad7581b9cbb13c55b285c09c","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":93.06666666666669,"warning":null},{"id":"ad7ebbddb49c0e728ba114d7","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.6097074468085,"warning":null},{"id":"d15eb698c8417578a083d5a2","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-35.1333333333333,"warning":null},{"id":"531621bce0f156b7a851eb0b","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.05,"warning":null},{"id":"396c5b6a5799009c00a077a9","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"20f35a16a687d6b454dbaa39","modelId":"ernie-4.5-300b-a47b-pt","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"ERNIE 4.5 300B A47B","configuration":"ERNIE 4.5 300B A47B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ernie-4-5-300b-a47b; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.06060606060606,"warning":null},{"id":"f99755b76c6471b984bef051","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":85,"warning":null},{"id":"c71e752f02177e2307ec0208","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.42857142857143,"warning":null},{"id":"0fc7ba284be33c52df15619c","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":86.5,"warning":null},{"id":"94de804551d84e436bcfab2c","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.6767676767677,"warning":null},{"id":"e7dfc21f139df43e3647f983","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.253012048192799,"warning":null},{"id":"381abd772bfd4fcc40a9ff1d","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.3605442176871,"warning":null},{"id":"0fa215c1732d7ec7afca35f1","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.16402116402111,"warning":null},{"id":"24b49036b5b6c2c71015d226","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":83.0285904255319,"warning":null},{"id":"47e6a1dbad4f44e3baab9363","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":64.5664739884393,"warning":null},{"id":"cec86b4c9567fb892efd3dde","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":-45.6166666666667,"warning":null},{"id":"637a534eabbcc15462e13a67","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.133333333333333,"warning":null},{"id":"a17190accc3a0092e345b5d3","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":83.9181286549707,"warning":null},{"id":"f2919bcee1f19cc027c0b8e4","modelId":"ernie-5.0-thinking-preview","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"ERNIE 5.0 Thinking Preview","configuration":"ERNIE 5.0 Thinking Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/ernie-5-0-thinking-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":25,"warning":null},{"id":"bab5b3f721c054e194163da2","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":24,"warning":null},{"id":"b597d1e3c86a13c59c590891","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":50.3333333333333,"warning":null},{"id":"d0660023c24169d0375b9331","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":0,"warning":null},{"id":"c83bd4489ef7f16d4df9e0cf","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":0,"warning":null},{"id":"74f33d01f1f6fbcdae474f72","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":0,"warning":null},{"id":"a41dda65db95525981059fa9","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":0,"warning":null},{"id":"b3b843795c22987d82505da7","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":42.4242424242424,"warning":null},{"id":"1ebdbcfcce04b951368b4f81","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":51.5151515151515,"warning":null},{"id":"8caf0e4036cb60fb443a2182","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":5.69972196478221,"warning":null},{"id":"c1b99c8edf1d5b0b83a10907","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":5.977757182576459,"warning":null},{"id":"10e9713791139c6bfc66aea4","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":25.3061224489796,"warning":null},{"id":"ffc52f3cf3a2ef4dd82fc717","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":22.9931972789116,"warning":null},{"id":"4dc04b302fcd46bc8980c038","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":29.3121693121693,"warning":null},{"id":"942dab2d051ced6ab8272528","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":51.6402116402116,"warning":null},{"id":"578f3fc0f7765bd8fde6c59d","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":50.0498670212766,"warning":null},{"id":"a589219818ac81f6b4db247b","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":58.7682845744681,"warning":null},{"id":"de9a29070b73434bde934a9d","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":-82.15,"warning":null},{"id":"91f5aaaa147fa965a95ee6e2","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":-79.8166666666667,"warning":null},{"id":"cd1008d27b1fbfac60e39554","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":5,"warning":null},{"id":"37a86f44ce022d6dafdf777f","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":6.833333333333333,"warning":null},{"id":"81337225c1cfbaecc298a109","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":20.467836257309898,"warning":null},{"id":"e07bdb18a2b42aa76c775099","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":16.374269005848,"warning":null},{"id":"19f33b7a6965d3055111ffb1","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Exaone 4.0 1.2B (Non-reasoning)","configuration":"Exaone 4.0 1.2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b","score":0,"warning":null},{"id":"f639c6955dcc41a97a992d9a","modelId":"exaone-4.0-1.2b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Exaone 4.0 1.2B (Reasoning)","configuration":"Exaone 4.0 1.2B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning","score":0,"warning":null},{"id":"c900cfefe08cce4e82a15a9b","modelId":"exaone-4.0-32b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":39.3333333333333,"warning":null},{"id":"e146162ac9b155d4b57a4230","modelId":"exaone-4.0-32b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":80,"warning":null},{"id":"c48949f7d4d375f4aaf944fa","modelId":"exaone-4.0-32b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":0,"warning":null},{"id":"3dccf3f99ac4f647f345a44e","modelId":"exaone-4.0-32b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":0,"warning":null},{"id":"bbb70ff8ccf50d3761bd741a","modelId":"exaone-4.0-32b","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":73.46354166666667,"warning":null},{"id":"465814ec06b1b537bd6b8db7","modelId":"exaone-4.0-32b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":62.8282828282828,"warning":null},{"id":"182b7997becaf9b5dfe635a2","modelId":"exaone-4.0-32b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":73.93939393939391,"warning":null},{"id":"d3806f14df2e84d68e93bb3b","modelId":"exaone-4.0-32b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":5.004633920296571,"warning":null},{"id":"688816e2f1a961f4d3aff674","modelId":"exaone-4.0-32b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":11.445783132530101,"warning":null},{"id":"96fc68b9a4cdba13bc5714a4","modelId":"exaone-4.0-32b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":33.469387755102,"warning":null},{"id":"c2bb057ef3c15aa7c1a0099c","modelId":"exaone-4.0-32b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":36.3265306122449,"warning":null},{"id":"44e88de85e270c332ba612c8","modelId":"exaone-4.0-32b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":47.1957671957672,"warning":null},{"id":"45918216b4f57506bc18f43f","modelId":"exaone-4.0-32b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":74.70899470899471,"warning":null},{"id":"ab9a17932f0001c18c76fbf4","modelId":"exaone-4.0-32b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":93.93333333333331,"warning":null},{"id":"df985a406bd973b58bb12714","modelId":"exaone-4.0-32b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":97.6666666666667,"warning":null},{"id":"caaf789de95efc45eec9e06f","modelId":"exaone-4.0-32b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":76.8284574468085,"warning":null},{"id":"1cc2edb1a9f3b941f175cda1","modelId":"exaone-4.0-32b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":81.7569813829787,"warning":null},{"id":"28161676227107f4bf1e949f","modelId":"exaone-4.0-32b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":-62.7666666666667,"warning":null},{"id":"d18d1d42d9c3d891e66ccc05","modelId":"exaone-4.0-32b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":-60.0666666666667,"warning":null},{"id":"bd5ae655caef8856694260ac","modelId":"exaone-4.0-32b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":10.616666666666667,"warning":null},{"id":"1eaec2770c32a1d977fe2e9f","modelId":"exaone-4.0-32b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":13.866666666666665,"warning":null},{"id":"f0e22773a86c483105fb9aaf","modelId":"exaone-4.0-32b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":4.09356725146199,"warning":null},{"id":"0c56e3b4c1bd36102a0d428b","modelId":"exaone-4.0-32b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":17.2514619883041,"warning":null},{"id":"27cf0b2a4eed2df72f1b5425","modelId":"exaone-4.0-32b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"EXAONE 4.0 32B (Non-reasoning)","configuration":"EXAONE 4.0 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b","score":1.51515151515152,"warning":null},{"id":"d58e0132dbc6ea2836492ddf","modelId":"exaone-4.0-32b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"EXAONE 4.0 32B (Reasoning)","configuration":"EXAONE 4.0 32B (Reasoning); Model source: https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning","score":3.78787878787879,"warning":null},{"id":"d7d6e5dfb2517db3a3abffd9","modelId":"exaone-4.5-33b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.6666666666667,"warning":null},{"id":"300ba2762404242763d4c0e3","modelId":"exaone-4.5-33b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"30e3abcc63438702d05b2993","modelId":"exaone-4.5-33b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":627.65,"warning":null},{"id":"0a34bb9a5d6b6b0a922ce76e","modelId":"exaone-4.5-33b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.39393939393939,"warning":null},{"id":"41ced3e964a27a11df4b1c3e","modelId":"exaone-4.5-33b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.8822984244671,"warning":null},{"id":"85ca8391a463610733f224f0","modelId":"exaone-4.5-33b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":57.959183673469404,"warning":null},{"id":"58a06a071e5a98afe4e66531","modelId":"exaone-4.5-33b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.3410404624277,"warning":null},{"id":"87ade12107a80c21624bd73f","modelId":"exaone-4.5-33b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-50.7166666666667,"warning":null},{"id":"e7c7a13c51cb53b14149a39e","modelId":"exaone-4.5-33b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.233333333333334,"warning":null},{"id":"f9200d5c5a1c2397d0c658a6","modelId":"exaone-4.5-33b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.07017543859651,"warning":null},{"id":"d3258d1e2e465783b346ca7f","modelId":"exaone-4.5-33b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.4545454545455,"warning":null},{"id":"22b05a6d0064688a6d4b8d73","modelId":"exaone-4.5-33b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"EXAONE 4.5 33B","configuration":"EXAONE 4.5 33B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/exaone-4-5-33b; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.3483146067416,"warning":null},{"id":"778a476fac3a54bc26ad1bdc","modelId":"gemini-2.5-flash","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":60.33333333333331,"warning":null},{"id":"25e8b81f8b05ec46c5e80257","modelId":"gemini-2.5-flash","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":73.3333333333333,"warning":null},{"id":"c843963587d72d6e7fa6ab2b","modelId":"gemini-2.5-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":49.9,"warning":null},{"id":"d1e35c9dfd5a9177d6520490","modelId":"gemini-2.5-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":65.3333333333333,"warning":null},{"id":"8fbe3f48f7d31ed271a50ddf","modelId":"gemini-2.5-flash","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":1.42857142857143,"warning":null},{"id":"03903b802c05359369266f36","modelId":"gemini-2.5-flash","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":1.1428571428571401,"warning":null},{"id":"ae60d7a4d3b3a85a296b38ab","modelId":"gemini-2.5-flash","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":68.2828282828283,"warning":null},{"id":"7a919ff134ab8dd622151ef8","modelId":"gemini-2.5-flash","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":78.989898989899,"warning":null},{"id":"0508741ce4e4c770a963f3a4","modelId":"gemini-2.5-flash","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":4.72659870250232,"warning":null},{"id":"29c12307a2fa27b9adfab4e4","modelId":"gemini-2.5-flash","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":12.1408711770158,"warning":null},{"id":"ad52dd4994d43cfb7388537b","modelId":"gemini-2.5-flash","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":38.9795918367347,"warning":null},{"id":"615f11f6104fbdbc6397c19a","modelId":"gemini-2.5-flash","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":50.2721088435374,"warning":null},{"id":"f2274f10c01fd49af34cc8c7","modelId":"gemini-2.5-flash","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":49.5238095238095,"warning":null},{"id":"a32eda887ff803501ac260c2","modelId":"gemini-2.5-flash","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":69.5238095238095,"warning":null},{"id":"a2a790a25cbcf597773c9220","modelId":"gemini-2.5-flash","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":93.2,"warning":null},{"id":"b3ffd498b7959470e367bd26","modelId":"gemini-2.5-flash","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":98.1333333333333,"warning":null},{"id":"8e548cc9df3852affb6827c7","modelId":"gemini-2.5-flash","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":8.33333333333333,"warning":null},{"id":"e9a8955bfe6f14e6cc47c6be","modelId":"gemini-2.5-flash","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":8.888888888888891,"warning":null},{"id":"5513fb39e65010cbd84258eb","modelId":"gemini-2.5-flash","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":80.9175531914894,"warning":null},{"id":"aa36fae3bef0b68268249bfe","modelId":"gemini-2.5-flash","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":83.1532579787234,"warning":null},{"id":"4871389cdfa8311f33acc44c","modelId":"gemini-2.5-flash","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":65.4913294797688,"warning":null},{"id":"8810b2fe580ca34e86a3b029","modelId":"gemini-2.5-flash","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":69.0751445086705,"warning":null},{"id":"a6ea19c704d0cd6d45804ad9","modelId":"gemini-2.5-flash","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":-42.5666666666667,"warning":null},{"id":"94436d1283ceade19a098e93","modelId":"gemini-2.5-flash","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":-29.8,"warning":null},{"id":"89031d6f4b0b9da5cd80cf55","modelId":"gemini-2.5-flash","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":26.13333333333333,"warning":null},{"id":"be837d02ebf79658b1d356cf","modelId":"gemini-2.5-flash","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":25.95,"warning":null},{"id":"b82146057c975a009a40f506","modelId":"gemini-2.5-flash","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":14.9122807017544,"warning":null},{"id":"b6896924c93716199a8e8b23","modelId":"gemini-2.5-flash","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":31.5789473684211,"warning":null},{"id":"0b1b7e45360ba1982d470496","modelId":"gemini-2.5-flash","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash (Non-reasoning)","configuration":"Gemini 2.5 Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash","score":12.1212121212121,"warning":null},{"id":"a6d86a700f4535aa3b842c46","modelId":"gemini-2.5-flash","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemini 2.5 Flash (Reasoning)","configuration":"Gemini 2.5 Flash (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-reasoning","score":13.6363636363636,"warning":null},{"id":"4b6d985260431c716d5f32f1","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":35.3333333333333,"warning":null},{"id":"a433d84489e1746d7f57ce6b","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":53.3333333333333,"warning":null},{"id":"7c4270b425ce13c10d94c734","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":32,"warning":null},{"id":"d69a72ef36f478ea09b68875","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":55.6666666666667,"warning":null},{"id":"d4da0bef5d2711a9743bf008","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":0,"warning":null},{"id":"434ad978699d9f67751986dc","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":0,"warning":null},{"id":"32549bdfff973940b8fe54d1","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":47.3737373737374,"warning":null},{"id":"25128a1d8bb8e5c053dcad35","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":62.5252525252525,"warning":null},{"id":"838fbf397ffda157ad949a61","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":3.66079703429101,"warning":null},{"id":"60f98d8bd60241b8c86ec5d7","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":6.811862835959221,"warning":null},{"id":"6e11e8fedfcf94c7848f35e4","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":31.496598639455797,"warning":null},{"id":"2d5d302d8a59f5716d532cb4","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":49.8639455782313,"warning":null},{"id":"208bce24d8fb34ba60bd10e9","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":40,"warning":null},{"id":"9f124c6e37fc898fcec9d2aa","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":59.2592592592593,"warning":null},{"id":"b5463a06d82c58c7e8fba350","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":92.60000000000001,"warning":null},{"id":"bc2be91ff8211d91bea25150","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":96.8666666666667,"warning":null},{"id":"3e51c2efec3e1e4facb453c9","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":2.2222222222222197,"warning":null},{"id":"f8b3bc91b10e83be18e8677b","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":72.4401595744681,"warning":null},{"id":"6a0ea081f38de34cf0138ec6","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":75.91422872340429,"warning":null},{"id":"b619e01f7daa0e5ea4cdeda1","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":53.9884393063584,"warning":null},{"id":"4989b8aaa192e67ee9b036ce","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":58.2080924855491,"warning":null},{"id":"bd0e18878398a2cba1e2c630","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":-58.7833333333333,"warning":null},{"id":"54fcfd9dba64059091858233","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":-45.6166666666667,"warning":null},{"id":"67df11bafe9809cfd9e3f3eb","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":15.433333333333332,"warning":null},{"id":"86b22a6d3c908a4896b22e32","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":17.9,"warning":null},{"id":"333ef0ed6319c3f365aae494","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":19.0058479532164,"warning":null},{"id":"402b1b95380a385fcfc42d37","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":18.4210526315789,"warning":null},{"id":"c90f54c21e1329dfe593d000","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Non-reasoning)","configuration":"Gemini 2.5 Flash-Lite (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite","score":2.27272727272727,"warning":null},{"id":"eb222f50e00f52ee760583e4","modelId":"gemini-2.5-flash-lite","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemini 2.5 Flash-Lite (Reasoning)","configuration":"Gemini 2.5 Flash-Lite (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-2-5-flash-lite-reasoning","score":4.545454545454549,"warning":null},{"id":"a2baacd01517ef45b2eceb1d","modelId":"gemini-2.5-pro","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":315.4,"warning":null},{"id":"487059beacefde1e01685e8d","modelId":"gemini-2.5-pro","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":87.6666666666667,"warning":null},{"id":"5604a1b3b4ab8c68dc8d01bc","modelId":"gemini-2.5-pro","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":69,"warning":null},{"id":"fe94c818a9ad0ca7d39e39ef","modelId":"gemini-2.5-pro","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.174946419340874,"warning":null},{"id":"9aec0db3dacd7fcf771012a9","modelId":"gemini-2.5-pro","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.57142857142857,"warning":null},{"id":"2a2fff8b12d3d37901295fdf","modelId":"gemini-2.5-pro","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.2,"warning":null},{"id":"88d422808c7de7f23d709556","modelId":"gemini-2.5-pro","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":615.9,"warning":null},{"id":"defe800b4fa5856397240d2e","modelId":"gemini-2.5-pro","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":90.3125,"warning":null},{"id":"0780118e8e66b234eca4b2a4","modelId":"gemini-2.5-pro","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.4444444444444,"warning":null},{"id":"cb4e80a7918d6b9057e3deed","modelId":"gemini-2.5-pro","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.5208526413346,"warning":null},{"id":"f077b068853bedaf080c341f","modelId":"gemini-2.5-pro","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.707482993197296,"warning":null},{"id":"b5a906c034fd39fe365ed813","modelId":"gemini-2.5-pro","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.1058201058201,"warning":null},{"id":"69605a228871fa6d6a1fe38d","modelId":"gemini-2.5-pro","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":96.7333333333333,"warning":null},{"id":"effe61acb1f2ecd3194c56be","modelId":"gemini-2.5-pro","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":86.186835106383,"warning":null},{"id":"8f2d5e3be696b0d89edeb2fc","modelId":"gemini-2.5-pro","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.9132947976879,"warning":null},{"id":"fed8f4ab77fcd5d31da67c95","modelId":"gemini-2.5-pro","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":-16.35,"warning":null},{"id":"cf0ed4c7679f5831c0151b93","modelId":"gemini-2.5-pro","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.050000000000004,"warning":null},{"id":"b346e2f4d8c39e5b6a8796ce","modelId":"gemini-2.5-pro","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.296296296296305,"warning":null},{"id":"5336414aba2be78f3187de97","modelId":"gemini-2.5-pro","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.093567251462005,"warning":null},{"id":"80b93729bec1b12b13fec2bd","modelId":"gemini-2.5-pro","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.69072164948454,"warning":null},{"id":"fe7921ca6643b00dc3e8c896","modelId":"gemini-2.5-pro","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.5151515151515,"warning":null},{"id":"0f6648f08f82d8663f02b246","modelId":"gemini-2.5-pro","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.4644194756554,"warning":null},{"id":"9861b3363626336b8e1278dd","modelId":"gemini-2.5-pro","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Gemini 2.5 Pro","configuration":"Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"53fc9ec1dee0accada2433b0","modelId":"gemini-2.5-pro","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Gemini 2.5 Pro (Thinking 8K)","configuration":"Gemini 2.5 Pro (Thinking 8K); Source model ID: gemini-2-5-pro-2025-06-17-thinking-8k; 120 tasks","score":2.92,"warning":null},{"id":"6cc85ba2b198bd02c85a961a","modelId":"gemini-2.5-pro","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Gemini 2.5 Pro (Thinking 16K)","configuration":"Gemini 2.5 Pro (Thinking 16K); Source model ID: gemini-2-5-pro-2025-06-17-thinking-16k; 120 tasks","score":4.03,"warning":null},{"id":"85789420efbd10e4bf8e8a0f","modelId":"gemini-2.5-pro","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Gemini 2.5 Pro (Thinking 1K)","configuration":"Gemini 2.5 Pro (Thinking 1K); Source model ID: gemini-2-5-pro-2025-06-17-thinking-1k; 120 tasks","score":0,"warning":null},{"id":"e1746e4a5f84cad00df32d6b","modelId":"gemini-2.5-pro","benchmarkId":"arc-v2semiprivate","level":"thinking","sourceLabel":"Gemini 2.5 Pro (Thinking 32K)","configuration":"Gemini 2.5 Pro (Thinking 32K); Source model ID: gemini-2-5-pro-2025-06-17-thinking-32k; 120 tasks","score":4.859999999999999,"warning":null},{"id":"076c87b82049cfa2ea7b9df0","modelId":"gemini-3-flash-preview","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":55.6666666666667,"warning":null},{"id":"162b72dff2b62a478a4e3d38","modelId":"gemini-3-flash-preview","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":97,"warning":null},{"id":"b3a845d5ca338864a0c68e84","modelId":"gemini-3-flash-preview","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":27.728613569321496,"warning":null},{"id":"5e4484b725f885d1ff5e913f","modelId":"gemini-3-flash-preview","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":55.3333333333333,"warning":null},{"id":"681dcd67742f3fabcb4e8443","modelId":"gemini-3-flash-preview","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":78,"warning":null},{"id":"b771ca3369e45caa49d4b3fe","modelId":"gemini-3-flash-preview","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":1.42857142857143,"warning":null},{"id":"862b3fc84116cb2abfb29a11","modelId":"gemini-3-flash-preview","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":8.57142857142857,"warning":null},{"id":"766bfc6c0bb47794ea896d7c","modelId":"gemini-3-flash-preview","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":92.74999999999999,"warning":null},{"id":"f0939c33b02de61e8d2569c0","modelId":"gemini-3-flash-preview","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":91.4375,"warning":null},{"id":"d45eab2a552c001f2dbdb704","modelId":"gemini-3-flash-preview","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":81.2121212121212,"warning":null},{"id":"5177df7f65f8989816e07078","modelId":"gemini-3-flash-preview","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":89.79797979797979,"warning":null},{"id":"5a0c8bdb65808c38cc8c6ba8","modelId":"gemini-3-flash-preview","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":14.967562557924,"warning":null},{"id":"f524fa4818eae0de4de4b842","modelId":"gemini-3-flash-preview","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":36.5616311399444,"warning":null},{"id":"8d1a6871f955048317879ba7","modelId":"gemini-3-flash-preview","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":55.1020408163265,"warning":null},{"id":"fe637f0f65778514caf29868","modelId":"gemini-3-flash-preview","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":77.9591836734694,"warning":null},{"id":"3877c7c555480e56e2553353","modelId":"gemini-3-flash-preview","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":79.6825396825397,"warning":null},{"id":"afb2c3230511cde285428634","modelId":"gemini-3-flash-preview","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":90.7936507936508,"warning":null},{"id":"65ec7e6d31d6f6ce02771c4b","modelId":"gemini-3-flash-preview","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":11.6666666666667,"warning":null},{"id":"91700195796ca55967f40f20","modelId":"gemini-3-flash-preview","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":11.1111111111111,"warning":null},{"id":"7161c5ae63b41bca96c70974","modelId":"gemini-3-flash-preview","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":88.2230718085106,"warning":null},{"id":"a699cac3b6da2ec95d940e1a","modelId":"gemini-3-flash-preview","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":89.0292553191489,"warning":null},{"id":"1db4c190ae70acb2a1c1a232","modelId":"gemini-3-flash-preview","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":78.5549132947977,"warning":null},{"id":"57c50354c54c32290ddfc4c1","modelId":"gemini-3-flash-preview","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":79.9421965317919,"warning":null},{"id":"e31d78ed7068e350eae0e017","modelId":"gemini-3-flash-preview","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":-4.31666666666667,"warning":null},{"id":"31aec0c830003796ddb584fb","modelId":"gemini-3-flash-preview","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":10.1333333333333,"warning":null},{"id":"9fae7f3a431a07e9ef03a649","modelId":"gemini-3-flash-preview","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":45.78333333333333,"warning":null},{"id":"6ca294472ce7424a59037593","modelId":"gemini-3-flash-preview","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":53.43333333333333,"warning":null},{"id":"090d329b550ff7c39b218328","modelId":"gemini-3-flash-preview","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":43.2748538011696,"warning":null},{"id":"cb0e8ee7331851f023b16462","modelId":"gemini-3-flash-preview","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":80.4093567251462,"warning":null},{"id":"216792d88d988a2e05a41153","modelId":"gemini-3-flash-preview","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":20.8247422680412,"warning":null},{"id":"66bd4898aef466d04784881c","modelId":"gemini-3-flash-preview","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemini 3 Flash Preview (Non-reasoning)","configuration":"Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash","score":31.818181818181802,"warning":null},{"id":"f07bd2d137eff751c94e16e4","modelId":"gemini-3-flash-preview","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemini 3 Flash Preview (Reasoning)","configuration":"Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning","score":38.636363636363605,"warning":null},{"id":"da304a0f8d4e4dc282b7a95b","modelId":"gemini-3-flash-preview","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Gemini 3 Flash Preview (High)","configuration":"Gemini 3 Flash Preview (High); Source model ID: gemini-3-flash-preview-thinking-high; 120 tasks","score":33.61,"warning":null},{"id":"8f72a698e068a7bc179feb19","modelId":"gemini-3-flash-preview","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Gemini 3 Flash Preview (Low)","configuration":"Gemini 3 Flash Preview (Low); Source model ID: gemini-3-flash-preview-thinking-low; 120 tasks","score":1.25,"warning":null},{"id":"c3906ea3a7c1254fb6ccba8d","modelId":"gemini-3-flash-preview","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Gemini 3 Flash Preview (Medium)","configuration":"Gemini 3 Flash Preview (Medium); Source model ID: gemini-3-flash-preview-thinking-medium; 120 tasks","score":12.78,"warning":null},{"id":"f433631bd967cd374a5a92a9","modelId":"gemini-3-flash-preview","benchmarkId":"arc-v2semiprivate","level":"minimal","sourceLabel":"Gemini 3 Flash Preview (Minimal)","configuration":"Gemini 3 Flash Preview (Minimal); Source model ID: gemini-3-flash-preview-thinking-minimal; 120 tasks","score":3.3300000000000005,"warning":null},{"id":"9ed78211ce574b898ce5c37e","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.75,"warning":null},{"id":"fb38f5a1da43f9f671c2940b","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":226.15,"warning":null},{"id":"95738bc56bfab2218391b063","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.168141592920401,"warning":null},{"id":"e51ce9e31d112599849140e1","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.3333333333333,"warning":null},{"id":"542af94496db9fff0c50c33b","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.796182033119545,"warning":null},{"id":"1f43c952940a4b6d26d536be","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.1428571428571401,"warning":null},{"id":"8416976c2cf8e61964b2a869","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.02148612354521,"warning":null},{"id":"866f484125051166bc2e4453","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.8,"warning":null},{"id":"3435307b024c7565dbd94fc7","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":595.99,"warning":null},{"id":"f39228d0894775a799d9e673","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.2222222222222,"warning":null},{"id":"02998383bd3440afe47af683","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.1477782602403,"warning":null},{"id":"a500a1b31b9c03cf2da51aa8","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.191844300278,"warning":null},{"id":"96ee84a5b928f3599cf5d764","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.2108843537415,"warning":null},{"id":"4aae5d6df970c338630860a9","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.11111111111111,"warning":null},{"id":"334d043fe09ccc4d1fdbf484","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.5491329479769,"warning":null},{"id":"897f612ed5343edc51d5b099","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":-16.4166666666667,"warning":null},{"id":"4bc71b7684588e825fa67080","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.266666666666666,"warning":null},{"id":"097b9973b90993f5f5e7d1df","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.4027777777778,"warning":null},{"id":"bf184358925df7a4fbedf4bc","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.2865497076023,"warning":null},{"id":"2684a58ff4342575f23cbc46","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.69072164948454,"warning":null},{"id":"29f5bb04ad1bd05a7465f796","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.2424242424242,"warning":null},{"id":"37c6a530f1ded7b9888ea2c3","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.0861423220974,"warning":null},{"id":"a09a2ae31ee117af6ce3dddb","modelId":"gemini-3.1-flash-lite","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Gemini 3.1 Flash-Lite","configuration":"Gemini 3.1 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.505050505050505,"warning":null},{"id":"7c7f774514f7fa2297208e0f","modelId":"gemini-3.1-pro","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.25,"warning":null},{"id":"b06e9c41fbb683c7a2f4f192","modelId":"gemini-3.1-pro","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":458.83,"warning":null},{"id":"37687afd20028c6089e77920","modelId":"gemini-3.1-pro","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.0058997050148,"warning":null},{"id":"5f4e475d1f8d57db24bcb7a6","modelId":"gemini-3.1-pro","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":82,"warning":null},{"id":"db8f74e2e14e95ffdcaeb92d","modelId":"gemini-3.1-pro","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.427718398098364,"warning":null},{"id":"fa3f112c9b6e79acc46b504f","modelId":"gemini-3.1-pro","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.714285714285698,"warning":null},{"id":"93374c1590601b233140cd4a","modelId":"gemini-3.1-pro","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.166517457475386,"warning":null},{"id":"8063177a2a63d1be8648e2f8","modelId":"gemini-3.1-pro","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.8,"warning":null},{"id":"369dcfed5847bd7a41289d20","modelId":"gemini-3.1-pro","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":903.94,"warning":null},{"id":"39bf8cf4de7d4ae5d9295e26","modelId":"gemini-3.1-pro","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":93.16666666666666,"warning":null},{"id":"a3fd1ba1d2b182c00683d93b","modelId":"gemini-3.1-pro","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":94.1414141414141,"warning":null},{"id":"f119405d93465a62350dc255","modelId":"gemini-3.1-pro","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.8507743522941,"warning":null},{"id":"b3631e2d668ca3ff2ebfe823","modelId":"gemini-3.1-pro","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.0342910101946,"warning":null},{"id":"9aa04e6ff77c61f9b93c9290","modelId":"gemini-3.1-pro","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.1428571428571,"warning":null},{"id":"5c7f8cd7187c61c11375f19b","modelId":"gemini-3.1-pro","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.3309120258273,"warning":null},{"id":"208c2682d2e878ad0bfc59b4","modelId":"gemini-3.1-pro","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.5555555555556,"warning":null},{"id":"45e4f876ba3f9fcf04c8c5fa","modelId":"gemini-3.1-pro","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.4277456647399,"warning":null},{"id":"6a904d86ad7c12c3aac7713b","modelId":"gemini-3.1-pro","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.8833333333333,"warning":null},{"id":"24d00d3350012cb696297151","modelId":"gemini-3.1-pro","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.85,"warning":null},{"id":"72fd11da3d45e05f88f9fba5","modelId":"gemini-3.1-pro","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.6805555555556,"warning":null},{"id":"1d824de33344d5f7c900a32c","modelId":"gemini-3.1-pro","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":95.6140350877193,"warning":null},{"id":"6d20dfb2c84bb4190f7edf29","modelId":"gemini-3.1-pro","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.4432989690722,"warning":null},{"id":"f78b4be38ed10e8ddcd80664","modelId":"gemini-3.1-pro","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":53.787878787878796,"warning":null},{"id":"154ebcd0575e2428b67b2398","modelId":"gemini-3.1-pro","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.78277153558051,"warning":null},{"id":"fd2e6ea2003857920a1bdfcf","modelId":"gemini-3.1-pro","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Gemini 3.1 Pro Preview","configuration":"Gemini 3.1 Pro Preview; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-1-pro-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.04040404040404,"warning":null},{"id":"db901e8199046d5c8d479ba0","modelId":"gemini-3.1-pro","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gemini-3-1-pro-preview","configuration":"gemini-3-1-pro-preview; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":11.7,"warning":null},{"id":"8f6dd87d3bec8be094065e59","modelId":"gemini-3.1-pro","benchmarkId":"swepro-minisweagentstarredrows","level":"thinking","sourceLabel":"gemini-3.1-pro (thinking)*","configuration":"gemini-3.1-pro (thinking)*; 731 tasks; source date 2026-04-08","score":46.1,"warning":null},{"id":"09a429372313877fb69d9077","modelId":"gemini-3.1-pro","benchmarkId":"terminal-geminicli","level":"high","sourceLabel":"Gemini 3.1 Pro","configuration":"Gemini 3.1 Pro; Reported effort: high; 445 trials; recorded 2026-02-19","score":65.84,"warning":null},{"id":"a01dc047adae16bf8c7acb63","modelId":"gemini-3.1-pro","benchmarkId":"terminal-terminus2","level":"high","sourceLabel":"Gemini 3.1 Pro","configuration":"Gemini 3.1 Pro; Reported effort: high; 445 trials; recorded 2026-02-19","score":65.62,"warning":null},{"id":"48c0d21f430546e8b664e36e","modelId":"gemini-3.5-flash","benchmarkId":"aa-aa-analyst-agent","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":45,"warning":null},{"id":"832b5d2faac682af2778bb8f","modelId":"gemini-3.5-flash","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":869.74,"warning":null},{"id":"f0700ff7cd391b4c306b5da1","modelId":"gemini-3.5-flash","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":870.71,"warning":null},{"id":"2fa218e0cf898a409b6950ed","modelId":"gemini-3.5-flash","benchmarkId":"aa-apex-agents-aa","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":47.0501474926254,"warning":null},{"id":"bcf5c26a7ddbb18487aaa05c","modelId":"gemini-3.5-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":73.3333333333333,"warning":null},{"id":"921be86f7b8792e802437eff","modelId":"gemini-3.5-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":74.3333333333333,"warning":null},{"id":"8e65297694f3500bd1feb181","modelId":"gemini-3.5-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":61.33333333333329,"warning":null},{"id":"917db71bf57d80367ae8bfd5","modelId":"gemini-3.5-flash","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":42.07973565652745,"warning":null},{"id":"4b0114a88e6b6714abe361aa","modelId":"gemini-3.5-flash","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":13.1428571428571,"warning":null},{"id":"5b35874c17908b217e3f71aa","modelId":"gemini-3.5-flash","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":10.8571428571429,"warning":null},{"id":"dd1feb290814181d6c5dd6c7","modelId":"gemini-3.5-flash","benchmarkId":"aa-critpt","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":1.42857142857143,"warning":null},{"id":"e90839926b182c19b92db90f","modelId":"gemini-3.5-flash","benchmarkId":"aa-enterprise-ops-gym-aa","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":50.07460459564309,"warning":null},{"id":"464626e6d0154934d2a6e655","modelId":"gemini-3.5-flash","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":19.8,"warning":null},{"id":"5d2eedb5e7f7997fccd036ec","modelId":"gemini-3.5-flash","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":1259.06,"warning":null},{"id":"0ef4ba55001e85543ca153ea","modelId":"gemini-3.5-flash","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":92.2222222222222,"warning":null},{"id":"cb5a3a6576ceb4adb3c8df02","modelId":"gemini-3.5-flash","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":92.12121212121211,"warning":null},{"id":"d007c9e0b18cd0ddd4703b50","modelId":"gemini-3.5-flash","benchmarkId":"aa-gpqa-diamond","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":82.8282828282828,"warning":null},{"id":"b58ff93118c3e42b1754d425","modelId":"gemini-3.5-flash","benchmarkId":"aa-harvey-lab-aa","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":82.0813431755681,"warning":null},{"id":"a1c845fdb2e5b52dfe9e7a72","modelId":"gemini-3.5-flash","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":42.678405931418,"warning":null},{"id":"b9a0dc10839ac43723ac2505","modelId":"gemini-3.5-flash","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":41.3345690454124,"warning":null},{"id":"bb0b2ca6de9c6338eead631b","modelId":"gemini-3.5-flash","benchmarkId":"aa-humanitys-last-exam","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":24.0963855421687,"warning":null},{"id":"1db5c743173591e43f7f5c1a","modelId":"gemini-3.5-flash","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":76.32653061224491,"warning":null},{"id":"dc28dff3ff295e97d2349723","modelId":"gemini-3.5-flash","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":74.5578231292517,"warning":null},{"id":"590ddab9886c546ab0d14b7c","modelId":"gemini-3.5-flash","benchmarkId":"aa-ifbench","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":47.2789115646259,"warning":null},{"id":"8428a80e7390cee8670bbddd","modelId":"gemini-3.5-flash","benchmarkId":"aa-itbench-aa","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":40.3483992467043,"warning":null},{"id":"dad0aa507881840bac4cab00","modelId":"gemini-3.5-flash","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":18.3333333333333,"warning":null},{"id":"a771020cca119625e60aaadd","modelId":"gemini-3.5-flash","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":84.2774566473988,"warning":null},{"id":"35c03f5c2529a7110f27178b","modelId":"gemini-3.5-flash","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":83.8728323699422,"warning":null},{"id":"cfd513399a8483ae072d0f2b","modelId":"gemini-3.5-flash","benchmarkId":"aa-mmmu-pro","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":80.1156069364162,"warning":null},{"id":"8591301a5ba5c21a75e096ac","modelId":"gemini-3.5-flash","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":21.1833333333333,"warning":null},{"id":"43b3aefe7350df929f9338ae","modelId":"gemini-3.5-flash","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":20.8166666666667,"warning":null},{"id":"2bcf32e69932a11f901a5098","modelId":"gemini-3.5-flash","benchmarkId":"aa-omniscience","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":0.666666666666667,"warning":null},{"id":"98ac17a806eee8aa49717aff","modelId":"gemini-3.5-flash","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":51.4,"warning":null},{"id":"1a8897c73ef4384656620585","modelId":"gemini-3.5-flash","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":51.05,"warning":null},{"id":"2412d1136cc38ada8c6b745a","modelId":"gemini-3.5-flash","benchmarkId":"aa-omniscience-accuracy","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":43.016666666666666,"warning":null},{"id":"b2d64f49b13cffb585e68d94","modelId":"gemini-3.5-flash","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":53.9351851851852,"warning":null},{"id":"5995551cd29bfab0e3cc8de4","modelId":"gemini-3.5-flash","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":95.3216374269006,"warning":null},{"id":"ed3e1c0e64e9cfa96b91e340","modelId":"gemini-3.5-flash","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":95.6140350877193,"warning":null},{"id":"2d3d9672d6f1a58a61fceace","modelId":"gemini-3.5-flash","benchmarkId":"aa-tau2-bench","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":58.7719298245614,"warning":null},{"id":"da70a188d3e459342f2a34f6","modelId":"gemini-3.5-flash","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":32.1649484536082,"warning":null},{"id":"df563aa32b42e8f9d09508eb","modelId":"gemini-3.5-flash","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":40.9090909090909,"warning":null},{"id":"0c8c9a8ad3983efe4fdd3bcb","modelId":"gemini-3.5-flash","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"Gemini 3.5 Flash (medium)","configuration":"Gemini 3.5 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-medium","score":39.3939393939394,"warning":null},{"id":"5c81bad7ecf4502ae991784d","modelId":"gemini-3.5-flash","benchmarkId":"aa-terminalbench-hard","level":"minimal","sourceLabel":"Gemini 3.5 Flash (minimal)","configuration":"Gemini 3.5 Flash (minimal); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-minimal","score":46.2121212121212,"warning":null},{"id":"588473cbcd9f97a6d2d1c049","modelId":"gemini-3.5-flash","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":78.65168539325839,"warning":null},{"id":"6217a48cc35c3658cab6318f","modelId":"gemini-3.5-flash","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"Gemini 3.5 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-5-flash","score":6.56565656565657,"warning":null},{"id":"fb38b0f3dad2c23ea05267b5","modelId":"gemini-3.5-flash","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Gemini 3.5 Flash (High)","configuration":"Gemini 3.5 Flash (High); Source model ID: gemini-3-5-flash-high; 120 tasks","score":72.08,"warning":null},{"id":"0e2bb982e97ed49d227de10d","modelId":"gemini-3.5-flash","benchmarkId":"arc-v2semiprivate","level":"minimal","sourceLabel":"Gemini 3.5 Flash (Minimal)","configuration":"Gemini 3.5 Flash (Minimal); Source model ID: gemini-3-5-flash-minimal; 120 tasks","score":8.89,"warning":null},{"id":"d995aaf1dca8340a4a693d8a","modelId":"gemini-3.5-flash","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gemini-3-5-flash","configuration":"gemini-3-5-flash; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":36.1,"warning":null},{"id":"581ccc3575dba857c4980929","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":645.32,"warning":null},{"id":"aa3e7986ac74b1d41c049659","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":76,"warning":null},{"id":"14a902d4f36d2bebe6ff22a0","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":25.011270511840955,"warning":null},{"id":"2e8ef8685e32a69af902f783","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"93f57b1a7efa63a3d40f7270","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.345568487018795,"warning":null},{"id":"ae13f406495e677556b5a0c3","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.600000000000001,"warning":null},{"id":"7d41ac4cda47841b9af63236","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":1063.25,"warning":null},{"id":"bf28d2d6dffc1a351c70a760","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":83.8383838383838,"warning":null},{"id":"a1cfe34cd9aecb7162043dcc","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.813716404077798,"warning":null},{"id":"fc74bcb7728d73322b4c984c","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.2222222222222205,"warning":null},{"id":"fcc617a3338c6253fdf4353c","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.0173410404624,"warning":null},{"id":"2996b27e98c9a488eb6dd898","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.23333333333333,"warning":null},{"id":"199cbf5b9764d44dc0a19484","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.46666666666667,"warning":null},{"id":"26f351bc48bbc25a81380a4b","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.3194444444444,"warning":null},{"id":"ae5702c7b4374ba438f5ea3d","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.5257731958763,"warning":null},{"id":"f3e410a3346994f7eea97dc6","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":53.558052434456904,"warning":null},{"id":"e253ea51b6a540f66de5395f","modelId":"gemini-3.5-flash-lite","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Gemini 3.5 Flash-Lite","configuration":"Gemini 3.5 Flash-Lite; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-3-5-flash-lite; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.01010101010101,"warning":null},{"id":"8b0081bbd7294e66bbccf771","modelId":"gemini-3.5-flash-lite","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Gemini 3.5 Flash-Lite (High)","configuration":"Gemini 3.5 Flash-Lite (High); Source model ID: gemini-3-5-flash-lite-high; 120 tasks","score":10.277777777777779,"warning":null},{"id":"673c903462f2e3ace1f8a3a5","modelId":"gemini-3.5-flash-lite","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Gemini 3.5 Flash-Lite (Low)","configuration":"Gemini 3.5 Flash-Lite (Low); Source model ID: gemini-3-5-flash-lite-low; 120 tasks","score":1.5277777777777777,"warning":null},{"id":"38942fa126421e15bf1592ee","modelId":"gemini-3.5-flash-lite","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Gemini 3.5 Flash-Lite (Medium)","configuration":"Gemini 3.5 Flash-Lite (Medium); Source model ID: gemini-3-5-flash-lite-medium; 120 tasks","score":5.277777777777778,"warning":null},{"id":"f591fd70b9b02e903ae88a25","modelId":"gemini-3.5-flash-lite","benchmarkId":"arc-v2semiprivate","level":"minimal","sourceLabel":"Gemini 3.5 Flash-Lite (Minimal)","configuration":"Gemini 3.5 Flash-Lite (Minimal); Source model ID: gemini-3-5-flash-lite-minimal; 120 tasks","score":0.8333333333333334,"warning":null},{"id":"0d2bef889970f2b2e07886ac","modelId":"gemini-3.6-flash","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":952.75,"warning":null},{"id":"02af98883e86e08c7d0d14b2","modelId":"gemini-3.6-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":80,"warning":null},{"id":"b50c064c019434c76349a34e","modelId":"gemini-3.6-flash","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":53.01669491509355,"warning":null},{"id":"72c53815d6f2e5985dc88b2e","modelId":"gemini-3.6-flash","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":10.5714285714286,"warning":null},{"id":"d0973640464da38626274814","modelId":"gemini-3.6-flash","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":17.4,"warning":null},{"id":"eb531999926abd475dd85d12","modelId":"gemini-3.6-flash","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":1331.37,"warning":null},{"id":"30e71b2d4dac7faf9d150a7e","modelId":"gemini-3.6-flash","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":92.82828282828281,"warning":null},{"id":"956c95bb8e0b490a259250c3","modelId":"gemini-3.6-flash","benchmarkId":"aa-harvey-lab-aa","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":85.1498046026921,"warning":null},{"id":"9e22f9c6c9fb4eb1d727f54c","modelId":"gemini-3.6-flash","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":40.824837812789596,"warning":null},{"id":"bef04938effbeeff2ad67939","modelId":"gemini-3.6-flash","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":14.444444444444398,"warning":null},{"id":"f4c925125109603e5ab10dd8","modelId":"gemini-3.6-flash","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":83.2369942196532,"warning":null},{"id":"01c9c562ca1e20be38366b5e","modelId":"gemini-3.6-flash","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":22.1333333333333,"warning":null},{"id":"0ec0fd270fa75ee2504d1492","modelId":"gemini-3.6-flash","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":49.96666666666666,"warning":null},{"id":"0e4d77610ce1730581d1461a","modelId":"gemini-3.6-flash","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":53.3564814814815,"warning":null},{"id":"7ffc630ea762d5a97e563372","modelId":"gemini-3.6-flash","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":29.8969072164948,"warning":null},{"id":"ab54c861e14442ee403959a2","modelId":"gemini-3.6-flash","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":77.52808988764049,"warning":null},{"id":"567b11a1bef86be59583e08b","modelId":"gemini-3.6-flash","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"Gemini 3.6 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-6-flash","score":7.07070707070707,"warning":null},{"id":"a40850daad4b8e157f489b7d","modelId":"gemini-3.6-flash","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Gemini 3.6 Flash (High)","configuration":"Gemini 3.6 Flash (High); Source model ID: gemini-3-6-flash-high; 120 tasks","score":60.416666666666664,"warning":null},{"id":"05c31f600e16e2079feb1579","modelId":"gemini-3.6-flash","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Gemini 3.6 Flash (Low)","configuration":"Gemini 3.6 Flash (Low); Source model ID: gemini-3-6-flash-low; 120 tasks","score":30.416666666666664,"warning":null},{"id":"3965013d4d14d4352a1e30c3","modelId":"gemini-3.6-flash","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Gemini 3.6 Flash (Medium)","configuration":"Gemini 3.6 Flash (Medium); Source model ID: gemini-3-6-flash-medium; 120 tasks","score":50.416666666666664,"warning":null},{"id":"d701fa1ba2e4bdda269e42e3","modelId":"gemini-3.6-flash","benchmarkId":"arc-v2semiprivate","level":"minimal","sourceLabel":"Gemini 3.6 Flash (Minimal)","configuration":"Gemini 3.6 Flash (Minimal); Source model ID: gemini-3-6-flash-minimal; 120 tasks","score":2.638888888888889,"warning":null},{"id":"c81497e333fcbd26ddd6cc87","modelId":"gemini-3.6-flash","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gemini-3-6-flash","configuration":"gemini-3-6-flash; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":46.7,"warning":null},{"id":"2ffc6e719db431730b9a76d2","modelId":"gemini-3.7-flash","benchmarkId":"aa-aa-analyst-agent","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":60,"warning":null},{"id":"15fcc7b3d81479e0cc30ec90","modelId":"gemini-3.7-flash","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":1115.67,"warning":null},{"id":"d9f672a5f7f4a4ed529fc3c0","modelId":"gemini-3.7-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":81.6666666666667,"warning":null},{"id":"3d3e98fc6c09a465346ff045","modelId":"gemini-3.7-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":78.6666666666667,"warning":null},{"id":"7b18453959beabe4bebe0683","modelId":"gemini-3.7-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":83,"warning":null},{"id":"7bc1e313c94fe673b2f5922f","modelId":"gemini-3.7-flash","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":62.02749292053469,"warning":null},{"id":"cf96594b0ed1f96377909640","modelId":"gemini-3.7-flash","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":14.285714285714299,"warning":null},{"id":"dfbce63c7307804098e6a934","modelId":"gemini-3.7-flash","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":5.71428571428571,"warning":null},{"id":"02a82960bc44c535be451a94","modelId":"gemini-3.7-flash","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":9.42857142857143,"warning":null},{"id":"763a8c264e79f3dfd28feea7","modelId":"gemini-3.7-flash","benchmarkId":"aa-enterprise-ops-gym-aa","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":50.40286481647269,"warning":null},{"id":"623b9bf3960dd897e5d3a62b","modelId":"gemini-3.7-flash","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":23.599999999999998,"warning":null},{"id":"335f683b38de6b878c93a2de","modelId":"gemini-3.7-flash","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":1433.14,"warning":null},{"id":"8daadf8e459cc18a9edb5539","modelId":"gemini-3.7-flash","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":1354.06,"warning":null},{"id":"e20b3c33a214f6c253b39d83","modelId":"gemini-3.7-flash","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":1406.6,"warning":null},{"id":"033e1bceeaf591f76562b322","modelId":"gemini-3.7-flash","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":94.5454545454545,"warning":null},{"id":"3cb5439ae05f88b975030a3d","modelId":"gemini-3.7-flash","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":90.1010101010101,"warning":null},{"id":"3fb858efa3a20cfc576dee30","modelId":"gemini-3.7-flash","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":92.12121212121211,"warning":null},{"id":"0dc2d6f01a20b073316891ed","modelId":"gemini-3.7-flash","benchmarkId":"aa-harvey-lab-aa","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":90.6643508467217,"warning":null},{"id":"d0e918b40a70a3fc785372aa","modelId":"gemini-3.7-flash","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":47.8683966635774,"warning":null},{"id":"1eadf639a7b64077516b415a","modelId":"gemini-3.7-flash","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":35.1251158480074,"warning":null},{"id":"6a7cad906a57f42cc02339f5","modelId":"gemini-3.7-flash","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":38.9712696941613,"warning":null},{"id":"38e737a0e552ebb4ef35e0a0","modelId":"gemini-3.7-flash","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":15,"warning":null},{"id":"d3eb581d14d32fb68f0df6ff","modelId":"gemini-3.7-flash","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":85.4913294797688,"warning":null},{"id":"8854a52a87268c9344295da4","modelId":"gemini-3.7-flash","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":84.8554913294798,"warning":null},{"id":"7efd00c773b07079aae442c1","modelId":"gemini-3.7-flash","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":84.7398843930636,"warning":null},{"id":"d286dd08c71ca1a94b6b4312","modelId":"gemini-3.7-flash","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":26.4833333333333,"warning":null},{"id":"2165aa4444d69b835f683bdf","modelId":"gemini-3.7-flash","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":22.1333333333333,"warning":null},{"id":"cca0a6b63d00776b6e87dae5","modelId":"gemini-3.7-flash","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":23.7,"warning":null},{"id":"227c852a7bff02f6f5ca567b","modelId":"gemini-3.7-flash","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":55.31666666666667,"warning":null},{"id":"7e813c8a37564aff5565dbde","modelId":"gemini-3.7-flash","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":53.56666666666666,"warning":null},{"id":"e0dfe712d13607e0f7d46c60","modelId":"gemini-3.7-flash","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":54,"warning":null},{"id":"99981533fdcbe148dc5a8339","modelId":"gemini-3.7-flash","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":57.175925925925895,"warning":null},{"id":"6468affea290ffe50d9864d4","modelId":"gemini-3.7-flash","benchmarkId":"aa-scicode","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":55.671296296296305,"warning":null},{"id":"d9c3b38b79987468d416a723","modelId":"gemini-3.7-flash","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":59.837962962963,"warning":null},{"id":"d7975b0656398a8aaca18ed7","modelId":"gemini-3.7-flash","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":32.7835051546392,"warning":null},{"id":"d3ef65f4bf0e05d2f9d76fcc","modelId":"gemini-3.7-flash","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":29.4845360824742,"warning":null},{"id":"78d7af9f4fc293caa27736b8","modelId":"gemini-3.7-flash","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":35.4639175257732,"warning":null},{"id":"da8576588c7b0a1eab39f8c5","modelId":"gemini-3.7-flash","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":85.76779026217231,"warning":null},{"id":"c81592af7ed61ce7169fc91b","modelId":"gemini-3.7-flash","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"Gemini 3.7 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low","score":79.7752808988764,"warning":null},{"id":"64fef02ab879ce4a145da39c","modelId":"gemini-3.7-flash","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"Gemini 3.7 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium","score":78.2771535580524,"warning":null},{"id":"548e1414ba9f0cf973c69518","modelId":"gemini-3.7-flash","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Gemini 3.7 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash","score":13.6363636363636,"warning":null},{"id":"1e7c651364e9ee25998857ec","modelId":"gemini-3.7-flash","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Gemini 3.7 Flash (High)","configuration":"Gemini 3.7 Flash (High); Source model ID: google-gemini-3-7-flash-high; 120 tasks","score":84.58333333333333,"warning":null},{"id":"c66a9ac890388e11ea72db7a","modelId":"gemini-3.7-flash","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Gemini 3.7 Flash (Low)","configuration":"Gemini 3.7 Flash (Low); Source model ID: google-gemini-3-7-flash-low; 120 tasks","score":52.916666666666664,"warning":null},{"id":"198d114dc938db6f199de747","modelId":"gemini-3.7-flash","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Gemini 3.7 Flash (Medium)","configuration":"Gemini 3.7 Flash (Medium); Source model ID: google-gemini-3-7-flash-medium; 120 tasks","score":63.74999999999999,"warning":null},{"id":"b75fe3ec33c013c7d01ac1f8","modelId":"gemini-3.7-flash","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gemini-3-7-flash","configuration":"gemini-3-7-flash; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":65.3,"warning":null},{"id":"0a8c13fbff0cf24590cc04f5","modelId":"gemini-3.7-flash","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"gemini-3-7-flash","configuration":"gemini-3-7-flash; Reported effort: low; 113 unique tasks; 452 attempts; 4 runs","score":53.8,"warning":null},{"id":"3ee91dfd4e3a98ca959ff95c","modelId":"gemini-3.7-flash","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"gemini-3-7-flash","configuration":"gemini-3-7-flash; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs","score":65.5,"warning":null},{"id":"7d0702eeff3949dd042a2fa3","modelId":"gemini-3.8-flash","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":1201.59,"warning":null},{"id":"c34c178b65592e795b4ce504","modelId":"gemini-3.8-flash","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":1055.59,"warning":null},{"id":"3d14c6c4c0ac850e9893270a","modelId":"gemini-3.8-flash","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":1176.54,"warning":null},{"id":"fa03d1f1eab99dcae29627e6","modelId":"gemini-3.8-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":81.3333333333333,"warning":null},{"id":"bb5a47af5bbb05252e36909c","modelId":"gemini-3.8-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":80.6666666666667,"warning":null},{"id":"a8913d162877cdf204b25cf8","modelId":"gemini-3.8-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":84,"warning":null},{"id":"c3d11b8510947a6f385c2981","modelId":"gemini-3.8-flash","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":59.93009432118242,"warning":null},{"id":"0375b76709103c37e2772339","modelId":"gemini-3.8-flash","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":36.509404614862525,"warning":null},{"id":"4e4cf4aefdb6627276b41de9","modelId":"gemini-3.8-flash","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":60.8899739211415,"warning":null},{"id":"d8116ad936926f7e5d42cfc6","modelId":"gemini-3.8-flash","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":18.2857142857143,"warning":null},{"id":"fce47e70c8b6a91358f037ac","modelId":"gemini-3.8-flash","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":4,"warning":null},{"id":"dd1501b4ee4241b7a2f2fc55","modelId":"gemini-3.8-flash","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":12.285714285714299,"warning":null},{"id":"9e224dfcbf47d68bf41d3b8b","modelId":"gemini-3.8-flash","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":21,"warning":null},{"id":"0a003ed6d7d4810443711338","modelId":"gemini-3.8-flash","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":18.6,"warning":null},{"id":"ece8a1e32a834fb3846d3e2b","modelId":"gemini-3.8-flash","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":22.8,"warning":null},{"id":"5ee89d80876b2c8b5dbc820c","modelId":"gemini-3.8-flash","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":1463.81,"warning":null},{"id":"74ee4b8771de4179c255f519","modelId":"gemini-3.8-flash","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":1358.55,"warning":null},{"id":"443b3e01dacbb5afc498695b","modelId":"gemini-3.8-flash","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":1455.38,"warning":null},{"id":"015e3e9bffa0ff59feb7dba4","modelId":"gemini-3.8-flash","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":95.2525252525253,"warning":null},{"id":"245d13fe1bdcddee2cf1de6a","modelId":"gemini-3.8-flash","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":92.020202020202,"warning":null},{"id":"1e0e5dfe41adf43f56eca928","modelId":"gemini-3.8-flash","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":93.53535353535351,"warning":null},{"id":"ff15412b30403c3252d273d1","modelId":"gemini-3.8-flash","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":47.8220574606117,"warning":null},{"id":"36d7ccd405b78c98c664c26d","modelId":"gemini-3.8-flash","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":37.0713623725672,"warning":null},{"id":"ab851146f8ddd99d32600bc8","modelId":"gemini-3.8-flash","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":42.122335495829496,"warning":null},{"id":"9c64bb74f8fe5f3043682b5a","modelId":"gemini-3.8-flash","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":21.6666666666667,"warning":null},{"id":"b8c59f541f7805b02740779b","modelId":"gemini-3.8-flash","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":85.606936416185,"warning":null},{"id":"b15f5d90d3ee83a48e00ec0e","modelId":"gemini-3.8-flash","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":84.5086705202312,"warning":null},{"id":"311f120c93ce87f66d442b9c","modelId":"gemini-3.8-flash","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":84.2196531791908,"warning":null},{"id":"b362fc4da74b513f0c9e56aa","modelId":"gemini-3.8-flash","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":29.55,"warning":null},{"id":"349a9170a6967dde2f69d616","modelId":"gemini-3.8-flash","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":21.35,"warning":null},{"id":"29918922aae0f8078778c893","modelId":"gemini-3.8-flash","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":28.5833333333333,"warning":null},{"id":"ee812a20006b312bf3a9ead1","modelId":"gemini-3.8-flash","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":54.6,"warning":null},{"id":"a187fa977e12f34c4e80fd19","modelId":"gemini-3.8-flash","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":52.21666666666667,"warning":null},{"id":"bb26375ac1e276d6bde537c4","modelId":"gemini-3.8-flash","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":52.983333333333334,"warning":null},{"id":"08294d5a9e316499d4fa619e","modelId":"gemini-3.8-flash","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":56.5972222222222,"warning":null},{"id":"349131d8d0617e56a85bc759","modelId":"gemini-3.8-flash","benchmarkId":"aa-scicode","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":54.976851851851805,"warning":null},{"id":"1a76f4a4ebb003dfa2f1e2a8","modelId":"gemini-3.8-flash","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":55.0925925925926,"warning":null},{"id":"631bc4c0ebce57b5312a5f98","modelId":"gemini-3.8-flash","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":44.948453608247405,"warning":null},{"id":"8f6dd3569c76f245c1790da2","modelId":"gemini-3.8-flash","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":33.1958762886598,"warning":null},{"id":"52f48c58bd80ba863f55dc0e","modelId":"gemini-3.8-flash","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":45.7731958762887,"warning":null},{"id":"12cd11cee76cf6a4c36e0087","modelId":"gemini-3.8-flash","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":87.6404494382023,"warning":null},{"id":"ee28fa94d3de082b63c35438","modelId":"gemini-3.8-flash","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":83.1460674157303,"warning":null},{"id":"bc03c5fa8f7705011b0cc961","modelId":"gemini-3.8-flash","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":83.8951310861423,"warning":null},{"id":"0c3c62c25ba7e7bb7bb448f6","modelId":"gemini-3.8-flash","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Gemini 3.8 Flash (high); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash","score":19.6969696969697,"warning":null},{"id":"388ac9f7e08ee8daaaa73970","modelId":"gemini-3.8-flash","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"Gemini 3.8 Flash (low)","configuration":"Gemini 3.8 Flash (low); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-low","score":10.1010101010101,"warning":null},{"id":"be8f73138f8e1ba0c8ebc015","modelId":"gemini-3.8-flash","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"Gemini 3.8 Flash (medium); Model source: https://artificialanalysis.ai/models/gemini-3-8-flash-medium","score":19.6969696969697,"warning":null},{"id":"405dcd6b0cb92b2c4c19515e","modelId":"gemini-3.8-flash","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gemini-3-8-flash","configuration":"gemini-3-8-flash; Reported effort: high; 113 unique tasks; 447 attempts; 4 runs","score":73.8,"warning":null},{"id":"02f746944e782131d58a2c53","modelId":"gemini-3.8-flash","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"gemini-3-8-flash","configuration":"gemini-3-8-flash; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs","score":71,"warning":null},{"id":"bae0ffc1da12b473f74a2b1f","modelId":"gemma-3-12b-it","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.3333333333333,"warning":null},{"id":"b1ac9024e3d4ec61f9a27b73","modelId":"gemma-3-12b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.33333333333333,"warning":null},{"id":"9f5c45f943e79042aec9e467","modelId":"gemma-3-12b-it","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.19111706206154658,"warning":null},{"id":"e92bfd8b7eb0fc97830fe231","modelId":"gemma-3-12b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"a6589219b0e0884945d77b28","modelId":"gemma-3-12b-it","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1,"warning":null},{"id":"c9ac6749ea0ddde7b22c0665","modelId":"gemma-3-12b-it","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-169.68,"warning":null},{"id":"475a94e16f23c1a63ea69240","modelId":"gemma-3-12b-it","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.93229166666666,"warning":null},{"id":"adccbe9b822ee7f815ae4a80","modelId":"gemma-3-12b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.949494949494905,"warning":null},{"id":"641540b21e3f392cf8f0bd9a","modelId":"gemma-3-12b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.21,"warning":null},{"id":"71da35fd94ce73f427f2e7ce","modelId":"gemma-3-12b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.734693877551,"warning":null},{"id":"22e8ad1e201236cae3a05725","modelId":"gemma-3-12b-it","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.650793650793599,"warning":null},{"id":"080268458062c51d69e21edf","modelId":"gemma-3-12b-it","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":85.3333333333333,"warning":null},{"id":"c0ba5642ee15db5fba8b4514","modelId":"gemma-3-12b-it","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":59.4913563829787,"warning":null},{"id":"e09f5f3a1d31437d4e2c6d10","modelId":"gemma-3-12b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.514450867052,"warning":null},{"id":"5ac2366a97ebc55c10126e78","modelId":"gemma-3-12b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-77.0666666666667,"warning":null},{"id":"65e36893b56d652cbfd11b4a","modelId":"gemma-3-12b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.299999999999999,"warning":null},{"id":"4dfa25465b0259154b3eed24","modelId":"gemma-3-12b-it","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.4351851851852,"warning":null},{"id":"bb329105825c1bb19bf3af65","modelId":"gemma-3-12b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.8187134502924,"warning":null},{"id":"a374e979dbabf157744673dc","modelId":"gemma-3-12b-it","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.824742268041237,"warning":null},{"id":"2b0bbcfc9a419ea70d04d3c8","modelId":"gemma-3-12b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.757575757575758,"warning":null},{"id":"e99a62a6a4b3677568cbb008","modelId":"gemma-3-12b-it","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"fe7aac0ecbb0c2849f090886","modelId":"gemma-3-12b-it","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Gemma 3 12B Instruct","configuration":"Gemma 3 12B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-12b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"870a7107c43ca88307ffdbaf","modelId":"gemma-3-1b-it","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.33333333333333,"warning":null},{"id":"ea441b9a6112bdfae0f748f8","modelId":"gemma-3-1b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"93c701d15fcbd95282d8974f","modelId":"gemma-3-1b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"ea7330bf72144219f9f1610c","modelId":"gemma-3-1b-it","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.020833333333336,"warning":null},{"id":"a85c5930a31d561cbd2a37be","modelId":"gemma-3-1b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.737373737373698,"warning":null},{"id":"5d6447d51ae1eeef0c7328cd","modelId":"gemma-3-1b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.32900834105653,"warning":null},{"id":"a8f8c4241e62ccc94f5c438c","modelId":"gemma-3-1b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.9319727891156,"warning":null},{"id":"967c42becbfc1b7f69a023c4","modelId":"gemma-3-1b-it","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.6931216931216901,"warning":null},{"id":"b405af3f368ddd8defb911f5","modelId":"gemma-3-1b-it","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.4,"warning":null},{"id":"19ee2523e0c844fa8d5056a4","modelId":"gemma-3-1b-it","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.4724069148936,"warning":null},{"id":"d572ac181de7f4a7bd81c4e9","modelId":"gemma-3-1b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-75.45,"warning":null},{"id":"986669b662cfc130d20c3054","modelId":"gemma-3-1b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.75,"warning":null},{"id":"e7781a6c80a8cf308f349051","modelId":"gemma-3-1b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.526315789473701,"warning":null},{"id":"fd8260748e66a80c27ada5ea","modelId":"gemma-3-1b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 3 1B Instruct","configuration":"Gemma 3 1B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-1b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"52d80905949128ccdd8df2d8","modelId":"gemma-3-270m-it","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.33333333333333,"warning":null},{"id":"76fadff0e219977139924094","modelId":"gemma-3-270m-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"9fbe186ff0d120f39021406b","modelId":"gemma-3-270m-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"3309f5884078782f5109c1aa","modelId":"gemma-3-270m-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.4242424242424,"warning":null},{"id":"296e9bf178830a18dc28aea5","modelId":"gemma-3-270m-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.6144578313252995,"warning":null},{"id":"b36408c26ff599f500a313f0","modelId":"gemma-3-270m-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.108843537415,"warning":null},{"id":"5d43728608ad6d1780bac10c","modelId":"gemma-3-270m-it","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.317460317460317,"warning":null},{"id":"ae1485e7ba3805532af5d722","modelId":"gemma-3-270m-it","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.52692819148936,"warning":null},{"id":"20bea5cafe0c9e45a478f6d6","modelId":"gemma-3-270m-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":-29.2666666666667,"warning":null},{"id":"da6a60d5479d339a034ebb01","modelId":"gemma-3-270m-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.8833333333333334,"warning":null},{"id":"5d60afe4189ee37f28c901da","modelId":"gemma-3-270m-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.06432748538012,"warning":null},{"id":"5482e2f6a8f5c425ecbe1b94","modelId":"gemma-3-270m-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 3 270M","configuration":"Gemma 3 270M; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-270m; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"6171d7d4fbe5f0e0c06bf689","modelId":"gemma-3-27b-it","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.6666666666667,"warning":null},{"id":"879b05bb7efdb989b22b0dc3","modelId":"gemma-3-27b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.33333333333333,"warning":null},{"id":"06a85450b2a17ff417c7e6eb","modelId":"gemma-3-27b-it","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.19111706206154658,"warning":null},{"id":"2a72e48f0c589d27795a37bd","modelId":"gemma-3-27b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"1ba477dce1a0ef87c127a612","modelId":"gemma-3-27b-it","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.2,"warning":null},{"id":"9ff6f2c43a694eba82d86602","modelId":"gemma-3-27b-it","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-171.05,"warning":null},{"id":"5421892f4adacf93e8314be4","modelId":"gemma-3-27b-it","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.36979166666666,"warning":null},{"id":"8ff7f32b33421c1c9c6ce965","modelId":"gemma-3-27b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.8282828282828,"warning":null},{"id":"b72a49afa1eabcb932b719b4","modelId":"gemma-3-27b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.3999999999999995,"warning":null},{"id":"c9a7a6546e6e6d3d50d90e69","modelId":"gemma-3-27b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.8367346938776,"warning":null},{"id":"c238d9191ee2d48b6a84b9f0","modelId":"gemma-3-27b-it","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.650793650793599,"warning":null},{"id":"77df7e4831b72de2ed9a1961","modelId":"gemma-3-27b-it","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.26666666666671,"warning":null},{"id":"7c0d40f3fd2faa8072484fd1","modelId":"gemma-3-27b-it","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.86336436170211,"warning":null},{"id":"1d78d7410ecf03f58df197db","modelId":"gemma-3-27b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.0346820809249,"warning":null},{"id":"09f9d18827eea3ab094fd5d4","modelId":"gemma-3-27b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-67.2166666666667,"warning":null},{"id":"2e45792d6883b2e89cc3c62c","modelId":"gemma-3-27b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.950000000000001,"warning":null},{"id":"fe3bf9bdec38cedda2c4603a","modelId":"gemma-3-27b-it","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.2638888888889,"warning":null},{"id":"ea5e72c4e76b0f441b7b788e","modelId":"gemma-3-27b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.526315789473701,"warning":null},{"id":"0382a1aa06c99f35d0e5edc0","modelId":"gemma-3-27b-it","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.824742268041237,"warning":null},{"id":"6c6288b8deb73d4839d789d6","modelId":"gemma-3-27b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.78787878787879,"warning":null},{"id":"7c690cd70e1220383d0f7914","modelId":"gemma-3-27b-it","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.49438202247191,"warning":null},{"id":"bbca9a0d6ee1668274b86945","modelId":"gemma-3-27b-it","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Gemma 3 27B Instruct","configuration":"Gemma 3 27B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-27b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"d22ebd4720d57b1d0764161d","modelId":"gemma-3-4b-it","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.666666666666702,"warning":null},{"id":"613fa8b94c50285eabaf9c8f","modelId":"gemma-3-4b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.66666666666667,"warning":null},{"id":"a442736b72445b13048e7d53","modelId":"gemma-3-4b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"cf36cb19af8c5e42ca17f4dd","modelId":"gemma-3-4b-it","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.447916666666664,"warning":null},{"id":"0cb0a7036c6d87b2926d3b6e","modelId":"gemma-3-4b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.0909090909091,"warning":null},{"id":"7d8ce4772f34fadf12075913","modelId":"gemma-3-4b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.29,"warning":null},{"id":"0b13cb76860c726d995622e9","modelId":"gemma-3-4b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.2993197278912,"warning":null},{"id":"62201b3cf05086b0b77a78bb","modelId":"gemma-3-4b-it","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.2169312169312,"warning":null},{"id":"555c7d3fe8cc0863494ec509","modelId":"gemma-3-4b-it","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.6,"warning":null},{"id":"616fdd55adeeae6be1242f52","modelId":"gemma-3-4b-it","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.688829787234,"warning":null},{"id":"99f7e488d25cf68d9af18b26","modelId":"gemma-3-4b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.942196531791897,"warning":null},{"id":"84dea6e1e3ef3afc74262d95","modelId":"gemma-3-4b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-82.8833333333333,"warning":null},{"id":"024ea9c47f612bdb82a2af67","modelId":"gemma-3-4b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.733333333333333,"warning":null},{"id":"b46e070e0d48161a9317ca32","modelId":"gemma-3-4b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.97076023391813,"warning":null},{"id":"94f7565276574925a5e8b94f","modelId":"gemma-3-4b-it","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.412371134020619,"warning":null},{"id":"7c2754460e15897101c6669f","modelId":"gemma-3-4b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.757575757575758,"warning":null},{"id":"3a5f475968c70faa3e41558a","modelId":"gemma-3-4b-it","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Gemma 3 4B Instruct","configuration":"Gemma 3 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.374531835205993,"warning":null},{"id":"254339b1bd7ba893610b28a5","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.3333333333333,"warning":null},{"id":"5cc3c6f529c5fcaac01b08b9","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"d24e94beebb7749ea1d8ffea","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"3e9213eb8cb6f7bda1d0f1e5","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.9292929292929,"warning":null},{"id":"6e6e05f44c22c523f43e0263","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.17052826691381,"warning":null},{"id":"fc57f0fecccf2986223f97b0","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.0408163265306,"warning":null},{"id":"265009dd01320779e45d8889","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.52380952380952,"warning":null},{"id":"6c6b8a1e0fb87413ec47be0e","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.1333333333333,"warning":null},{"id":"e2a432a9133e962dcc3af709","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.815824468085104,"warning":null},{"id":"b27d10aabf75f3a064bc461e","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-80.1666666666667,"warning":null},{"id":"085cdd0603d97d7410437c05","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.833333333333333,"warning":null},{"id":"6beb07747331dd05fccc4d18","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"f0214606125afc28f6556fde","modelId":"gemma-3n-e2b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 3n E2B Instruct","configuration":"Gemma 3n E2B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.757575757575758,"warning":null},{"id":"ea42f23527add8b9c39d253d","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.3333333333333,"warning":null},{"id":"99d58e99ccd89cd35c2b912b","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"696ce85764f9c9d4b1ba6e1c","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"c0d8d76e50c09ce3e119f8ba","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.5959595959596,"warning":null},{"id":"fc586044e84b48830b7341ca","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.49490268767377,"warning":null},{"id":"01760f7dbd3659373c5cb7d0","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.891156462585,"warning":null},{"id":"0a88eeceeac43fa8c6eca502","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.603174603174601,"warning":null},{"id":"8cd759735b2f8417924de7a2","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.0666666666667,"warning":null},{"id":"90efdea1edf0d70b9c91f2e0","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.828125,"warning":null},{"id":"f604330d5bdfb9b2f5bfd3f5","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.242774566473997,"warning":null},{"id":"9082176c134078aa550097ff","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-81.3333333333333,"warning":null},{"id":"2ae2a55f56fb56a01959e687","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.983333333333334,"warning":null},{"id":"5a340915e75cfe29b8a881e4","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.97076023391813,"warning":null},{"id":"a0fdfcd89c7b44fa4f91571d","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.206185567010309,"warning":null},{"id":"b88afa6c66f560b3e323a93e","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.27272727272727,"warning":null},{"id":"42b31d167ae12b063c4787ce","modelId":"gemma-3n-e4b-it","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Gemma 3n E4B Instruct","configuration":"Gemma 3n E4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gemma-3n-e4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.7490636704119851,"warning":null},{"id":"2fa190ad552336df40fc5759","modelId":"gemma-4-12b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":35,"warning":null},{"id":"7f25db26af07cec60d504c7c","modelId":"gemma-4-12b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":63.66666666666671,"warning":null},{"id":"716efdabc122b732d667420c","modelId":"gemma-4-12b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":0,"warning":null},{"id":"bea6c787579f9a1237d89ed4","modelId":"gemma-4-12b-it","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":0,"warning":null},{"id":"903a6d2eb139cb2a79eb5200","modelId":"gemma-4-12b-it","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":590.73,"warning":null},{"id":"bf1dc487a514004349865eb5","modelId":"gemma-4-12b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":66.06060606060609,"warning":null},{"id":"a333a9160f2666010facc8ed","modelId":"gemma-4-12b-it","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":75.2525252525252,"warning":null},{"id":"9b0cac4689133115cef3a717","modelId":"gemma-4-12b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":6.34847080630213,"warning":null},{"id":"e9d2340a77f08483cc4db4b8","modelId":"gemma-4-12b-it","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":15.6626506024096,"warning":null},{"id":"01faa81311cd7b4f50088ac4","modelId":"gemma-4-12b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":45.1700680272109,"warning":null},{"id":"a15f95933b64d5141645bcf6","modelId":"gemma-4-12b-it","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":73.5374149659864,"warning":null},{"id":"d44fa4443a7ce8124d0a70d3","modelId":"gemma-4-12b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":61.965317919075105,"warning":null},{"id":"38462004b6ccf5545dc45a40","modelId":"gemma-4-12b-it","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":69.6531791907514,"warning":null},{"id":"2b90c9332daa18e534fd0fcf","modelId":"gemma-4-12b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":-52.8,"warning":null},{"id":"ce50829c14122f3091899493","modelId":"gemma-4-12b-it","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":-52.7166666666667,"warning":null},{"id":"2751c624590967f5d5249682","modelId":"gemma-4-12b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":11.883333333333333,"warning":null},{"id":"f5850b32526048230419690d","modelId":"gemma-4-12b-it","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":15.616666666666667,"warning":null},{"id":"5e5cb56ee5eb6803aa8bd6a2","modelId":"gemma-4-12b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":31.8713450292398,"warning":null},{"id":"d9aa2621884ddc873af35623","modelId":"gemma-4-12b-it","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":36.2573099415205,"warning":null},{"id":"350822620ac30f66a2da1d9b","modelId":"gemma-4-12b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 4 12B (Non-reasoning)","configuration":"Gemma 4 12B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning","score":11.363636363636399,"warning":null},{"id":"5ca27f0cf0791ac115c1d87e","modelId":"gemma-4-12b-it","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":18.181818181818198,"warning":null},{"id":"afa273af8ca9474f2626494e","modelId":"gemma-4-12b-it","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemma 4 12B (Reasoning)","configuration":"Gemma 4 12B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-12b","score":27.340823970037498,"warning":null},{"id":"949edb06f6af88efae6f287b","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":42.3333333333333,"warning":null},{"id":"2ecf2ada691fdd1c0a03b480","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":65.6666666666667,"warning":null},{"id":"6fc2dd3e0d651bd9249e2633","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":0,"warning":null},{"id":"f6dcd64e671508e237b35918","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":0,"warning":null},{"id":"d7a9b3fa326769247dc5cb1e","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":713.04,"warning":null},{"id":"5fcfd34173707143f2a99925","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":71.4141414141414,"warning":null},{"id":"297b1d6d72e973e016718eff","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":79.1919191919192,"warning":null},{"id":"0311d8249343cd490439681b","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":11.4921223354958,"warning":null},{"id":"8b3cd8bd20e702eedb423658","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":19.3234476367006,"warning":null},{"id":"4b414517eb3739571023617d","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":45.442176870748305,"warning":null},{"id":"b0b8625f23efeef97463192d","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":72.4489795918367,"warning":null},{"id":"123c6d4efe200397de794a3b","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":23.6346516007533,"warning":null},{"id":"f245bbe38d52f3b84a64e4dc","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":66.7052023121387,"warning":null},{"id":"7177df54c2337ce7eaf62e08","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":69.2485549132948,"warning":null},{"id":"67499adc1b46f586a1c3d2b0","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":-62.3166666666667,"warning":null},{"id":"49acca20990729f11bd62386","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":-50.8333333333333,"warning":null},{"id":"f2a7a0301ac7cdb230df1663","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":15.483333333333333,"warning":null},{"id":"319e9e5b1b3e864344a503b3","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":19.1,"warning":null},{"id":"2bb7da5d78c57f44d827d9f9","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":40.3508771929825,"warning":null},{"id":"d8a5c15274c4f18730b4d9f5","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":43.5672514619883,"warning":null},{"id":"23c4101446e544ed2ac5b82f","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":11.9587628865979,"warning":null},{"id":"6cd407ecade291b598835150","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 4 26B A4B (Non-reasoning)","configuration":"Gemma 4 26B A4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning","score":25,"warning":null},{"id":"81715bf25a80b1a5d222b5cf","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":13.639999999999999,"warning":null},{"id":"60c606d7f6815f665071f6e1","modelId":"gemma-4-26b-a4b-it","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemma 4 26B A4B (Reasoning)","configuration":"Gemma 4 26B A4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-26b-a4b","score":38.9513108614232,"warning":null},{"id":"ea2a8c7140a73f18e4fb3694","modelId":"gemma-4-31b-it","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":376.57,"warning":null},{"id":"0a11579402aa7ddc9dd6348f","modelId":"gemma-4-31b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":46.6666666666667,"warning":null},{"id":"706f0676dad235cacaacf815","modelId":"gemma-4-31b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":69.6666666666667,"warning":null},{"id":"6d730c431d429efc51487ae1","modelId":"gemma-4-31b-it","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":4.933063448681232,"warning":null},{"id":"89a616e7c917c56392cafec6","modelId":"gemma-4-31b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":0,"warning":null},{"id":"601a3ec51179b6fffcfaead1","modelId":"gemma-4-31b-it","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":1.42857142857143,"warning":null},{"id":"5e1832dadb83cec7d9868f04","modelId":"gemma-4-31b-it","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":28.349746344374815,"warning":null},{"id":"b21e911e97485a34e9502144","modelId":"gemma-4-31b-it","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":6,"warning":null},{"id":"92b9aeaf6b5e97c54493380c","modelId":"gemma-4-31b-it","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":691.46,"warning":null},{"id":"8d6837e9f7a3768a8f372375","modelId":"gemma-4-31b-it","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":755.45,"warning":null},{"id":"7fa903a68ff27edd309baae9","modelId":"gemma-4-31b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":76.2626262626263,"warning":null},{"id":"a0a564da6c85edee9be55904","modelId":"gemma-4-31b-it","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":85.6565656565657,"warning":null},{"id":"de6a2332adf2390b998fb058","modelId":"gemma-4-31b-it","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":47.228253003329,"warning":null},{"id":"7701f8f5dda40cd06fa4c776","modelId":"gemma-4-31b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":11.8164967562558,"warning":null},{"id":"8e3a35ca0c938e259f5e70b4","modelId":"gemma-4-31b-it","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":23.6329935125116,"warning":null},{"id":"559274bb4d2db9e3dee3156b","modelId":"gemma-4-31b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":53.469387755102005,"warning":null},{"id":"26dcfe7fc4f0f3ca73ea75cd","modelId":"gemma-4-31b-it","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":75.57823129251699,"warning":null},{"id":"25e5a78d91ee39f3070e8ee1","modelId":"gemma-4-31b-it","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":37.288135593220304,"warning":null},{"id":"fca70e45bb76253f1f919976","modelId":"gemma-4-31b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":70.3468208092486,"warning":null},{"id":"6cbd352ef10ac02c691f3078","modelId":"gemma-4-31b-it","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":73.4104046242775,"warning":null},{"id":"ba8e82e53d70d6f8aafa303e","modelId":"gemma-4-31b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":-51.6833333333333,"warning":null},{"id":"098d80e8ba47d8a6ef0c241f","modelId":"gemma-4-31b-it","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":-47.9333333333333,"warning":null},{"id":"c7458f1927e4b1a2a3dabfd7","modelId":"gemma-4-31b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":16.633333333333333,"warning":null},{"id":"31dd36e84421125afbaf73c8","modelId":"gemma-4-31b-it","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":20.033333333333335,"warning":null},{"id":"e131f49fc0290c2c251ad59d","modelId":"gemma-4-31b-it","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":45.4861111111111,"warning":null},{"id":"5fb1a0a25e052c05799b4a8d","modelId":"gemma-4-31b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":65.4970760233918,"warning":null},{"id":"46fcde8fb24e810ecbd0e3fd","modelId":"gemma-4-31b-it","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":59.9415204678363,"warning":null},{"id":"38550b8a2a207eb0da07c6e6","modelId":"gemma-4-31b-it","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":8.8659793814433,"warning":null},{"id":"2d0393ab86c8e9008391b8f9","modelId":"gemma-4-31b-it","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":14.8453608247423,"warning":null},{"id":"4c693dcad0bad4f75e983ec7","modelId":"gemma-4-31b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":30.303030303030297,"warning":null},{"id":"6a59f286887b9777ef477767","modelId":"gemma-4-31b-it","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":36.363636363636395,"warning":null},{"id":"7082033eb30f427626a4ffe5","modelId":"gemma-4-31b-it","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Gemma 4 31B (Non-reasoning)","configuration":"Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning","score":29.213483146067396,"warning":null},{"id":"e0daed7f980e0bd9dd3d6801","modelId":"gemma-4-31b-it","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":43.4456928838951,"warning":null},{"id":"632c819ff919f14202c38e37","modelId":"gemma-4-31b-it","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Gemma 4 31B (Reasoning)","configuration":"Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b","score":0,"warning":null},{"id":"5110c2885f54e024cd329be3","modelId":"gemma-4-e2b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":16.3333333333333,"warning":null},{"id":"6983a9fbb42127d71547b6b4","modelId":"gemma-4-e2b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":16.3333333333333,"warning":null},{"id":"64f0265c1003812ec781556f","modelId":"gemma-4-e2b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":0,"warning":null},{"id":"673c72fe749a675bb48c99c2","modelId":"gemma-4-e2b-it","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":0,"warning":null},{"id":"921d07d6198fee45dc68baf6","modelId":"gemma-4-e2b-it","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":36.05,"warning":null},{"id":"9c01f4e5c42675a3c6f3d9aa","modelId":"gemma-4-e2b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":40.5050505050505,"warning":null},{"id":"117449d508219e8cd6e43180","modelId":"gemma-4-e2b-it","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":43.3333333333333,"warning":null},{"id":"e0d5158b58c9798a658ce75a","modelId":"gemma-4-e2b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":4.72659870250232,"warning":null},{"id":"e3dabdefbac77e863019f219","modelId":"gemma-4-e2b-it","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":4.77293790546803,"warning":null},{"id":"2135126d4e4981631a2395d2","modelId":"gemma-4-e2b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":33.605442176870696,"warning":null},{"id":"a3fed7a0571b3df4e44deacb","modelId":"gemma-4-e2b-it","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":38.0272108843537,"warning":null},{"id":"935ddb78227e9b20558bbd5e","modelId":"gemma-4-e2b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":41.7919075144509,"warning":null},{"id":"9dbacd79912a83e02071a8f7","modelId":"gemma-4-e2b-it","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":44.5664739884393,"warning":null},{"id":"cc429fcc1335cb09f66d90b4","modelId":"gemma-4-e2b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":-60.1833333333333,"warning":null},{"id":"e73a2705c80206386d342583","modelId":"gemma-4-e2b-it","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":-23.5833333333333,"warning":null},{"id":"c21205c79690fad58d74523b","modelId":"gemma-4-e2b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":8.15,"warning":null},{"id":"0b86207217f529cfa79a01fb","modelId":"gemma-4-e2b-it","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":6.633333333333333,"warning":null},{"id":"4fa492fe78a6b6374bdaad9c","modelId":"gemma-4-e2b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":22.2222222222222,"warning":null},{"id":"381279b32093010e53f60864","modelId":"gemma-4-e2b-it","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":20.7602339181287,"warning":null},{"id":"ed4c579b74058292c68ba773","modelId":"gemma-4-e2b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 4 E2B (Non-reasoning)","configuration":"Gemma 4 E2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning","score":2.27272727272727,"warning":null},{"id":"e62ae3c573bc0ed516e86b34","modelId":"gemma-4-e2b-it","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":3.03030303030303,"warning":null},{"id":"94f2c4df5cb23012e2ed42af","modelId":"gemma-4-e2b-it","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemma 4 E2B (Reasoning)","configuration":"Gemma 4 E2B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e2b","score":0.374531835205993,"warning":null},{"id":"7d5dc30c068300c623a91a48","modelId":"gemma-4-e4b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":24,"warning":null},{"id":"b93409ba27f2f5c6f9a53d14","modelId":"gemma-4-e4b-it","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":32,"warning":null},{"id":"7d1148ef014c1313b8bb33c9","modelId":"gemma-4-e4b-it","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":0.28571428571428603,"warning":null},{"id":"892bc5fe99c93c72090843f4","modelId":"gemma-4-e4b-it","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":0.571428571428571,"warning":null},{"id":"32105aa20ddbef33298c2a12","modelId":"gemma-4-e4b-it","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":176.92,"warning":null},{"id":"09f4fa9699ed45e540bccdf5","modelId":"gemma-4-e4b-it","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":54.949494949494905,"warning":null},{"id":"dc6981039f93bb34311c5aaa","modelId":"gemma-4-e4b-it","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":57.5757575757576,"warning":null},{"id":"94598d71e00dbc497012ed1f","modelId":"gemma-4-e4b-it","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":4.81927710843374,"warning":null},{"id":"8014fef86e630db2b5b16922","modelId":"gemma-4-e4b-it","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":3.75347544022243,"warning":null},{"id":"7c949f5675b407fd8b972461","modelId":"gemma-4-e4b-it","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":40.5442176870748,"warning":null},{"id":"8b37f6fe8c07bb8bf8c55d62","modelId":"gemma-4-e4b-it","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":44.2176870748299,"warning":null},{"id":"fb8d6f02b4833a2bfacb1689","modelId":"gemma-4-e4b-it","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":51.2138728323699,"warning":null},{"id":"8edf8e0f16e79a110f25a4db","modelId":"gemma-4-e4b-it","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":51.38728323699419,"warning":null},{"id":"6ecea92ea2a8f843cc72ea55","modelId":"gemma-4-e4b-it","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":-40.9833333333333,"warning":null},{"id":"bf37eb7ed991ae1c14f31e61","modelId":"gemma-4-e4b-it","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":-19.7,"warning":null},{"id":"411b36bb3f028339dc23a40a","modelId":"gemma-4-e4b-it","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":8.316666666666666,"warning":null},{"id":"bb15c5f471328aba08aaf5b4","modelId":"gemma-4-e4b-it","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":8.583333333333334,"warning":null},{"id":"97f873fbbc402712668863f5","modelId":"gemma-4-e4b-it","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":26.023391812865498,"warning":null},{"id":"7bf99cf2364cac7350bf17b5","modelId":"gemma-4-e4b-it","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":20.7602339181287,"warning":null},{"id":"d6faa5c06f974d9bd6bd6075","modelId":"gemma-4-e4b-it","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Gemma 4 E4B (Non-reasoning)","configuration":"Gemma 4 E4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning","score":7.57575757575758,"warning":null},{"id":"7e25eac2feb6eedc0f86c175","modelId":"gemma-4-e4b-it","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":8.33333333333333,"warning":null},{"id":"17d5928b1cc07aea7cc8ca5c","modelId":"gemma-4-e4b-it","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Gemma 4 E4B (Reasoning)","configuration":"Gemma 4 E4B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-e4b","score":1.8726591760299598,"warning":null},{"id":"8298ccc202056776af853910","modelId":"glm-4.5","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":73.6666666666667,"warning":null},{"id":"a005dca05213b4a73bd1f631","modelId":"glm-4.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":52.66666666666669,"warning":null},{"id":"9d40825300ffb78278062990","modelId":"glm-4.5","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":0,"warning":null},{"id":"fa89cbb630e45386ecb9a21b","modelId":"glm-4.5","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":78.1818181818182,"warning":null},{"id":"0a25e325728168d4811f7328","modelId":"glm-4.5","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":12.9749768303985,"warning":null},{"id":"53c7ad0bcc622084c5c97bac","modelId":"glm-4.5","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":44.0816326530612,"warning":null},{"id":"5252efc29a3f74f35b2cc18b","modelId":"glm-4.5","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":73.7566137566138,"warning":null},{"id":"fed2921be1ef626eaf2a2bbe","modelId":"glm-4.5","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":97.8666666666667,"warning":null},{"id":"dbbfc474edba92c7dab9b479","modelId":"glm-4.5","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":83.51063829787229,"warning":null},{"id":"f36782bceb8f45f46260015d","modelId":"glm-4.5","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":-27.3833333333333,"warning":null},{"id":"9532998fc69d20d9ec16b054","modelId":"glm-4.5","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":25.133333333333336,"warning":null},{"id":"08f28aaf925a9d0fe859921a","modelId":"glm-4.5","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":42.9824561403509,"warning":null},{"id":"370832ef81cc12e7336b2145","modelId":"glm-4.5","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-4.5 (Reasoning)","configuration":"GLM-4.5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4.5","score":21.969696969697,"warning":null},{"id":"30778ad113a0f6285db2b6ff","modelId":"glm-4.5-air","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.6666666666667,"warning":null},{"id":"450ec3814ad0983a05e7a649","modelId":"glm-4.5-air","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.6666666666667,"warning":null},{"id":"cf0dba8bcf1455f91c347f09","modelId":"glm-4.5-air","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"3d56ef2f2e608d5f1b411ba5","modelId":"glm-4.5-air","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.3333333333333,"warning":null},{"id":"1d3e677c3bf1025f2a641c60","modelId":"glm-4.5-air","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.043558850787771,"warning":null},{"id":"4b433f8594cf7a6275f6bdda","modelId":"glm-4.5-air","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.551020408163296,"warning":null},{"id":"e8cfae35f6575df2ef5f407a","modelId":"glm-4.5-air","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.3597883597884,"warning":null},{"id":"527bf2fab21343432d365235","modelId":"glm-4.5-air","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":96.5333333333333,"warning":null},{"id":"97020ae33cadfba84dafac57","modelId":"glm-4.5-air","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.4660904255319,"warning":null},{"id":"01d4601ce35baf7582b2b1d6","modelId":"glm-4.5-air","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":-61.5333333333333,"warning":null},{"id":"e7949f905f5354d088ef79b6","modelId":"glm-4.5-air","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.25,"warning":null},{"id":"eb25975b22bc9375e5cd191c","modelId":"glm-4.5-air","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.4912280701754,"warning":null},{"id":"dc0e4f99afd02c7db9b646f0","modelId":"glm-4.5-air","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-4.5-Air","configuration":"GLM-4.5-Air; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-4-5-air; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.4545454545455,"warning":null},{"id":"4871200d6165cb682b2f4db0","modelId":"glm-4.5v","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":15.333333333333298,"warning":null},{"id":"e4545c8e6a9f48f87e9183ab","modelId":"glm-4.5v","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":73,"warning":null},{"id":"0729665e03aab12509527098","modelId":"glm-4.5v","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":0,"warning":null},{"id":"922c35fbdd3776fc47267594","modelId":"glm-4.5v","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":0,"warning":null},{"id":"eca393b7c441fead8a16594f","modelId":"glm-4.5v","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":0,"warning":null},{"id":"f40e1888dda90b48a7c89c2d","modelId":"glm-4.5v","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":0,"warning":null},{"id":"1d03512bcc278ddfc0116961","modelId":"glm-4.5v","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":57.272727272727295,"warning":null},{"id":"e8adc6d5ef578a1953c26485","modelId":"glm-4.5v","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":68.38383838383841,"warning":null},{"id":"4dcf51bad5f69f32997356ae","modelId":"glm-4.5v","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":3.47544022242817,"warning":null},{"id":"03c90c119703b5139fdd86d2","modelId":"glm-4.5v","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":6.302131603336419,"warning":null},{"id":"713f47b76c588cdeed905e1a","modelId":"glm-4.5v","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":28.6394557823129,"warning":null},{"id":"7c2c5f83154687619618e3e1","modelId":"glm-4.5v","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":34.2176870748299,"warning":null},{"id":"c761f12b0a18361cd10bacb2","modelId":"glm-4.5v","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":35.2380952380952,"warning":null},{"id":"b524713fda2561eae7d1aa5f","modelId":"glm-4.5v","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":60.4232804232804,"warning":null},{"id":"f5091aafad1bbf696b1ec861","modelId":"glm-4.5v","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":75.0748005319149,"warning":null},{"id":"24ecfed1451beb78d27f9aad","modelId":"glm-4.5v","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":78.82313829787229,"warning":null},{"id":"35ffcd0393390b9865e927f4","modelId":"glm-4.5v","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":42.7745664739884,"warning":null},{"id":"09112bc5833f03e221eb9dcd","modelId":"glm-4.5v","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":50.4624277456647,"warning":null},{"id":"3448b6b298eb30f990513f92","modelId":"glm-4.5v","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":-55.5833333333333,"warning":null},{"id":"d6ed32645d4db9e47a014182","modelId":"glm-4.5v","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":-46.2833333333333,"warning":null},{"id":"b391e172392ad37ac3d246b5","modelId":"glm-4.5v","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":18.21666666666667,"warning":null},{"id":"bcd773de3a0b8d695f5c99e9","modelId":"glm-4.5v","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":20.833333333333336,"warning":null},{"id":"089e4a139e5493e3585dcc44","modelId":"glm-4.5v","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":19.5906432748538,"warning":null},{"id":"e34271c056b08e75014f0dbd","modelId":"glm-4.5v","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":22.5146198830409,"warning":null},{"id":"4503f7cd70608a6263c8a831","modelId":"glm-4.5v","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GLM-4.5V (Non-reasoning)","configuration":"GLM-4.5V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v","score":6.81818181818182,"warning":null},{"id":"ba4b24c2832b05c124a17fb1","modelId":"glm-4.5v","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-4.5V (Reasoning)","configuration":"GLM-4.5V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-5v-reasoning","score":5.3030303030303,"warning":null},{"id":"94b2207ac99b20596113e239","modelId":"glm-4.6","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":44.3333333333333,"warning":null},{"id":"4c0bdeccb0c354ff92adf063","modelId":"glm-4.6","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":86,"warning":null},{"id":"6f35e6b7857e8f7192a4a601","modelId":"glm-4.6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":26.333333333333297,"warning":null},{"id":"0344a85a899d64b5d461c992","modelId":"glm-4.6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":54,"warning":null},{"id":"315001284817defdcd52844a","modelId":"glm-4.6","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":0,"warning":null},{"id":"fed9d2112a78902f9f4f0e51","modelId":"glm-4.6","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":1.1428571428571401,"warning":null},{"id":"f20e2ae26627536827c101f6","modelId":"glm-4.6","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":873.8,"warning":null},{"id":"1bae8321f9546badb45d0fb9","modelId":"glm-4.6","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":85.56250000000001,"warning":null},{"id":"f82dc3cb8c29059c143578fe","modelId":"glm-4.6","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":63.232323232323196,"warning":null},{"id":"ccadcb53ecb9ac27bab7aeb6","modelId":"glm-4.6","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":77.97979797979801,"warning":null},{"id":"6d3bc66cda454029e3c6020a","modelId":"glm-4.6","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":5.4680259499536605,"warning":null},{"id":"3b40312601b47b4babec1ab4","modelId":"glm-4.6","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":14.457831325301198,"warning":null},{"id":"ebea8e8659f63d3cc4eee8fd","modelId":"glm-4.6","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":36.734693877551,"warning":null},{"id":"3fb0125cf298b473640c0aec","modelId":"glm-4.6","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":43.401360544217695,"warning":null},{"id":"40fe745d4d40c37a7d37481e","modelId":"glm-4.6","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":56.0846560846561,"warning":null},{"id":"c88494c785e24d0e1cdaf51f","modelId":"glm-4.6","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":69.5238095238095,"warning":null},{"id":"a3c0ba45f30db91ea4c183c1","modelId":"glm-4.6","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":78.407579787234,"warning":null},{"id":"1db53b8e924e88e0152b0bca","modelId":"glm-4.6","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":82.920545212766,"warning":null},{"id":"34147f34008b905a9aaccb96","modelId":"glm-4.6","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":-31.6833333333333,"warning":null},{"id":"ed586d5fb6e4774692dbe3d6","modelId":"glm-4.6","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":-41.8833333333333,"warning":null},{"id":"9c2e61e1aa9164545b79fcd2","modelId":"glm-4.6","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":21.416666666666668,"warning":null},{"id":"c53213ee6f0915802c451959","modelId":"glm-4.6","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":26.883333333333333,"warning":null},{"id":"d316796d0ffdebfc5767c923","modelId":"glm-4.6","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":76.9005847953216,"warning":null},{"id":"9199e4208a43755ee68b1b8e","modelId":"glm-4.6","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":70.4678362573099,"warning":null},{"id":"5bda5b832f8326e62befe8f7","modelId":"glm-4.6","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":13.4020618556701,"warning":null},{"id":"d02b87f4d69acd7535e38333","modelId":"glm-4.6","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GLM-4.6 (Non-reasoning)","configuration":"GLM-4.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6","score":28.7878787878788,"warning":null},{"id":"2b53925946f0f877aafc59ae","modelId":"glm-4.6","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":25,"warning":null},{"id":"2f27314674aef5a4b49f2640","modelId":"glm-4.6","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"GLM-4.6 (Reasoning)","configuration":"GLM-4.6 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6-reasoning","score":49.438202247191,"warning":null},{"id":"4928b0276fd6c9a8c444b71e","modelId":"glm-4.6v","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":26.333333333333297,"warning":null},{"id":"837343c2ac3011d1ba300da8","modelId":"glm-4.6v","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":85.3333333333333,"warning":null},{"id":"e5e6ec6c228c7287c39d279f","modelId":"glm-4.6v","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":17,"warning":null},{"id":"d141580c3462963d595336e2","modelId":"glm-4.6v","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":48.6666666666667,"warning":null},{"id":"3905dcd5f1aeeae6a2266f50","modelId":"glm-4.6v","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":0,"warning":null},{"id":"afd55634a947e6c3807e9226","modelId":"glm-4.6v","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":0,"warning":null},{"id":"eba8c8cdf1f756b264cfd259","modelId":"glm-4.6v","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":74.34375,"warning":null},{"id":"7122a72135860cf4a9ad81f7","modelId":"glm-4.6v","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":80.62500000000001,"warning":null},{"id":"e7fd67d8815e3bbfa5923edc","modelId":"glm-4.6v","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":56.565656565656596,"warning":null},{"id":"ba3ca764bdc9824f995c4087","modelId":"glm-4.6v","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":71.9191919191919,"warning":null},{"id":"c68005b6921e3ff990365ab4","modelId":"glm-4.6v","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":3.66079703429101,"warning":null},{"id":"ecd415b5cced2b02caaf3681","modelId":"glm-4.6v","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":9.63855421686747,"warning":null},{"id":"c716d0178a13ce9a95ae3cd0","modelId":"glm-4.6v","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":27.891156462585,"warning":null},{"id":"0421e7c6e87d6634872e2e40","modelId":"glm-4.6v","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":30.068027210884402,"warning":null},{"id":"7d7305f2366a230af2f05859","modelId":"glm-4.6v","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":41.0582010582011,"warning":null},{"id":"7c7927de9636469ac8d473a7","modelId":"glm-4.6v","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":15.978835978836,"warning":null},{"id":"384accf5ced6dc13a246274e","modelId":"glm-4.6v","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":75.1579122340426,"warning":null},{"id":"fdb7e30eb45da4db40e78049","modelId":"glm-4.6v","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":79.8869680851064,"warning":null},{"id":"c89a56b6d6bbbcefc7ae2df1","modelId":"glm-4.6v","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":42.196531791907496,"warning":null},{"id":"2827544ddf30cfce3f005022","modelId":"glm-4.6v","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":48.5549132947977,"warning":null},{"id":"39a8e6640c8191a779ffb48c","modelId":"glm-4.6v","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":-37.6333333333333,"warning":null},{"id":"6fddb525b5d0b94467ba8661","modelId":"glm-4.6v","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":-26.95,"warning":null},{"id":"e1cded7b38ba045706848908","modelId":"glm-4.6v","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":17.4,"warning":null},{"id":"b6ce561dc26c02cc5b8f2b40","modelId":"glm-4.6v","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":16.183333333333334,"warning":null},{"id":"7cfeb8b11e9274ce0f4325c1","modelId":"glm-4.6v","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":30.701754385964904,"warning":null},{"id":"52cdb947037479b540381f2c","modelId":"glm-4.6v","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":31.5789473684211,"warning":null},{"id":"56681bacf5ef1774b2acc379","modelId":"glm-4.6v","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GLM-4.6V (Non-reasoning)","configuration":"GLM-4.6V (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v","score":3.03030303030303,"warning":null},{"id":"35b1c4bf5d6fa8c5baaf36b7","modelId":"glm-4.6v","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-4.6V (Reasoning)","configuration":"GLM-4.6V (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-6v-reasoning","score":14.3939393939394,"warning":null},{"id":"0771a4f46146e10e4235d642","modelId":"glm-4.7","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":48,"warning":null},{"id":"9d958d31de170d1f70fe36e3","modelId":"glm-4.7","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":95,"warning":null},{"id":"2e0855d0f0f6762f6c2ffdef","modelId":"glm-4.7","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":40.6666666666667,"warning":null},{"id":"600cd8ff296dbf4c45f8dfb1","modelId":"glm-4.7","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":71,"warning":null},{"id":"be2db485b78d0a1b46ed5356","modelId":"glm-4.7","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":0,"warning":null},{"id":"7c1a7f1baae339fd5be9c307","modelId":"glm-4.7","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":1.7102040816326498,"warning":null},{"id":"4346349a6b3d09e86089959d","modelId":"glm-4.7","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":1095.87,"warning":null},{"id":"5bc781f14b12760c914bf4ff","modelId":"glm-4.7","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":79.94270833333333,"warning":null},{"id":"d361191da2645058d234a667","modelId":"glm-4.7","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":66.3636363636364,"warning":null},{"id":"e6b2c07688573b5ef356beb2","modelId":"glm-4.7","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":85.8585858585858,"warning":null},{"id":"f2ab30db0772c1973993e6ed","modelId":"glm-4.7","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":6.39481000926784,"warning":null},{"id":"b20d65229b0b347c90b78a5c","modelId":"glm-4.7","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":27.386468952734,"warning":null},{"id":"580c7737090958a16068b38c","modelId":"glm-4.7","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":54.6258503401361,"warning":null},{"id":"bf52da1f53cc20f4500101b1","modelId":"glm-4.7","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":67.891156462585,"warning":null},{"id":"6382cf43b3a8232f5674c7b0","modelId":"glm-4.7","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":56.190476190476204,"warning":null},{"id":"1e4ba8a5e58f7505da22c681","modelId":"glm-4.7","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":89.41798941798939,"warning":null},{"id":"6011d3f6af7d6023a6300e86","modelId":"glm-4.7","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":79.42985372340429,"warning":null},{"id":"6ab0834a7bf56a40feab81d4","modelId":"glm-4.7","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":85.61336436170211,"warning":null},{"id":"99a720d42d9ab77eb33f8999","modelId":"glm-4.7","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":-47.3166666666667,"warning":null},{"id":"4e7b558ad298402697e6731f","modelId":"glm-4.7","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":-36.4333333333333,"warning":null},{"id":"b5f9786af6208eb41d64f34a","modelId":"glm-4.7","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":23.633333333333333,"warning":null},{"id":"c2a7e666a331885b7d3dc6b5","modelId":"glm-4.7","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":29.31666666666667,"warning":null},{"id":"1df34276ac9f506932188cd2","modelId":"glm-4.7","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":94.15204678362569,"warning":null},{"id":"66a84bbe9d4d9beec66aa404","modelId":"glm-4.7","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":95.906432748538,"warning":null},{"id":"2c709f287f79e8409cab1324","modelId":"glm-4.7","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":12.1649484536082,"warning":null},{"id":"ed118dd9b03ad11a94dbc60a","modelId":"glm-4.7","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GLM-4.7 (Non-reasoning)","configuration":"GLM-4.7 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-non-reasoning","score":30.303030303030297,"warning":null},{"id":"fcf8a79a09b5a2fbc1bf7633","modelId":"glm-4.7","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":31.818181818181802,"warning":null},{"id":"c0a612c35973a4492ab95c32","modelId":"glm-4.7","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"GLM-4.7 (Reasoning)","configuration":"GLM-4.7 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7","score":45.3183520599251,"warning":null},{"id":"9cd24111c9965cfb6c1082ac","modelId":"glm-4.7-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":20.3333333333333,"warning":null},{"id":"cd1295cb2630e66e6f215155","modelId":"glm-4.7-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":41.6666666666667,"warning":null},{"id":"ed9425416741e32642acdd40","modelId":"glm-4.7-flash","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":0,"warning":null},{"id":"0db7ae079fcd8b12ea4ae666","modelId":"glm-4.7-flash","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":0.28571428571428603,"warning":null},{"id":"7d0bb65c43e4e65421db7974","modelId":"glm-4.7-flash","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":45.1515151515151,"warning":null},{"id":"1c6b02da06598a9564b5f0a1","modelId":"glm-4.7-flash","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":58.0808080808081,"warning":null},{"id":"64779412a942295b2f1fcc41","modelId":"glm-4.7-flash","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":4.95829471733086,"warning":null},{"id":"f063c4ae2b226ece4cb36abb","modelId":"glm-4.7-flash","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":7.5996292863762696,"warning":null},{"id":"9dd6590fc2f380b2c4012ea3","modelId":"glm-4.7-flash","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":46.2585034013605,"warning":null},{"id":"4c84ae887b9f12258846745d","modelId":"glm-4.7-flash","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":60.816326530612194,"warning":null},{"id":"a401455d8af56dc225e840c7","modelId":"glm-4.7-flash","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":-68.9333333333333,"warning":null},{"id":"7ce9b77baf9eb443d943cfaf","modelId":"glm-4.7-flash","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":-62.6166666666667,"warning":null},{"id":"b9f06013867513c4304ef9e3","modelId":"glm-4.7-flash","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":13.05,"warning":null},{"id":"4f604a4640d84fc42eceed08","modelId":"glm-4.7-flash","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":16.150000000000002,"warning":null},{"id":"6e4ef0923f16cd949083876d","modelId":"glm-4.7-flash","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":91.812865497076,"warning":null},{"id":"70b12115dcee433abbc02722","modelId":"glm-4.7-flash","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":98.8304093567251,"warning":null},{"id":"12babe8e33433fd23f2ac171","modelId":"glm-4.7-flash","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GLM-4.7-Flash (Non-reasoning)","configuration":"GLM-4.7-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash-non-reasoning","score":3.78787878787879,"warning":null},{"id":"29f7ca5fdc620111b0d18ca8","modelId":"glm-4.7-flash","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-4.7-Flash (Reasoning)","configuration":"GLM-4.7-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/glm-4-7-flash","score":21.969696969697,"warning":null},{"id":"371e32e413b5c1e2b63024dc","modelId":"glm-5","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":14.454277286135694,"warning":null},{"id":"3428cabd424a2de0154d82fe","modelId":"glm-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":43.6666666666667,"warning":null},{"id":"fe7a9aae7813ba9b022e0a72","modelId":"glm-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":75.6666666666667,"warning":null},{"id":"08067a5c23ad9c568ec00812","modelId":"glm-5","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":0,"warning":null},{"id":"ae84ac005a4fdeda6ace0f05","modelId":"glm-5","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":2,"warning":null},{"id":"498eceb3c7be3ce505460dd0","modelId":"glm-5","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":81.91666666666666,"warning":null},{"id":"d7755d2a416f32e67386047d","modelId":"glm-5","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":66.5656565656566,"warning":null},{"id":"b9a1cabde7a1e7348cc33f64","modelId":"glm-5","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":82.020202020202,"warning":null},{"id":"16de6f0d8d08fe75b8727d3a","modelId":"glm-5","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":7.645968489341979,"warning":null},{"id":"3fa3e46f37c7db7f5e084225","modelId":"glm-5","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":29.286376274328102,"warning":null},{"id":"13e503950411783d5ec9b173","modelId":"glm-5","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":55.170068027210895,"warning":null},{"id":"b2025179161cc4f662dcc530","modelId":"glm-5","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":72.312925170068,"warning":null},{"id":"7ee2916f2a458729d0bf1b6b","modelId":"glm-5","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":-11.8,"warning":null},{"id":"9d54baf80501bc9f77e431c4","modelId":"glm-5","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":0.266666666666667,"warning":null},{"id":"5a3b5525815de32a23e559dd","modelId":"glm-5","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":23.05,"warning":null},{"id":"8c3a2030b1af48fb9ae3dde5","modelId":"glm-5","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":26.3,"warning":null},{"id":"9229265b86c1968b93d86775","modelId":"glm-5","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":97.3684210526316,"warning":null},{"id":"7cbdf43c125960c2074118eb","modelId":"glm-5","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":98.2456140350877,"warning":null},{"id":"ad5cb316707e497431201b78","modelId":"glm-5","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GLM-5 (Non-reasoning)","configuration":"GLM-5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-non-reasoning","score":39.3939393939394,"warning":null},{"id":"2e99d17495fc238ef6244f56","modelId":"glm-5","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-5 (Reasoning)","configuration":"GLM-5 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5","score":43.1818181818182,"warning":null},{"id":"1f452159e71bb7cf6c9df55c","modelId":"glm-5-turbo","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.6666666666667,"warning":null},{"id":"38fd5b20ee074591cd6ee178","modelId":"glm-5-turbo","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"82f973f0bcc93805188086f9","modelId":"glm-5-turbo","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.74747474747471,"warning":null},{"id":"4768564e465e1b47587ec2d7","modelId":"glm-5-turbo","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.757182576459698,"warning":null},{"id":"6da62a2c7f9a3a460475f9f5","modelId":"glm-5-turbo","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.1972789115646,"warning":null},{"id":"0bdaf0c08a9f5d6437f640a7","modelId":"glm-5-turbo","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":-16.3666666666667,"warning":null},{"id":"0a4a8c34851842bb451eabc3","modelId":"glm-5-turbo","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.449999999999996,"warning":null},{"id":"776868e5b235788549bdbee8","modelId":"glm-5-turbo","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":98.5380116959064,"warning":null},{"id":"556b2cb34128790508b0a194","modelId":"glm-5-turbo","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-5-Turbo","configuration":"GLM-5-Turbo; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.3333333333333,"warning":null},{"id":"a1cfc8028694159742765a26","modelId":"glm-5.1","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":964.01,"warning":null},{"id":"c39102d86367d9fb4babc11b","modelId":"glm-5.1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":53.3333333333333,"warning":null},{"id":"595338c539b2c4564f1d642c","modelId":"glm-5.1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":73.6666666666667,"warning":null},{"id":"fc73ee323b1e28e5bc9197ae","modelId":"glm-5.1","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":20.308354687857076,"warning":null},{"id":"30a13e7c9545cc95c3213936","modelId":"glm-5.1","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":0,"warning":null},{"id":"fc8df65d5ad38aaa1f26ee2c","modelId":"glm-5.1","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":4.57142857142857,"warning":null},{"id":"f5c0ac6e2cf24335a4aafeb8","modelId":"glm-5.1","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":8.4,"warning":null},{"id":"a53881997b19ab4302152797","modelId":"glm-5.1","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":1180.01,"warning":null},{"id":"3af2e846ff223b71f85e5654","modelId":"glm-5.1","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":83.93939393939391,"warning":null},{"id":"54f0aef98b6d8f147c847061","modelId":"glm-5.1","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":86.7676767676768,"warning":null},{"id":"bdf6dc6e16a18d863fbad514","modelId":"glm-5.1","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":27.9425393883225,"warning":null},{"id":"ae183160f013826b3737ac2c","modelId":"glm-5.1","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":30.0741427247451,"warning":null},{"id":"9c83698c69eebf7abc6a73de","modelId":"glm-5.1","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":51.9727891156463,"warning":null},{"id":"485e3cc25dc48e1a9389fc9a","modelId":"glm-5.1","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":76.2585034013605,"warning":null},{"id":"4fb343bd4b97cb79826e7420","modelId":"glm-5.1","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":40.254237288135606,"warning":null},{"id":"d5b509e455ea18ca2e688dc8","modelId":"glm-5.1","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":-22.4333333333333,"warning":null},{"id":"7fdcae53e99c38cc6d93e736","modelId":"glm-5.1","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":0.85,"warning":null},{"id":"e4cb9ffa9390c3c6084fbc6a","modelId":"glm-5.1","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":25.183333333333337,"warning":null},{"id":"29edc738b17c43dc468be90f","modelId":"glm-5.1","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":23.7,"warning":null},{"id":"751a38b92383dd44f4f4b6f8","modelId":"glm-5.1","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":44.7916666666667,"warning":null},{"id":"49be3f22ea03e85c39c33f83","modelId":"glm-5.1","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":97.07602339181291,"warning":null},{"id":"2b4a47e946d0bad8e61425fe","modelId":"glm-5.1","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":97.6608187134503,"warning":null},{"id":"824624d738ab3059a6e8fbd8","modelId":"glm-5.1","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":13.6082474226804,"warning":null},{"id":"f1da9a555bd7b230511bbc67","modelId":"glm-5.1","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GLM-5.1 (Non-reasoning)","configuration":"GLM-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1-non-reasoning","score":35.6060606060606,"warning":null},{"id":"a6d79b63b7974c406cbce5a0","modelId":"glm-5.1","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":43.1818181818182,"warning":null},{"id":"407c1f4b591ee717a0225582","modelId":"glm-5.1","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":61.797752808988804,"warning":null},{"id":"4942502e2f28e870df1cfb21","modelId":"glm-5.1","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"GLM-5.1 (Reasoning)","configuration":"GLM-5.1 (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5-1","score":2.02020202020202,"warning":null},{"id":"b5077a6fd8bbb23f0cf30638","modelId":"glm-5.1","benchmarkId":"terminal-claudecode","level":"max","sourceLabel":"GLM-5.1","configuration":"GLM-5.1; Reported effort: max; 445 trials; recorded 2026-03-27","score":58.65,"warning":null},{"id":"67b15250b5c413661efd7b0e","modelId":"glm-5.2","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":1231.38,"warning":null},{"id":"c55f7602a85dcd8123ca612a","modelId":"glm-5.2","benchmarkId":"aa-apex-agents-aa","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":33.7020648967552,"warning":null},{"id":"18cdac599b2798cbd58f55ac","modelId":"glm-5.2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":78.3333333333333,"warning":null},{"id":"e94927ce7fbb41be1446de36","modelId":"glm-5.2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":42.3333333333333,"warning":null},{"id":"b685b7628055bf6f6e85663c","modelId":"glm-5.2","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":28.398977210054348,"warning":null},{"id":"1a5b16a69844953fd2b67b9a","modelId":"glm-5.2","benchmarkId":"aa-critpt","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":20.8571428571429,"warning":null},{"id":"509692cc7e198e1eba713675","modelId":"glm-5.2","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":3.14285714285714,"warning":null},{"id":"2b0108fef26ae8d59ed7c16d","modelId":"glm-5.2","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":42.733512384362875,"warning":null},{"id":"62f8f1a0d281696ac1bdb1b4","modelId":"glm-5.2","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":10.4,"warning":null},{"id":"517e739317baa8eb42f2d78a","modelId":"glm-5.2","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":1406.07,"warning":null},{"id":"18c42bfe96c85a2bd5b0c271","modelId":"glm-5.2","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":1306.43,"warning":null},{"id":"734f734b8fe4083cb205726a","modelId":"glm-5.2","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":89.49494949494951,"warning":null},{"id":"3a6e78ca66808b560219a6ef","modelId":"glm-5.2","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":68.58585858585859,"warning":null},{"id":"02dde0b3aee40e4db7e181ef","modelId":"glm-5.2","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":90.9683022145028,"warning":null},{"id":"16a667a162f6c87ff81115a1","modelId":"glm-5.2","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":41.1492122335496,"warning":null},{"id":"5734fedef2340bfa5ea45ecc","modelId":"glm-5.2","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":9.7775718257646,"warning":null},{"id":"04cb55028548a3cf387804ed","modelId":"glm-5.2","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":73.3333333333333,"warning":null},{"id":"30b346436bc3eba563c3b0cd","modelId":"glm-5.2","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":42.6553672316384,"warning":null},{"id":"65cdc57d1a980747e1369c54","modelId":"glm-5.2","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":7.2222222222222205,"warning":null},{"id":"0deb219d986680fe5482eff9","modelId":"glm-5.2","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":4.43333333333333,"warning":null},{"id":"d905bff8aaed379cbae34a55","modelId":"glm-5.2","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":-6.56666666666667,"warning":null},{"id":"3c94594dbb5ec187decd3c95","modelId":"glm-5.2","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":24.333333333333336,"warning":null},{"id":"18c771702d3ba14c5fc02b8a","modelId":"glm-5.2","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":20.283333333333335,"warning":null},{"id":"2aee869413c2bc6b49a8cf69","modelId":"glm-5.2","benchmarkId":"aa-scicode","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":51.1574074074074,"warning":null},{"id":"04cdbbf68448a780f51d2317","modelId":"glm-5.2","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":99.1228070175439,"warning":null},{"id":"559a9c09dcdd9d2aac2890d4","modelId":"glm-5.2","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":34.639175257732,"warning":null},{"id":"d298d6a3d4fc3a4d17703a24","modelId":"glm-5.2","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":16.7010309278351,"warning":null},{"id":"5eb3f20394c7766f2c9cb0f7","modelId":"glm-5.2","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":50.7575757575758,"warning":null},{"id":"731debb2ebe4ab8788acee6f","modelId":"glm-5.2","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":77.9026217228464,"warning":null},{"id":"1714719aac77d33cf0b3aa16","modelId":"glm-5.2","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"GLM-5.2 (Non-reasoning)","configuration":"GLM-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/glm-5-2-non-reasoning","score":51.685393258427005,"warning":null},{"id":"5257c396059cf0e1ea69c0fa","modelId":"glm-5.2","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"GLM-5.2 (max)","configuration":"GLM-5.2 (max); Model source: https://artificialanalysis.ai/models/glm-5-2","score":1.01010101010101,"warning":null},{"id":"41fb67eca9e0c6af98ac79d1","modelId":"glm-5.2","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"glm-5-2","configuration":"glm-5-2; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":36.3,"warning":null},{"id":"036eacdadd55f02cf88f8c65","modelId":"glm-5.2","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"glm-5-2","configuration":"glm-5-2; Reported effort: max; 113 unique tasks; 450 attempts; 4 runs","score":43.8,"warning":null},{"id":"be4dbe3360dd3f02bd332d2c","modelId":"glm-5.3","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":1512.51,"warning":null},{"id":"03589e0cd6d71614dbdee7a5","modelId":"glm-5.3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":79.6666666666667,"warning":null},{"id":"8e6fdbe329769f9b2d1bc773","modelId":"glm-5.3","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":62.202864996264196,"warning":null},{"id":"1b2b1bb5c7a2e87c08d5a4c1","modelId":"glm-5.3","benchmarkId":"aa-critpt","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":19.1428571428571,"warning":null},{"id":"395626c3695359937c7d12a8","modelId":"glm-5.3","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":36.436884512085946,"warning":null},{"id":"e7f416a17884df7aef90f9f4","modelId":"glm-5.3","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":11.200000000000001,"warning":null},{"id":"d421e3e8a95478bc0e53938b","modelId":"glm-5.3","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":1667.27,"warning":null},{"id":"a8d48be7c4b3b312fd3982fd","modelId":"glm-5.3","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":91.7171717171717,"warning":null},{"id":"580cd529e7bf91092259785c","modelId":"glm-5.3","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":42.2613531047266,"warning":null},{"id":"c030d58ba58b16f1f98af31d","modelId":"glm-5.3","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":48.3333333333333,"warning":null},{"id":"8dff0f2b52603e6e86eb2d04","modelId":"glm-5.3","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":14.3,"warning":null},{"id":"815c075d82fa152d7eecba36","modelId":"glm-5.3","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":33.85,"warning":null},{"id":"bc1e10b808769dbc5b58076f","modelId":"glm-5.3","benchmarkId":"aa-scicode","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":59.0277777777778,"warning":null},{"id":"4e0077d4dc5e45d0d02cd521","modelId":"glm-5.3","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":50.3092783505155,"warning":null},{"id":"aa57afbaecfad6b6f2b99ee3","modelId":"glm-5.3","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":83.8951310861423,"warning":null},{"id":"3c1ac3e144270be20ee96d03","modelId":"glm-5.3","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"GLM-5.3 (max); Model source: https://artificialanalysis.ai/models/glm-5-3","score":41.9191919191919,"warning":null},{"id":"9e2a553a0ef9312c689f04ed","modelId":"glm-5.3","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"glm-5-3","configuration":"glm-5-3; Reported effort: max; 113 unique tasks; 451 attempts; 4 runs","score":69,"warning":null},{"id":"07489b0b2fa05d32b9093115","modelId":"glm-5.3-flash","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":1449.23,"warning":null},{"id":"2edf5c6a680fd2d04a804ddf","modelId":"glm-5.3-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":80,"warning":null},{"id":"451a12a824fab4ecfd7a24e5","modelId":"glm-5.3-flash","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":60.36862782167782,"warning":null},{"id":"2e29f3fa7a4442d420295d70","modelId":"glm-5.3-flash","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.4285714285714,"warning":null},{"id":"7d01a0db6aef0175ea0ebcc2","modelId":"glm-5.3-flash","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.21396598030439,"warning":null},{"id":"c84d1f50e5616dea725fb651","modelId":"glm-5.3-flash","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.4,"warning":null},{"id":"e3ebc0609117d26f1b3c42a6","modelId":"glm-5.3-flash","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":1655.63,"warning":null},{"id":"bcadd9e7664a3739734c4683","modelId":"glm-5.3-flash","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":91.2121212121212,"warning":null},{"id":"14bbcc046d8a9fe05aa2991a","modelId":"glm-5.3-flash","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.8517145505097,"warning":null},{"id":"18dfc980033586824c069087","modelId":"glm-5.3-flash","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.11111111111109,"warning":null},{"id":"ed40864bcdafb5eb329dcd23","modelId":"glm-5.3-flash","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.46666666666667,"warning":null},{"id":"9bdb6cca3acc7ef5de99c107","modelId":"glm-5.3-flash","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.500000000000004,"warning":null},{"id":"e1954fd811496a176698b207","modelId":"glm-5.3-flash","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.6203703703704,"warning":null},{"id":"8e4e0f16955a0fdb1d162c5f","modelId":"glm-5.3-flash","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.2164948453608,"warning":null},{"id":"3f2e3da28b530a9beae28ba4","modelId":"glm-5.3-flash","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.2696629213483,"warning":null},{"id":"7d247681ca8d8ade3d4bf48a","modelId":"glm-5.3-flash","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"GLM-5.3-Flash","configuration":"GLM-5.3-Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/glm-5-3-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.8282828282828,"warning":null},{"id":"ea4b0ccbfe7ece48ee812e8b","modelId":"glm-5.3-flash","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"glm-5-3-flash","configuration":"glm-5-3-flash; Reported effort: max; 113 unique tasks; 448 attempts; 4 runs","score":63.4,"warning":null},{"id":"f6783606396b8bce8ac51b24","modelId":"glm-5v-turbo","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":70.3333333333333,"warning":null},{"id":"12b6566ca4ca6c13138f9e96","modelId":"glm-5v-turbo","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":0.571428571428571,"warning":null},{"id":"44ad128942762572d234bdd2","modelId":"glm-5v-turbo","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":80.90909090909089,"warning":null},{"id":"16870d51f189414eb5dd849d","modelId":"glm-5v-turbo","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":17.1455050973123,"warning":null},{"id":"37982711b6c81550d0bf0ced","modelId":"glm-5v-turbo","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":61.0884353741497,"warning":null},{"id":"0bac296b6bcdc867575332aa","modelId":"glm-5v-turbo","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":72.7745664739884,"warning":null},{"id":"6f7ad24f8763d179c05b02ec","modelId":"glm-5v-turbo","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":-19.2833333333333,"warning":null},{"id":"4d967b270cc1b306d32a8d0a","modelId":"glm-5v-turbo","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":29.333333333333332,"warning":null},{"id":"8fbfbcae27f2a663fec6ea03","modelId":"glm-5v-turbo","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":98.5380116959064,"warning":null},{"id":"919e117fe8b99db2a9b0924f","modelId":"glm-5v-turbo","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"GLM 5V Turbo (Reasoning)","configuration":"GLM 5V Turbo (Reasoning); Model source: https://artificialanalysis.ai/models/glm-5v-turbo","score":32.5757575757576,"warning":null},{"id":"e86dccdbe57cd031461b162a","modelId":"gpt-3.5-turbo","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-3.5 Turbo","configuration":"GPT-3.5 Turbo; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-35-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.6969696969697,"warning":null},{"id":"7b7b5a85ad55f9f5265d61d4","modelId":"gpt-3.5-turbo","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-3.5 Turbo","configuration":"GPT-3.5 Turbo; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-35-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.0666666666667,"warning":null},{"id":"b4572ee6f0b5d5ed597a0caf","modelId":"gpt-3.5-turbo","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-3.5 Turbo","configuration":"GPT-3.5 Turbo; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-35-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.1851728723404,"warning":null},{"id":"9805c79b15db7da72bfdd42e","modelId":"gpt-4","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-4","configuration":"GPT-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":188.72,"warning":null},{"id":"33dcba80de235a7178254ae4","modelId":"gpt-4","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4","configuration":"GPT-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.949494949494905,"warning":null},{"id":"038ce8230ca4b6eb3d669d9a","modelId":"gpt-4","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-4","configuration":"GPT-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.197278911564595,"warning":null},{"id":"5d475d04cc97cb96522544e6","modelId":"gpt-4","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4","configuration":"GPT-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":56.8,"warning":null},{"id":"6a974fcb30a93f5f4469e5f6","modelId":"gpt-4","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4","configuration":"GPT-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":56.208444148936195,"warning":null},{"id":"1f1a98c6041a0347cedc067b","modelId":"gpt-4","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-4","configuration":"GPT-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":-33.8333333333333,"warning":null},{"id":"9fe1f5fef2e00423fce3cdba","modelId":"gpt-4","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-4","configuration":"GPT-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":21,"warning":null},{"id":"f633b74d416f6bd43ad13675","modelId":"gpt-4-turbo","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4 Turbo","configuration":"GPT-4 Turbo; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.1300000000000003,"warning":null},{"id":"9560dd4fd1468931e9052113","modelId":"gpt-4-turbo","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4 Turbo","configuration":"GPT-4 Turbo; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.100529100529098,"warning":null},{"id":"6ffe256a0e1313ed70520f43","modelId":"gpt-4-turbo","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4 Turbo","configuration":"GPT-4 Turbo; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.6666666666667,"warning":null},{"id":"02bbce731291738c87436522","modelId":"gpt-4-turbo","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4 Turbo","configuration":"GPT-4 Turbo; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-turbo; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.3733377659574,"warning":null},{"id":"71e63379395e6cbc0d8af312","modelId":"gpt-4.1","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.6666666666667,"warning":null},{"id":"6258690b3586212c0ba891ed","modelId":"gpt-4.1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.3333333333333,"warning":null},{"id":"62391a002947467a08c83e49","modelId":"gpt-4.1","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"6341242383674a88e3732cb2","modelId":"gpt-4.1","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.5656565656566,"warning":null},{"id":"08a0c963b233621f21dd0ccb","modelId":"gpt-4.1","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.18,"warning":null},{"id":"4d67dd78b382a9e804734322","modelId":"gpt-4.1","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.9931972789116,"warning":null},{"id":"615f90985d1bd979b83a9644","modelId":"gpt-4.1","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":45.7142857142857,"warning":null},{"id":"fbd303abbd8215370445d77e","modelId":"gpt-4.1","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":91.2666666666667,"warning":null},{"id":"cda7d9aee07435b67e05e255","modelId":"gpt-4.1","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.61835106382979,"warning":null},{"id":"babd604f90f1908b5bafa26a","modelId":"gpt-4.1","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":61.2138728323699,"warning":null},{"id":"516b003dce56d5a7659fc6e1","modelId":"gpt-4.1","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":-39.6333333333333,"warning":null},{"id":"45f0a1fb80d261d7173f15b7","modelId":"gpt-4.1","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.766666666666666,"warning":null},{"id":"2228ebd23f321bb595a53cb8","modelId":"gpt-4.1","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.076023391812896,"warning":null},{"id":"7c2b1459ddc5b975cc6374e5","modelId":"gpt-4.1","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-4.1","configuration":"GPT-4.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.6363636363636,"warning":null},{"id":"eebaae45907cf005abada7c4","modelId":"gpt-4.1-mini","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.3333333333333,"warning":null},{"id":"78e5e2b4996ff8eb159b948d","modelId":"gpt-4.1-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":44,"warning":null},{"id":"fef727774450464c08bdd0f7","modelId":"gpt-4.1-mini","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"daa1afd94711e85445c307d4","modelId":"gpt-4.1-mini","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":453.21,"warning":null},{"id":"2aa8871a8db562e9d18d39f5","modelId":"gpt-4.1-mini","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.3636363636364,"warning":null},{"id":"98e459e9baa066381c77aed4","modelId":"gpt-4.1-mini","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.0200000000000005,"warning":null},{"id":"b899d6847a198d9782271fcf","modelId":"gpt-4.1-mini","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.2993197278912,"warning":null},{"id":"f3555e10497e1abe114c7141","modelId":"gpt-4.1-mini","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.253968253968296,"warning":null},{"id":"22a4815b9fac3ade7ef81d55","modelId":"gpt-4.1-mini","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":92.5333333333333,"warning":null},{"id":"6a981d16086d951f236f90c7","modelId":"gpt-4.1-mini","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.0834441489362,"warning":null},{"id":"e223341eecccef740f030378","modelId":"gpt-4.1-mini","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.728323699422006,"warning":null},{"id":"d5aa5d02a1b67889fcf36b3d","modelId":"gpt-4.1-mini","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":-53.5666666666667,"warning":null},{"id":"b85f2dfb7db4041669025541","modelId":"gpt-4.1-mini","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.316666666666666,"warning":null},{"id":"e0c1df7e5bd17d33c2f2bd4e","modelId":"gpt-4.1-mini","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.9239766081871,"warning":null},{"id":"a234bcb3480d187f78e691a1","modelId":"gpt-4.1-mini","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.36082474226804,"warning":null},{"id":"c9e7e69728999f70de8da6ac","modelId":"gpt-4.1-mini","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.57575757575758,"warning":null},{"id":"4bdb55f172fca20477d7ecfe","modelId":"gpt-4.1-mini","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"GPT-4.1 mini","configuration":"GPT-4.1 mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.1123595505618,"warning":null},{"id":"28ea576bcc8fbc7f7d7c10fa","modelId":"gpt-4.1-nano","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":24,"warning":null},{"id":"489b206164aa46bc047e9442","modelId":"gpt-4.1-nano","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.3333333333333,"warning":null},{"id":"622f6b3b250d7dd489c93fdd","modelId":"gpt-4.1-nano","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"b87adbd661773ab7017dd58f","modelId":"gpt-4.1-nano","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.78,"warning":null},{"id":"0776aad3ae4e24e33e23a782","modelId":"gpt-4.1-nano","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.2121212121212,"warning":null},{"id":"a3e067b47919de9fb8db721d","modelId":"gpt-4.1-nano","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.75347544022243,"warning":null},{"id":"8a4df2fd7696ccf624dc7ec5","modelId":"gpt-4.1-nano","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.0408163265306,"warning":null},{"id":"b423f62f5dc4c141f8ed488b","modelId":"gpt-4.1-nano","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.5925925925926,"warning":null},{"id":"fd5c7d1cec7975be45682128","modelId":"gpt-4.1-nano","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.8,"warning":null},{"id":"77df975eff4ea000f47f5a15","modelId":"gpt-4.1-nano","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":65.6831781914894,"warning":null},{"id":"588685ec1855237622d161dc","modelId":"gpt-4.1-nano","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.1156069364162,"warning":null},{"id":"00077c09ee5961a857ea9812","modelId":"gpt-4.1-nano","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":-57.5833333333333,"warning":null},{"id":"9ac947bf063f982fe5973290","modelId":"gpt-4.1-nano","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.683333333333334,"warning":null},{"id":"123959e1480ca28caac46f0a","modelId":"gpt-4.1-nano","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.2514619883041,"warning":null},{"id":"f223b4e74f1c051e27d17567","modelId":"gpt-4.1-nano","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.50515463917526,"warning":null},{"id":"caebc613dd7096aa01c68408","modelId":"gpt-4.1-nano","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.78787878787879,"warning":null},{"id":"645eb8d2b06c1ca684efea03","modelId":"gpt-4.1-nano","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"GPT-4.1 nano","configuration":"GPT-4.1 nano; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4-1-nano; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.7453183520599302,"warning":null},{"id":"60cd4a91f69f107025375b3f","modelId":"gpt-4o","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-4o (March 2025, chatgpt-4o-latest)","configuration":"GPT-4o (March 2025, chatgpt-4o-latest); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt-03-25; Mode from evaluator isReasoning metadata; effort budget not specified","score":25.6666666666667,"warning":null},{"id":"bc7edbd7f528efe446e8db18","modelId":"gpt-4o","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":6,"warning":null},{"id":"870a8a46a2b531f6c5af62e8","modelId":"gpt-4o","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":41,"warning":null},{"id":"ca8731b9c382bd00c0d8665b","modelId":"gpt-4o","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-4o (ChatGPT)","configuration":"GPT-4o (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":56.00000000000001,"warning":null},{"id":"fddc09f5e0e8bc06d04874e4","modelId":"gpt-4o","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":49.3333333333333,"warning":null},{"id":"2ae788a49fc1d3e582e9f839","modelId":"gpt-4o","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"c2e74edde37a3d7442f9667e","modelId":"gpt-4o","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"24a10eeb3a46c7763c5a63b2","modelId":"gpt-4o","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4o (May '24)","configuration":"GPT-4o (May '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-05-13; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.6262626262626,"warning":null},{"id":"4e82b51b3daf5aa1c8d98aee","modelId":"gpt-4o","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4o (March 2025, chatgpt-4o-latest)","configuration":"GPT-4o (March 2025, chatgpt-4o-latest); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt-03-25; Mode from evaluator isReasoning metadata; effort budget not specified","score":65.4545454545455,"warning":null},{"id":"ba806794d6c0ebc1b2585e8f","modelId":"gpt-4o","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.1212121212121,"warning":null},{"id":"c88594bf8e16a074cc837dfb","modelId":"gpt-4o","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4o (ChatGPT)","configuration":"GPT-4o (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.11111111111109,"warning":null},{"id":"e0c41d17488dc4ec4ba0f0b7","modelId":"gpt-4o","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.3434343434343,"warning":null},{"id":"5b174d58d4c658ab3d23b8bd","modelId":"gpt-4o","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4o (ChatGPT)","configuration":"GPT-4o (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.73,"warning":null},{"id":"676bf2b6f6b8d425be537a91","modelId":"gpt-4o","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4o (March 2025, chatgpt-4o-latest)","configuration":"GPT-4o (March 2025, chatgpt-4o-latest); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt-03-25; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.9699999999999998,"warning":null},{"id":"c5b33db9dc0245a7fa091824","modelId":"gpt-4o","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.42,"warning":null},{"id":"c611da33ffcd9a9e78304e4b","modelId":"gpt-4o","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4o (May '24)","configuration":"GPT-4o (May '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-05-13; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.76,"warning":null},{"id":"fd73d709f3bb83bda7f56ac0","modelId":"gpt-4o","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.33,"warning":null},{"id":"adfbe98a4535a8b4dcbba8db","modelId":"gpt-4o","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.9863945578231,"warning":null},{"id":"e8a8172c365961fe52158eb8","modelId":"gpt-4o","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.285714285714306,"warning":null},{"id":"111a771f0c518f482817be18","modelId":"gpt-4o","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.7460317460317,"warning":null},{"id":"8d6af27176cb848c0da30e16","modelId":"gpt-4o","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4o (May '24)","configuration":"GPT-4o (May '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-05-13; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.4391534391534,"warning":null},{"id":"952674fc62e371988760c75e","modelId":"gpt-4o","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4o (March 2025, chatgpt-4o-latest)","configuration":"GPT-4o (March 2025, chatgpt-4o-latest); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt-03-25; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.5396825396825,"warning":null},{"id":"e26cd77447c8fea5c2954d73","modelId":"gpt-4o","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.8994708994709,"warning":null},{"id":"08df3f3cdd6b93731cef3bfe","modelId":"gpt-4o","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4o (March 2025, chatgpt-4o-latest)","configuration":"GPT-4o (March 2025, chatgpt-4o-latest); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt-03-25; Mode from evaluator isReasoning metadata; effort budget not specified","score":89.26666666666671,"warning":null},{"id":"51e4170d40d5c177fe0231db","modelId":"gpt-4o","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.9333333333333,"warning":null},{"id":"60f11419a7766054a4108a18","modelId":"gpt-4o","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4o (ChatGPT)","configuration":"GPT-4o (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.7333333333333,"warning":null},{"id":"67323d93d4710a1a34a75f0f","modelId":"gpt-4o","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.4666666666667,"warning":null},{"id":"93d23dcf1ef65f2e23f876f9","modelId":"gpt-4o","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4o (May '24)","configuration":"GPT-4o (May '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-05-13; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.1333333333333,"warning":null},{"id":"26a5dad1362342e4f74d3ddc","modelId":"gpt-4o","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4o (March 2025, chatgpt-4o-latest)","configuration":"GPT-4o (March 2025, chatgpt-4o-latest); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt-03-25; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.2942154255319,"warning":null},{"id":"8196e10e1bf2c6ab7a48896c","modelId":"gpt-4o","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.7672872340426,"warning":null},{"id":"893141e7225b21e42fa2ce7d","modelId":"gpt-4o","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4o (ChatGPT)","configuration":"GPT-4o (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.3354388297872,"warning":null},{"id":"ce9dd7a47db415076cf5f8f6","modelId":"gpt-4o","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4o (May '24)","configuration":"GPT-4o (May '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-05-13; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.9527925531915,"warning":null},{"id":"b8d0d0d98797b082257d92e1","modelId":"gpt-4o","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":56.300578034682104,"warning":null},{"id":"39324a10e110c667372e0e04","modelId":"gpt-4o","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":-10.5166666666667,"warning":null},{"id":"a9b3da7256fa223acaa958e2","modelId":"gpt-4o","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":-20.8666666666667,"warning":null},{"id":"750e957428961c84d14679b0","modelId":"gpt-4o","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.7,"warning":null},{"id":"b29b60a9d0d8925b03ed31d5","modelId":"gpt-4o","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.866666666666667,"warning":null},{"id":"007fbaa1f184a893e7a405b1","modelId":"gpt-4o","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.947368421052598,"warning":null},{"id":"79b4fb7fde5db57eeb15ccdc","modelId":"gpt-4o","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":25.1461988304094,"warning":null},{"id":"893788f0d9759cc5abf9ec76","modelId":"gpt-4o","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-4o (Nov '24)","configuration":"GPT-4o (Nov '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.33333333333333,"warning":null},{"id":"9d041de7b25693c5693bff38","modelId":"gpt-4o","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-4o (Aug '24)","configuration":"GPT-4o (Aug '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-2024-08-06; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.33333333333333,"warning":null},{"id":"454128a395b09cae70c46934","modelId":"gpt-4o-mini","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.6666666666667,"warning":null},{"id":"93eb46a4501346f6907da9f0","modelId":"gpt-4o-mini","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":188.06,"warning":null},{"id":"feeff42eebfedd28d3c20c28","modelId":"gpt-4o-mini","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.6262626262626,"warning":null},{"id":"40656865ba698a00d4904512","modelId":"gpt-4o-mini","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.2,"warning":null},{"id":"d07cd6e9ce1790b198fada31","modelId":"gpt-4o-mini","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.952380952381,"warning":null},{"id":"9211c553e48b0e7de26c2187","modelId":"gpt-4o-mini","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.3862433862434,"warning":null},{"id":"a918130cdb50b373f292baf0","modelId":"gpt-4o-mini","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.8666666666667,"warning":null},{"id":"89e1e3c13465dce088558ff9","modelId":"gpt-4o-mini","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"ebe5f26d2cff3c26c1e525dc","modelId":"gpt-4o-mini","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":64.77726063829789,"warning":null},{"id":"9efca0c777e99b96ac172fcc","modelId":"gpt-4o-mini","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.5028901734104,"warning":null},{"id":"cd920a26d682a51dea69c47c","modelId":"gpt-4o-mini","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.88659793814433,"warning":null},{"id":"0fd35df2bab242febe516b4d","modelId":"gpt-4o-mini","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"GPT-4o mini","configuration":"GPT-4o mini; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-4o-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.61797752808989,"warning":null},{"id":"7afd0dd2e0c2831bd43df404","modelId":"gpt-5","benchmarkId":"aa-aime-2025","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":94.3333333333333,"warning":null},{"id":"2978ced94c610a533fc15dcf","modelId":"gpt-5","benchmarkId":"aa-aime-2025","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":83,"warning":null},{"id":"bed6be5aefcab5726cdf356c","modelId":"gpt-5","benchmarkId":"aa-aime-2025","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":91.6666666666667,"warning":null},{"id":"7b75ed3c2005520bcff79192","modelId":"gpt-5","benchmarkId":"aa-aime-2025","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":31.6666666666667,"warning":null},{"id":"a69193c2658d703e3ab0d38f","modelId":"gpt-5","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.3333333333333,"warning":null},{"id":"2ec6f3cf2d9a8a6667b5416f","modelId":"gpt-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":78.2,"warning":null},{"id":"e1edfc9234b1bd40b3f2f40f","modelId":"gpt-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":76,"warning":null},{"id":"886b2d802aa24414c17a9bc7","modelId":"gpt-5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":65,"warning":null},{"id":"b4a62b69cdc0e1a0d5cb8379","modelId":"gpt-5","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":5.71428571428571,"warning":null},{"id":"2b8e7935b9e6eca2dc1c04a7","modelId":"gpt-5","benchmarkId":"aa-critpt","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":1.1428571428571401,"warning":null},{"id":"dccebb85dc27116f61d0ec95","modelId":"gpt-5","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":0,"warning":null},{"id":"8f32c3b7c6a7b931edd13fca","modelId":"gpt-5","benchmarkId":"aa-critpt","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":0,"warning":null},{"id":"97fe07dd084d37ebe2bd1af5","modelId":"gpt-5","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":1014.92,"warning":null},{"id":"6018e12c941db22d9c89342b","modelId":"gpt-5","benchmarkId":"aa-global-mmlu-lite","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":90.66666666666667,"warning":null},{"id":"314e8f1bbc4184a98514f076","modelId":"gpt-5","benchmarkId":"aa-global-mmlu-lite","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":90.39062499999999,"warning":null},{"id":"7f307c0c603f46e975d64aa7","modelId":"gpt-5","benchmarkId":"aa-global-mmlu-lite","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":84.421875,"warning":null},{"id":"e53c717a8e22876c004def0c","modelId":"gpt-5","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":85.3535353535353,"warning":null},{"id":"833910d2932748414e7ebb5a","modelId":"gpt-5","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":80.8080808080808,"warning":null},{"id":"90fa89e6f74cc8dc0598194b","modelId":"gpt-5","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":84.17508417508421,"warning":null},{"id":"e73bd02fe43e5cca4bc8c6a2","modelId":"gpt-5","benchmarkId":"aa-gpqa-diamond","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":67.2727272727273,"warning":null},{"id":"ebf5588481b79006df61a812","modelId":"gpt-5","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.58585858585859,"warning":null},{"id":"94ad8689092c3f208c75fad9","modelId":"gpt-5","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":28.498609823910996,"warning":null},{"id":"e7962edddc555df2dc20ca1c","modelId":"gpt-5","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":19.5551436515292,"warning":null},{"id":"e9c4f38fbea5a2fbb5f0ef73","modelId":"gpt-5","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":25.3938832252085,"warning":null},{"id":"dd50b1a9d15e800849ee68ea","modelId":"gpt-5","benchmarkId":"aa-humanitys-last-exam","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":6.02409638554217,"warning":null},{"id":"de2fbae5009e0d6316cb4494","modelId":"gpt-5","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.62650602409639,"warning":null},{"id":"aefdfb568ca7abbec2079513","modelId":"gpt-5","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":73.06122448979589,"warning":null},{"id":"44ce98b84236dedd7d3bf0c5","modelId":"gpt-5","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":66.5986394557823,"warning":null},{"id":"3b8bc6d894db65ddf0177cf7","modelId":"gpt-5","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":70.6122448979592,"warning":null},{"id":"feaabfee5cf01934c80e5513","modelId":"gpt-5","benchmarkId":"aa-ifbench","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":45.578231292517,"warning":null},{"id":"76566dd933fc00aeb2f0db10","modelId":"gpt-5","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":45.034013605442205,"warning":null},{"id":"eded1079d08788d3af7dc031","modelId":"gpt-5","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":84.5502645502646,"warning":null},{"id":"c15c44a6ad1e030b1e0c26da","modelId":"gpt-5","benchmarkId":"aa-livecodebench","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":76.29629629629629,"warning":null},{"id":"bd00f3071c01b1231d01a8a7","modelId":"gpt-5","benchmarkId":"aa-livecodebench","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":70.2645502645503,"warning":null},{"id":"51134d1b66daccb7f547b8b6","modelId":"gpt-5","benchmarkId":"aa-livecodebench","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":55.7671957671958,"warning":null},{"id":"c65c8b6baa6f11b465f55b52","modelId":"gpt-5","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.285714285714306,"warning":null},{"id":"9fea6793321b322748650d7c","modelId":"gpt-5","benchmarkId":"aa-math-500","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":99.4,"warning":null},{"id":"2b9d978aafb99e1ca5f6db8a","modelId":"gpt-5","benchmarkId":"aa-math-500","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":98.73333333333329,"warning":null},{"id":"9b3c6c148099d10324af1af1","modelId":"gpt-5","benchmarkId":"aa-math-500","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":99.1333333333333,"warning":null},{"id":"63161aa56edc9442139818a7","modelId":"gpt-5","benchmarkId":"aa-math-500","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":86.1333333333333,"warning":null},{"id":"9d2152c4a4c281085f9c1840","modelId":"gpt-5","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":87.0678191489362,"warning":null},{"id":"e499ff7d9dd41c59d2cf26c2","modelId":"gpt-5","benchmarkId":"aa-mmlu-pro","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":85.9790558510638,"warning":null},{"id":"af2e972e296da28768694fd4","modelId":"gpt-5","benchmarkId":"aa-mmlu-pro","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":86.7436835106383,"warning":null},{"id":"7398b8233e31b341403e09d3","modelId":"gpt-5","benchmarkId":"aa-mmlu-pro","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":80.63497340425529,"warning":null},{"id":"5be07669413d5fbc82f7c02d","modelId":"gpt-5","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.0395611702128,"warning":null},{"id":"91b99624fb02eb7e686199f7","modelId":"gpt-5","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":74.2196531791907,"warning":null},{"id":"9080d3104ad2cdaddbdd1934","modelId":"gpt-5","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":73.757225433526,"warning":null},{"id":"7a782b20675f1745dca4b7f6","modelId":"gpt-5","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":74.3352601156069,"warning":null},{"id":"c17ca7be5e2a6d1755562ef9","modelId":"gpt-5","benchmarkId":"aa-mmmu-pro","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":62.080924855491304,"warning":null},{"id":"9b00496d4476acb1c38c5a4b","modelId":"gpt-5","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":-8.73333333333333,"warning":null},{"id":"3f1e0619a146ac6e6cbb8e2f","modelId":"gpt-5","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":-10.7833333333333,"warning":null},{"id":"2b26c17405cd2af3cd3e0ce8","modelId":"gpt-5","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":-10.8666666666667,"warning":null},{"id":"fb32628f32aa74c40826c44f","modelId":"gpt-5","benchmarkId":"aa-omniscience","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":-33.8,"warning":null},{"id":"f47a7ce169e5b924bb59fbf5","modelId":"gpt-5","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":40.31666666666667,"warning":null},{"id":"544e9fde3bdc5b20a3b48fcc","modelId":"gpt-5","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":38.11666666666667,"warning":null},{"id":"5ddade22ee1406e208de826a","modelId":"gpt-5","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":39.483333333333334,"warning":null},{"id":"d4f30e4023a3cd5c890dc0f4","modelId":"gpt-5","benchmarkId":"aa-omniscience-accuracy","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":29.633333333333333,"warning":null},{"id":"a464ae01ac0f5f7f75c50348","modelId":"gpt-5","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":84.7953216374269,"warning":null},{"id":"78115af496f27ad55d68d169","modelId":"gpt-5","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":84.21052631578951,"warning":null},{"id":"c866f1bf891458ba5b21d1e5","modelId":"gpt-5","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":86.5497076023392,"warning":null},{"id":"4bb0fa1567c2b3a28b1a1a94","modelId":"gpt-5","benchmarkId":"aa-tau2-bench","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":66.9590643274854,"warning":null},{"id":"2ed696e37ca20657d9df1361","modelId":"gpt-5","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"63f5a7c021505daa16f98e6d","modelId":"gpt-5","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":22.0618556701031,"warning":null},{"id":"c02210fdaf89f9f0e12d99d4","modelId":"gpt-5","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":32.5757575757576,"warning":null},{"id":"94e1aba89ea3744034f015b4","modelId":"gpt-5","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"GPT-5 (low)","configuration":"GPT-5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-low","score":26.5151515151515,"warning":null},{"id":"9dc51ca56fcc852863e19286","modelId":"gpt-5","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"GPT-5 (medium)","configuration":"GPT-5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-medium","score":37.878787878787904,"warning":null},{"id":"d307de5a94bc7a0c78b7ba2e","modelId":"gpt-5","benchmarkId":"aa-terminalbench-hard","level":"minimal","sourceLabel":"GPT-5 (minimal)","configuration":"GPT-5 (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-minimal","score":18.181818181818198,"warning":null},{"id":"292b0f2eaa1075a11794a0fc","modelId":"gpt-5","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-5 (ChatGPT)","configuration":"GPT-5 (ChatGPT); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/gpt-5-chatgpt; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.8787878787879,"warning":null},{"id":"b5cc6d996a983a7ec027de79","modelId":"gpt-5","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"GPT-5 (high)","configuration":"GPT-5 (high); Model source: https://artificialanalysis.ai/models/gpt-5","score":35.2059925093633,"warning":null},{"id":"cd810b3c8809c7e5dacdc516","modelId":"gpt-5","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5 (High)","configuration":"GPT-5 (High); Source model ID: gpt-5-2025-08-07-high; 120 tasks","score":9.86,"warning":null},{"id":"6d4dee0e98a30d128b276dd5","modelId":"gpt-5","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5 (Low)","configuration":"GPT-5 (Low); Source model ID: gpt-5-2025-08-07-low; 120 tasks","score":1.94,"warning":null},{"id":"88ed12ff4a36b415143266f3","modelId":"gpt-5","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5 (Medium)","configuration":"GPT-5 (Medium); Source model ID: gpt-5-2025-08-07-medium; 120 tasks","score":7.489999999999999,"warning":null},{"id":"3fcb070e5d72027bf895a4eb","modelId":"gpt-5","benchmarkId":"arc-v2semiprivate","level":"minimal","sourceLabel":"GPT-5 (Minimal)","configuration":"GPT-5 (Minimal); Source model ID: gpt-5-2025-08-07-minimal; 120 tasks","score":0,"warning":null},{"id":"bb56015dbdf9bcad0f645fe0","modelId":"gpt-5-mini","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":437.58,"warning":null},{"id":"1271a620f3430d2823b4299b","modelId":"gpt-5-mini","benchmarkId":"aa-aime-2025","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":90.6666666666667,"warning":null},{"id":"b9e17b3cbbc705457a910059","modelId":"gpt-5-mini","benchmarkId":"aa-aime-2025","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":85,"warning":null},{"id":"dc315b6babd5754fe1888c5f","modelId":"gpt-5-mini","benchmarkId":"aa-aime-2025","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":46.6666666666667,"warning":null},{"id":"8f708b652c79fe0a2cb96ee2","modelId":"gpt-5-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":72.3333333333333,"warning":null},{"id":"b8e6f8d6007be0ba8722e722","modelId":"gpt-5-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":72.3333333333333,"warning":null},{"id":"2e73829fce5399bd164125ec","modelId":"gpt-5-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":39.3333333333333,"warning":null},{"id":"a23b0e2e3cd6a9e7f601c733","modelId":"gpt-5-mini","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":6.487466331916088,"warning":null},{"id":"9abc939d215e713e9155509b","modelId":"gpt-5-mini","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":0,"warning":null},{"id":"e66145b99e8be332098068be","modelId":"gpt-5-mini","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":1.42857142857143,"warning":null},{"id":"da13f3721ce5566b3b8d61d3","modelId":"gpt-5-mini","benchmarkId":"aa-critpt","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":0,"warning":null},{"id":"bcdcb630b7de8facd7ec6b9a","modelId":"gpt-5-mini","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":8.4,"warning":null},{"id":"948a35d44f528f1d38a3b66b","modelId":"gpt-5-mini","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":880.27,"warning":null},{"id":"edada08421a44d2f3e03ddd4","modelId":"gpt-5-mini","benchmarkId":"aa-global-mmlu-lite","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":87.42708333333333,"warning":null},{"id":"4de6a5ee986febfaed4eb744","modelId":"gpt-5-mini","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":82.8282828282828,"warning":null},{"id":"4bc1a117796f1bf9d343897d","modelId":"gpt-5-mini","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":80.3030303030303,"warning":null},{"id":"0bb8a1c2b23359f5ba188c31","modelId":"gpt-5-mini","benchmarkId":"aa-gpqa-diamond","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":68.68686868686869,"warning":null},{"id":"d4ded2383bf5737886312cd4","modelId":"gpt-5-mini","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":21.4550509731233,"warning":null},{"id":"d43fe2c78b72cd2774597421","modelId":"gpt-5-mini","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":15.940685820203901,"warning":null},{"id":"8bef9112daab2b8a62ce9988","modelId":"gpt-5-mini","benchmarkId":"aa-humanitys-last-exam","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":5.050973123262279,"warning":null},{"id":"91ccad8d704a295937a940bf","modelId":"gpt-5-mini","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":75.4421768707483,"warning":null},{"id":"0c852c10a1aeb9997ba4c18d","modelId":"gpt-5-mini","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":71.15646258503399,"warning":null},{"id":"6cc6553b8b5f44f42d0cff6d","modelId":"gpt-5-mini","benchmarkId":"aa-ifbench","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":45.578231292517,"warning":null},{"id":"ac22cfeedff8faaf8391a9e7","modelId":"gpt-5-mini","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":83.8095238095238,"warning":null},{"id":"92e0de6f0a6b1d9d6c54d04c","modelId":"gpt-5-mini","benchmarkId":"aa-livecodebench","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":69.2063492063492,"warning":null},{"id":"aea508d42b293a20541f37aa","modelId":"gpt-5-mini","benchmarkId":"aa-livecodebench","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":54.4973544973545,"warning":null},{"id":"4517e6ddfbacac5148c240d1","modelId":"gpt-5-mini","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":83.72672872340429,"warning":null},{"id":"8d8193aa657bab4d267af29d","modelId":"gpt-5-mini","benchmarkId":"aa-mmlu-pro","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":82.7792553191489,"warning":null},{"id":"3a392444daf4274640d0df32","modelId":"gpt-5-mini","benchmarkId":"aa-mmlu-pro","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":77.451795212766,"warning":null},{"id":"fd3f3cb5ed71699740cda268","modelId":"gpt-5-mini","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":70.0578034682081,"warning":null},{"id":"bdbc6cc0360082531b0a111d","modelId":"gpt-5-mini","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":68.8439306358381,"warning":null},{"id":"480b91e9af1b9ea0b14ece2b","modelId":"gpt-5-mini","benchmarkId":"aa-mmmu-pro","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":58.3815028901734,"warning":null},{"id":"987e8a0057a72933ce78e8fa","modelId":"gpt-5-mini","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":-17.3166666666667,"warning":null},{"id":"f7bce3e28e655c5285f0b018","modelId":"gpt-5-mini","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":-11.0333333333333,"warning":null},{"id":"07d410b5a7664b7b7f3f10c0","modelId":"gpt-5-mini","benchmarkId":"aa-omniscience","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":-53.05,"warning":null},{"id":"eba00be8c23a89a00c5a10b0","modelId":"gpt-5-mini","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":24.96666666666667,"warning":null},{"id":"d35182ee44e3d769141e77ef","modelId":"gpt-5-mini","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":23.066666666666666,"warning":null},{"id":"77d0804600c30799618023b2","modelId":"gpt-5-mini","benchmarkId":"aa-omniscience-accuracy","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":19.166666666666668,"warning":null},{"id":"d8f301314bc639970ffe4970","modelId":"gpt-5-mini","benchmarkId":"aa-scicode","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":39.0046296296296,"warning":null},{"id":"c1f5d834e4687add84c92091","modelId":"gpt-5-mini","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":68.4210526315789,"warning":null},{"id":"8fffe4c0f470f545e4bceee4","modelId":"gpt-5-mini","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":71.0526315789474,"warning":null},{"id":"81abc9bd0c31fab2bed3db62","modelId":"gpt-5-mini","benchmarkId":"aa-tau2-bench","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":31.8713450292398,"warning":null},{"id":"0d70a2d525d90c00d5382538","modelId":"gpt-5-mini","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":15.4639175257732,"warning":null},{"id":"bb7e22bf0f8a76fb67df7daf","modelId":"gpt-5-mini","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":33.3333333333333,"warning":null},{"id":"cb279744f928898f4a1303f7","modelId":"gpt-5-mini","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"GPT-5 mini (medium)","configuration":"GPT-5 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-mini-medium","score":28.7878787878788,"warning":null},{"id":"3ed6a32c5fe7f788d3e7fb6f","modelId":"gpt-5-mini","benchmarkId":"aa-terminalbench-hard","level":"minimal","sourceLabel":"GPT-5 mini (minimal)","configuration":"GPT-5 mini (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-mini-minimal","score":14.3939393939394,"warning":null},{"id":"957a65b66d2f331727303705","modelId":"gpt-5-mini","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":3.7453183520599302,"warning":null},{"id":"b4bdc6f08a0a0edd6d04d8e6","modelId":"gpt-5-mini","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"GPT-5 mini (high)","configuration":"GPT-5 mini (high); Model source: https://artificialanalysis.ai/models/gpt-5-mini","score":0,"warning":null},{"id":"849548a81dc92ff4714ec68d","modelId":"gpt-5-mini","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5 Mini (High)","configuration":"GPT-5 Mini (High); Source model ID: gpt-5-mini-2025-08-07-high; 120 tasks","score":4.44,"warning":null},{"id":"c50d5e16d51cce9801649bf5","modelId":"gpt-5-mini","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5 Mini (Low)","configuration":"GPT-5 Mini (Low); Source model ID: gpt-5-mini-2025-08-07-low; 120 tasks","score":0.83,"warning":null},{"id":"0bebc0e4edb23ab523a4bf08","modelId":"gpt-5-mini","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5 Mini (Medium)","configuration":"GPT-5 Mini (Medium); Source model ID: gpt-5-mini-2025-08-07-medium; 120 tasks","score":4.03,"warning":null},{"id":"6a02220558f7ab9b3d8a2e05","modelId":"gpt-5-mini","benchmarkId":"arc-v2semiprivate","level":"minimal","sourceLabel":"GPT-5 Mini (Minimal)","configuration":"GPT-5 Mini (Minimal); Source model ID: gpt-5-mini-2025-08-07-minimal; 120 tasks","score":1.67,"warning":null},{"id":"61bdf3b2d27f1ace40287537","modelId":"gpt-5-nano","benchmarkId":"aa-aime-2025","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":83.6666666666667,"warning":null},{"id":"c991b2fa62637a6be1454b5f","modelId":"gpt-5-nano","benchmarkId":"aa-aime-2025","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":78.3333333333333,"warning":null},{"id":"9b0374451c65b0b8a7ff50c3","modelId":"gpt-5-nano","benchmarkId":"aa-aime-2025","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":27.3333333333333,"warning":null},{"id":"13d6010f81e7fa3cdb5958b7","modelId":"gpt-5-nano","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":45,"warning":null},{"id":"253e6d1def64f85c64b0b28b","modelId":"gpt-5-nano","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":43.6666666666667,"warning":null},{"id":"64dd24dd1517cda4416c0940","modelId":"gpt-5-nano","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":20,"warning":null},{"id":"da129cc262ee6417dba1d29f","modelId":"gpt-5-nano","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":0,"warning":null},{"id":"18af4c452fdf8ca84656fc10","modelId":"gpt-5-nano","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":0,"warning":null},{"id":"c50f1c9e4759fe2cbbec4866","modelId":"gpt-5-nano","benchmarkId":"aa-critpt","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":0,"warning":null},{"id":"26850502e7bfad60ea1747a3","modelId":"gpt-5-nano","benchmarkId":"aa-global-mmlu-lite","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":81.22916666666666,"warning":null},{"id":"6567189c20b9832b2e06413d","modelId":"gpt-5-nano","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":67.5757575757576,"warning":null},{"id":"23cc64a4102c2fbf7f0d7a02","modelId":"gpt-5-nano","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":66.969696969697,"warning":null},{"id":"8f621e321f59f8dbed5a6f93","modelId":"gpt-5-nano","benchmarkId":"aa-gpqa-diamond","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":42.8282828282828,"warning":null},{"id":"d9bd254cfcef9d2712d22317","modelId":"gpt-5-nano","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":9.49953660797034,"warning":null},{"id":"484445c812989992c1caf66c","modelId":"gpt-5-nano","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":8.71177015755329,"warning":null},{"id":"a16ad3a4f80ef4f749aebf00","modelId":"gpt-5-nano","benchmarkId":"aa-humanitys-last-exam","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":3.9851714550509696,"warning":null},{"id":"3cbd5e115e1f8d30021e73c2","modelId":"gpt-5-nano","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":67.5510204081633,"warning":null},{"id":"6139f2a56cafb489a0d5e9a2","modelId":"gpt-5-nano","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":65.9183673469388,"warning":null},{"id":"43dc8e829983dcf65dd49ed1","modelId":"gpt-5-nano","benchmarkId":"aa-ifbench","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":32.5170068027211,"warning":null},{"id":"d0a48c169192e6dc13bc463a","modelId":"gpt-5-nano","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":78.94179894179891,"warning":null},{"id":"cebf68947470466956e5daa2","modelId":"gpt-5-nano","benchmarkId":"aa-livecodebench","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":76.29629629629629,"warning":null},{"id":"2d043407ce66d5fb5604aba1","modelId":"gpt-5-nano","benchmarkId":"aa-livecodebench","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":46.984126984127,"warning":null},{"id":"013b446a39385e3780136c25","modelId":"gpt-5-nano","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":78.0252659574468,"warning":null},{"id":"417196c8a2ed12522dc2bb77","modelId":"gpt-5-nano","benchmarkId":"aa-mmlu-pro","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":77.235704787234,"warning":null},{"id":"13a2a213533ba6d9c09df9fa","modelId":"gpt-5-nano","benchmarkId":"aa-mmlu-pro","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":55.6432845744681,"warning":null},{"id":"d13bcf16f36225a84e762f2a","modelId":"gpt-5-nano","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":60.982658959537595,"warning":null},{"id":"8bfb0a43a3f184fcbb2a73dd","modelId":"gpt-5-nano","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":58.2080924855491,"warning":null},{"id":"faffeb498dc7fd044f7d1b4b","modelId":"gpt-5-nano","benchmarkId":"aa-mmmu-pro","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":31.7919075144509,"warning":null},{"id":"24ff7126b123fbe6a2c9c298","modelId":"gpt-5-nano","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":-28.6666666666667,"warning":null},{"id":"0879c8d5d665baf326d041f1","modelId":"gpt-5-nano","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":-25.7833333333333,"warning":null},{"id":"b9c929a6fa6f2e980e735683","modelId":"gpt-5-nano","benchmarkId":"aa-omniscience","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":-64.0666666666667,"warning":null},{"id":"0fd9c1984793ae6a3d606b3f","modelId":"gpt-5-nano","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":19.083333333333332,"warning":null},{"id":"5631e681e91f5d7cf5e9ed45","modelId":"gpt-5-nano","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":17.583333333333336,"warning":null},{"id":"e6d315631424cf6394c7c95e","modelId":"gpt-5-nano","benchmarkId":"aa-omniscience-accuracy","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":13.083333333333332,"warning":null},{"id":"2d4c5eb419fdd9e604627199","modelId":"gpt-5-nano","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":36.5497076023392,"warning":null},{"id":"b7557fca860bacadf64b9382","modelId":"gpt-5-nano","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":30.409356725146203,"warning":null},{"id":"b2df4bbbd16fd7912105ad99","modelId":"gpt-5-nano","benchmarkId":"aa-tau2-bench","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":25.730994152046797,"warning":null},{"id":"78388e49ee401e48d45b1d6f","modelId":"gpt-5-nano","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"GPT-5 nano (high)","configuration":"GPT-5 nano (high); Model source: https://artificialanalysis.ai/models/gpt-5-nano","score":12.1212121212121,"warning":null},{"id":"927f5c0539489cc0a6dc1e69","modelId":"gpt-5-nano","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"GPT-5 nano (medium)","configuration":"GPT-5 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-nano-medium","score":17.4242424242424,"warning":null},{"id":"0ab95f3b9a2ec250c8aeb819","modelId":"gpt-5-nano","benchmarkId":"aa-terminalbench-hard","level":"minimal","sourceLabel":"GPT-5 nano (minimal)","configuration":"GPT-5 nano (minimal); Model source: https://artificialanalysis.ai/models/gpt-5-nano-minimal","score":6.81818181818182,"warning":null},{"id":"999b6bf8f366cec37f99e596","modelId":"gpt-5-nano","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5 Nano (High)","configuration":"GPT-5 Nano (High); Source model ID: gpt-5-nano-2025-08-07-high; 120 tasks","score":2.6100000000000003,"warning":null},{"id":"f05d176f9e5db89e675db70c","modelId":"gpt-5-nano","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5 Nano (Low)","configuration":"GPT-5 Nano (Low); Source model ID: gpt-5-nano-2025-08-07-low; 120 tasks","score":0,"warning":null},{"id":"b5db4793b8e4f1f4fac5f2e3","modelId":"gpt-5-nano","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5 Nano (Medium)","configuration":"GPT-5 Nano (Medium); Source model ID: gpt-5-nano-2025-08-07-medium; 120 tasks","score":0.88,"warning":null},{"id":"151137af98f4465de79cb3c1","modelId":"gpt-5-nano","benchmarkId":"arc-v2semiprivate","level":"minimal","sourceLabel":"GPT-5 Nano (Minimal)","configuration":"GPT-5 Nano (Minimal); Source model ID: gpt-5-nano-2025-08-07-minimal; 120 tasks","score":0,"warning":null},{"id":"239fa90dfb33619a5081e9f9","modelId":"gpt-5.1","benchmarkId":"aa-aime-2025","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":94,"warning":null},{"id":"6abab40890aa0c0372d0f089","modelId":"gpt-5.1","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":38,"warning":null},{"id":"f4f454e9391cd595d2c59a94","modelId":"gpt-5.1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":80,"warning":null},{"id":"242467cf8ae03ca5317cf999","modelId":"gpt-5.1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":45,"warning":null},{"id":"cebcc0d24f668fcc1ea52594","modelId":"gpt-5.1","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":4.857142857142859,"warning":null},{"id":"9268c5b8746b04887ef9d764","modelId":"gpt-5.1","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":0,"warning":null},{"id":"47fb804697213949c1022802","modelId":"gpt-5.1","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":929.53,"warning":null},{"id":"245233a893e0114ab6b3d52f","modelId":"gpt-5.1","benchmarkId":"aa-global-mmlu-lite","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":90.55729166666666,"warning":null},{"id":"6bd1a0bd70e4ab77e4a980c7","modelId":"gpt-5.1","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":87.27272727272731,"warning":null},{"id":"2fcc61e29b95a07ac78e5842","modelId":"gpt-5.1","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":64.3434343434343,"warning":null},{"id":"0a159bfc6abd91a7c701560d","modelId":"gpt-5.1","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":28.498609823910996,"warning":null},{"id":"7cf4aa2e67a6c7ef11ed452d","modelId":"gpt-5.1","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":5.28266913809083,"warning":null},{"id":"0f2435a7d3956433073252a2","modelId":"gpt-5.1","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":72.8571428571429,"warning":null},{"id":"3cf752361e0a75cc3c1dc615","modelId":"gpt-5.1","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":43.1972789115646,"warning":null},{"id":"36f6e69708f8a4a10940441e","modelId":"gpt-5.1","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":86.7724867724868,"warning":null},{"id":"f1596ea955bb7e7d0db23d9a","modelId":"gpt-5.1","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":49.417989417989396,"warning":null},{"id":"f5dc3af27f6bddfad8d051e8","modelId":"gpt-5.1","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":87.04288563829789,"warning":null},{"id":"15ccd3e2bad00dbe4d513d94","modelId":"gpt-5.1","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":80.1279920212766,"warning":null},{"id":"94dfe52c82affb9fd3334eb7","modelId":"gpt-5.1","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":75.4913294797688,"warning":null},{"id":"6ecc1a5e9d3e0bc1554f7e5a","modelId":"gpt-5.1","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":62.3699421965318,"warning":null},{"id":"f7c1b35ac1102f446ec8ef52","modelId":"gpt-5.1","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":5.4,"warning":null},{"id":"ad964ce0ca054e729c02f3c7","modelId":"gpt-5.1","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":-34.45,"warning":null},{"id":"753b9a8a6643e8cc1e4b81f8","modelId":"gpt-5.1","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":37.71666666666667,"warning":null},{"id":"dcb6c1cfb154e6dfd47677c2","modelId":"gpt-5.1","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":29.46666666666667,"warning":null},{"id":"31bc5bcd1fc862e3317e60bc","modelId":"gpt-5.1","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":81.87134502923979,"warning":null},{"id":"301d76c19099e4fcffbb57c5","modelId":"gpt-5.1","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":46.4912280701754,"warning":null},{"id":"1f211d243e12f56bc1a5a756","modelId":"gpt-5.1","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":15.876288659793799,"warning":null},{"id":"e264fcbbf9c34586e7b6dfb4","modelId":"gpt-5.1","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":45.454545454545496,"warning":null},{"id":"f32ac719f9f42f00e7041db0","modelId":"gpt-5.1","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-5.1 (Non-reasoning)","configuration":"GPT-5.1 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-1-non-reasoning","score":22.727272727272698,"warning":null},{"id":"67f77366629a3d4d08cce1e7","modelId":"gpt-5.1","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"GPT-5.1 (high)","configuration":"GPT-5.1 (high); Model source: https://artificialanalysis.ai/models/gpt-5-1","score":52.4344569288389,"warning":null},{"id":"0fbbe06ee7a41a332409a02a","modelId":"gpt-5.1","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.1 (Thinking, High)","configuration":"GPT-5.1 (Thinking, High); Source model ID: gpt-5-1-2025-11-13-thinking-high; 120 tasks","score":17.64,"warning":null},{"id":"0f99ee8a4e9e3a03a96cb7c2","modelId":"gpt-5.1","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.1 (Thinking, Low)","configuration":"GPT-5.1 (Thinking, Low); Source model ID: gpt-5-1-2025-11-13-thinking-low; 120 tasks","score":1.94,"warning":null},{"id":"be4f45a2511f61842abfae20","modelId":"gpt-5.1","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.1 (Thinking, Medium)","configuration":"GPT-5.1 (Thinking, Medium); Source model ID: gpt-5-1-2025-11-13-thinking-medium; 120 tasks","score":6.529999999999999,"warning":null},{"id":"29c08eeadae8b2d685b7f079","modelId":"gpt-5.1","benchmarkId":"arc-v2semiprivate","level":"none","sourceLabel":"GPT-5.1 (Thinking, None)","configuration":"GPT-5.1 (Thinking, None); Source model ID: gpt-5-1-2025-11-13-thinking-none; 120 tasks","score":0.42,"warning":null},{"id":"5bc5e74d87c25067c627e4bb","modelId":"gpt-5.2","benchmarkId":"aa-aime-2025","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":96.6666666666667,"warning":null},{"id":"43f5bf080d66ec470f227436","modelId":"gpt-5.2","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":51,"warning":null},{"id":"2b1d4ce339f0be508dd782ce","modelId":"gpt-5.2","benchmarkId":"aa-aime-2025","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":99,"warning":null},{"id":"b4acb1581e4d62d9741460e2","modelId":"gpt-5.2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":70.3333333333333,"warning":null},{"id":"97b188f9a482b61245c487bf","modelId":"gpt-5.2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":45.6666666666667,"warning":null},{"id":"15d27807becbd2e61b76c8dd","modelId":"gpt-5.2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":82.6666666666667,"warning":null},{"id":"8618dcdf278a13bab124801f","modelId":"gpt-5.2","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":7.85714285714285,"warning":null},{"id":"39e4db6a2d4b286593f81a2f","modelId":"gpt-5.2","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":0.571428571428571,"warning":null},{"id":"6e1307562e5cedc762ea7855","modelId":"gpt-5.2","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":11.5510204081633,"warning":null},{"id":"30c86445a68217a0a208f023","modelId":"gpt-5.2","benchmarkId":"aa-global-mmlu-lite","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":89.75520833333334,"warning":null},{"id":"8bcbd556ed005557ce8a7b3c","modelId":"gpt-5.2","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":86.80208333333333,"warning":null},{"id":"dafcc8bbf476817926c2900a","modelId":"gpt-5.2","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":86.3636363636364,"warning":null},{"id":"edd0345b8eecf02194512beb","modelId":"gpt-5.2","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":71.2121212121212,"warning":null},{"id":"eafdd4e9bad6ca5f08e931d3","modelId":"gpt-5.2","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":90.3030303030303,"warning":null},{"id":"0d7571d199452fb69e77eeef","modelId":"gpt-5.2","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":26.6913809082484,"warning":null},{"id":"8bf3ce28a17c78a01b889176","modelId":"gpt-5.2","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":8.01668211306766,"warning":null},{"id":"edec1a78b1ba26e435444410","modelId":"gpt-5.2","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":37.6737720111214,"warning":null},{"id":"1ce07261b3d388fb2c493603","modelId":"gpt-5.2","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":65.2380952380953,"warning":null},{"id":"93f2eb1c55112966a4b0b422","modelId":"gpt-5.2","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":47.414965986394606,"warning":null},{"id":"a6c3b23ea9419654c4f638f2","modelId":"gpt-5.2","benchmarkId":"aa-ifbench","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":75.4421768707483,"warning":null},{"id":"2a9d256e31c77a8f35cf66a7","modelId":"gpt-5.2","benchmarkId":"aa-livecodebench","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":89.41798941798939,"warning":null},{"id":"4fdab89ccf0e68eb33edd46b","modelId":"gpt-5.2","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":66.8783068783069,"warning":null},{"id":"c2034e9a0a8098ad23c06ef4","modelId":"gpt-5.2","benchmarkId":"aa-livecodebench","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":88.8888888888889,"warning":null},{"id":"d02cf01c1f12385d68f808a4","modelId":"gpt-5.2","benchmarkId":"aa-mmlu-pro","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":85.85438829787229,"warning":null},{"id":"902ccf2fb17b5ce2a099b850","modelId":"gpt-5.2","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":81.358045212766,"warning":null},{"id":"cbcfd9035f147316126e0cf6","modelId":"gpt-5.2","benchmarkId":"aa-mmlu-pro","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":87.358710106383,"warning":null},{"id":"12032c332a9dd9cc63c917aa","modelId":"gpt-5.2","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":74.5664739884393,"warning":null},{"id":"a3a15fb476b3147892ff7991","modelId":"gpt-5.2","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":65.8381502890173,"warning":null},{"id":"02827ac803609d1fcaaf7843","modelId":"gpt-5.2","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":0.266666666666667,"warning":null},{"id":"818ef12ce3bfce5ac2c89f3b","modelId":"gpt-5.2","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":-12.25,"warning":null},{"id":"9ecf2868fb35108a7e7ef152","modelId":"gpt-5.2","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":-0.883333333333333,"warning":null},{"id":"ef3e4ad9b8ae863c94c78e92","modelId":"gpt-5.2","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":38.28333333333334,"warning":null},{"id":"1e7c4454251c39b4487c0012","modelId":"gpt-5.2","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":30.85,"warning":null},{"id":"200f6e2532cdbd921a373829","modelId":"gpt-5.2","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":44.31666666666666,"warning":null},{"id":"82d00c246f0f4a0a3dd49e01","modelId":"gpt-5.2","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":74.2690058479532,"warning":null},{"id":"c1395f4f5ccb6546d770922c","modelId":"gpt-5.2","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":46.4912280701754,"warning":null},{"id":"be060584c97d18cacb40cd94","modelId":"gpt-5.2","benchmarkId":"aa-tau2-bench","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":84.7953216374269,"warning":null},{"id":"7064152db45f868fe5c922ea","modelId":"gpt-5.2","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":11.1340206185567,"warning":null},{"id":"6a6cf9e4615c5c5fe5261c6b","modelId":"gpt-5.2","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"GPT-5.2 (medium)","configuration":"GPT-5.2 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-2-medium","score":43.1818181818182,"warning":null},{"id":"8a2cead721972b6b2ce7905a","modelId":"gpt-5.2","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-5.2 (Non-reasoning)","configuration":"GPT-5.2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-2-non-reasoning","score":31.818181818181802,"warning":null},{"id":"16d35c254882070f80937822","modelId":"gpt-5.2","benchmarkId":"aa-terminalbench-hard","level":"xhigh","sourceLabel":"GPT-5.2 (xhigh)","configuration":"GPT-5.2 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-2","score":46.969696969697,"warning":null},{"id":"b725135e8e60193d69dd2960","modelId":"gpt-5.2","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.2 (High)","configuration":"GPT-5.2 (High); Source model ID: gpt-5-2-2025-12-11-thinking-high; 120 tasks","score":43.33,"warning":null},{"id":"bdca95afb303a9bc58cb0fba","modelId":"gpt-5.2","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.2 (Low)","configuration":"GPT-5.2 (Low); Source model ID: gpt-5-2-2025-12-11-thinking-low; 120 tasks","score":9.719999999999999,"warning":null},{"id":"17b466b9eb5c749ece0b0106","modelId":"gpt-5.2","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.2 (Medium)","configuration":"GPT-5.2 (Medium); Source model ID: gpt-5-2-2025-12-11-thinking-medium; 120 tasks","score":26.669999999999998,"warning":null},{"id":"5967fa8ce31cc61440245a31","modelId":"gpt-5.2","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.2 (XHigh)","configuration":"GPT-5.2 (XHigh); Source model ID: gpt-5-2-2025-12-11-thinking-xhigh; 120 tasks","score":52.910000000000004,"warning":null},{"id":"26501f216454a4be44cafa23","modelId":"gpt-5.2-pro","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.2 Pro (High)","configuration":"GPT-5.2 Pro (High); Source model ID: gpt-5-2-pro-2025-12-11-high; 120 tasks","score":54.16,"warning":null},{"id":"c69d8d070ed466b0864fd277","modelId":"gpt-5.2-pro","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.2 Pro (Medium)","configuration":"GPT-5.2 Pro (Medium); Source model ID: gpt-5-2-pro-2025-12-11-medium; 120 tasks","score":38.47,"warning":null},{"id":"fc4e29911e90397830821424","modelId":"gpt-5.3-codex","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":865.74,"warning":null},{"id":"3cfdc0adcdfbf4bc5d9d423f","modelId":"gpt-5.3-codex","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":83.3333333333333,"warning":null},{"id":"fc31cb13000d15bacea6922e","modelId":"gpt-5.3-codex","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":16.8571428571429,"warning":null},{"id":"263dabe16bfa078c8e1de364","modelId":"gpt-5.3-codex","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":91.5151515151515,"warning":null},{"id":"6c121d52dec8713a26190404","modelId":"gpt-5.3-codex","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":42.493049119555096,"warning":null},{"id":"771f9183573b3dad01cac7b0","modelId":"gpt-5.3-codex","benchmarkId":"aa-ifbench","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":75.3741496598639,"warning":null},{"id":"a226188131e02839f00830d4","modelId":"gpt-5.3-codex","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":78.4971098265896,"warning":null},{"id":"d2c8a67afe8f17e6b041971b","modelId":"gpt-5.3-codex","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":10.8666666666667,"warning":null},{"id":"719a5465610bb34014bb8403","modelId":"gpt-5.3-codex","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":52.88333333333334,"warning":null},{"id":"5a2a3b23fba84b174082230e","modelId":"gpt-5.3-codex","benchmarkId":"aa-tau2-bench","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":85.9649122807018,"warning":null},{"id":"a2b1e5ebc415de1c9208c5f8","modelId":"gpt-5.3-codex","benchmarkId":"aa-terminalbench-hard","level":"xhigh","sourceLabel":"GPT-5.3 Codex (xhigh)","configuration":"GPT-5.3 Codex (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-3-codex","score":53.030303030303,"warning":null},{"id":"b70ff21cadeade5250a4cdd4","modelId":"gpt-5.4","benchmarkId":"aa-apex-agents-aa","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":33.259587020649,"warning":null},{"id":"3f309b1f6f08733ebeaa0ef9","modelId":"gpt-5.4","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":76.6666666666667,"warning":null},{"id":"95d78edd094271c8788986f1","modelId":"gpt-5.4","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":58.3333333333333,"warning":null},{"id":"1f2febde52d8d84fd8ad145e","modelId":"gpt-5.4","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":82,"warning":null},{"id":"6c4e1bd0b148f6dd51d255ec","modelId":"gpt-5.4","benchmarkId":"aa-critpt","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":7.428571428571431,"warning":null},{"id":"2d984aba50e03049fd01ac4a","modelId":"gpt-5.4","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":0.571428571428571,"warning":null},{"id":"d37b112d29dad129f8c2272c","modelId":"gpt-5.4","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":23.42857143,"warning":null},{"id":"46bbf2825e58cadd1a201fc1","modelId":"gpt-5.4","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":1306.71,"warning":null},{"id":"800c2b0a0a70be8dcb0b707c","modelId":"gpt-5.4","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":87.0707070707071,"warning":null},{"id":"39ae139dd203eb5f9760d5fe","modelId":"gpt-5.4","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":74.8484848484848,"warning":null},{"id":"2344e5d6dcea1f546cabda9b","modelId":"gpt-5.4","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":92.020202020202,"warning":null},{"id":"1c96c49dbfd0aa0da502f5d7","modelId":"gpt-5.4","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":30.8155699721965,"warning":null},{"id":"b486a1fb6c5b341875d5225f","modelId":"gpt-5.4","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":11.2604263206673,"warning":null},{"id":"1f5b6d8b0cbb04daf83a73aa","modelId":"gpt-5.4","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":43.7442075996293,"warning":null},{"id":"7877f48e230cc4baeef262b1","modelId":"gpt-5.4","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":65.9183673469388,"warning":null},{"id":"df4e5119a87760b18053846e","modelId":"gpt-5.4","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":48.4353741496599,"warning":null},{"id":"0e811f1b201ee72834eab6f8","modelId":"gpt-5.4","benchmarkId":"aa-ifbench","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":73.9455782312925,"warning":null},{"id":"de2513acb4a89ca7531cc863","modelId":"gpt-5.4","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":77.9768786127168,"warning":null},{"id":"3aea57a33fca8a2445fb7b9b","modelId":"gpt-5.4","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":70.5780346820809,"warning":null},{"id":"a6f6ccba2bca3ef7bf7d0890","modelId":"gpt-5.4","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":78.4393063583815,"warning":null},{"id":"d716b0e63c7c102a4901c761","modelId":"gpt-5.4","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":4.78333333333333,"warning":null},{"id":"0f3e47626675965f1c173e90","modelId":"gpt-5.4","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":-15.6666666666667,"warning":null},{"id":"c500501b1945eea9d57c2159","modelId":"gpt-5.4","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":5.78333333333333,"warning":null},{"id":"5baf6141fd2ae3e320d68dc7","modelId":"gpt-5.4","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":47.85,"warning":null},{"id":"a69fa647e71e7ea817df5065","modelId":"gpt-5.4","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":37.38333333333333,"warning":null},{"id":"f673516a17545c4423d632a5","modelId":"gpt-5.4","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":50.849999999999994,"warning":null},{"id":"bb7fd95206fa5df765473dad","modelId":"gpt-5.4","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":74.56140350877189,"warning":null},{"id":"d29f2bc805408ffd2df1fcd8","modelId":"gpt-5.4","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":35.964912280701796,"warning":null},{"id":"e6cf2569a32871892e4f8b8d","modelId":"gpt-5.4","benchmarkId":"aa-tau2-bench","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":87.1345029239766,"warning":null},{"id":"7a637545b18b22b592f62617","modelId":"gpt-5.4","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":39.587628865979404,"warning":null},{"id":"e041f09eacf7d4fd39fd06fc","modelId":"gpt-5.4","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"GPT-5.4 (low)","configuration":"GPT-5.4 (low); Model source: https://artificialanalysis.ai/models/gpt-5-4-low","score":43.1818181818182,"warning":null},{"id":"9c16de1fecb482726fe8e501","modelId":"gpt-5.4","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-5.4 (Non-reasoning)","configuration":"GPT-5.4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-non-reasoning","score":37.878787878787904,"warning":null},{"id":"75d0d7792bc9a3baa87c3bb0","modelId":"gpt-5.4","benchmarkId":"aa-terminalbench-hard","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":57.5757575757576,"warning":null},{"id":"be1c7cf00872b8462a1131fe","modelId":"gpt-5.4","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"GPT-5.4 (xhigh)","configuration":"GPT-5.4 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4","score":78.2771535580524,"warning":null},{"id":"b0856c22135884a80af840b3","modelId":"gpt-5.4","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.4 (High)","configuration":"GPT-5.4 (High); Source model ID: gpt-5-4-high; 120 tasks","score":67.5,"warning":null},{"id":"061ce8db3e09b74846381514","modelId":"gpt-5.4","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.4 (Low)","configuration":"GPT-5.4 (Low); Source model ID: gpt-5-4-low; 120 tasks","score":29.17,"warning":null},{"id":"f3c4874853691ebdb76d0676","modelId":"gpt-5.4","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.4 (Medium)","configuration":"GPT-5.4 (Medium); Source model ID: gpt-5-4-medium; 120 tasks","score":55.42,"warning":null},{"id":"5a6430a8d8f773ee0e4b369f","modelId":"gpt-5.4","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.4 (XHigh)","configuration":"GPT-5.4 (XHigh); Source model ID: gpt-5-4-xhigh; 120 tasks","score":73.95,"warning":null},{"id":"38295b12f6b510281d185208","modelId":"gpt-5.4","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"gpt-5-4","configuration":"gpt-5-4; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs","score":51.8,"warning":null},{"id":"62c54d2819ec816195f7efee","modelId":"gpt-5.4","benchmarkId":"swepro-minisweagentstarredrows","level":"xhigh","sourceLabel":"gpt-5.4 (xHigh)*","configuration":"gpt-5.4 (xHigh)*; 731 tasks; source date 2026-04-08","score":59.1,"warning":null},{"id":"2534457eba7560619f63512e","modelId":"gpt-5.4-mini","benchmarkId":"aa-aa-analyst-agent","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":15,"warning":null},{"id":"5520b5130f9fa2fd774713f1","modelId":"gpt-5.4-mini","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":719.24,"warning":null},{"id":"7d7b7db9d9e2d62a4e6255fe","modelId":"gpt-5.4-mini","benchmarkId":"aa-apex-agents-aa","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":28.1710914454277,"warning":null},{"id":"d9e59571f50871ec599909b9","modelId":"gpt-5.4-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":67,"warning":null},{"id":"965e8c06b231b38d68f45540","modelId":"gpt-5.4-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":37,"warning":null},{"id":"5793613cad74b4bf6cb32671","modelId":"gpt-5.4-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":77,"warning":null},{"id":"445494e2c75b91f1b1c72cd2","modelId":"gpt-5.4-mini","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":26.204887225711754,"warning":null},{"id":"c09b14f332df9ba540c4257d","modelId":"gpt-5.4-mini","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":2.85714285714286,"warning":null},{"id":"1f0043eebb5fc496f99c5d41","modelId":"gpt-5.4-mini","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":0,"warning":null},{"id":"335557613d037f1c50797a2a","modelId":"gpt-5.4-mini","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":10,"warning":null},{"id":"44f6a9d0876c62f9969bd2e2","modelId":"gpt-5.4-mini","benchmarkId":"aa-enterprise-ops-gym-aa","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":34.61653237839451,"warning":null},{"id":"9d2598682aeda2b70f8949ff","modelId":"gpt-5.4-mini","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":13.4,"warning":null},{"id":"87338a3e4925e9b09e12613b","modelId":"gpt-5.4-mini","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":734.27,"warning":null},{"id":"368b27fc0d4a6105664dd792","modelId":"gpt-5.4-mini","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":1094.54,"warning":null},{"id":"a32e0b0ff5a7abc081b89492","modelId":"gpt-5.4-mini","benchmarkId":"aa-global-mmlu-lite","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":89.41145833333333,"warning":null},{"id":"836a4fc52dce6b924dd9342b","modelId":"gpt-5.4-mini","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":82.3232323232323,"warning":null},{"id":"bdf8e025a1f4ae5a410deeb3","modelId":"gpt-5.4-mini","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":60.606060606060595,"warning":null},{"id":"1a87bab0335db022f0edf404","modelId":"gpt-5.4-mini","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":87.4747474747475,"warning":null},{"id":"52d38f9a5a5985b6d76dae3f","modelId":"gpt-5.4-mini","benchmarkId":"aa-harvey-lab-aa","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":60.7468519322623,"warning":null},{"id":"7ccfc0bda87f4b31e905be73","modelId":"gpt-5.4-mini","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":18.5820203892493,"warning":null},{"id":"d2f48afd3e9ad8bb0db50802","modelId":"gpt-5.4-mini","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":5.88507877664504,"warning":null},{"id":"37d5d7b1d721fac5dafe7e7b","modelId":"gpt-5.4-mini","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":28.127896200185397,"warning":null},{"id":"1076b1318c5bc4c37d18d8ea","modelId":"gpt-5.4-mini","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":64.7619047619048,"warning":null},{"id":"5b7634e9a4f2aa6ce1c7c3d6","modelId":"gpt-5.4-mini","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":38.843537414966,"warning":null},{"id":"131dd74a1b35809a78362aab","modelId":"gpt-5.4-mini","benchmarkId":"aa-ifbench","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":73.265306122449,"warning":null},{"id":"941548924b2c6866be36f69b","modelId":"gpt-5.4-mini","benchmarkId":"aa-itbench-aa","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":18.6440677966102,"warning":null},{"id":"6c250f07c5969c6b28d8bed0","modelId":"gpt-5.4-mini","benchmarkId":"aa-itbench-aa","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":35.2165725047081,"warning":null},{"id":"dd8bda1b05dc61a3ffb32559","modelId":"gpt-5.4-mini","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":3.88888888888889,"warning":null},{"id":"4d560899b3e3a3783a09b409","modelId":"gpt-5.4-mini","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":71.1560693641618,"warning":null},{"id":"4caf2a595e0d1e29cd4e1527","modelId":"gpt-5.4-mini","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":60.462427745664705,"warning":null},{"id":"8da817cf91aaef2117cf732d","modelId":"gpt-5.4-mini","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":73.2947976878613,"warning":null},{"id":"3e51606290704088b2cbfc50","modelId":"gpt-5.4-mini","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":-20.6166666666667,"warning":null},{"id":"cfa95e087695c99aed69bc84","modelId":"gpt-5.4-mini","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":-45.4166666666667,"warning":null},{"id":"3cd56c92a3dde88ea9a3b202","modelId":"gpt-5.4-mini","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":-18.9166666666667,"warning":null},{"id":"e5f76e8ff788c8b28858d6ff","modelId":"gpt-5.4-mini","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":36.46666666666666,"warning":null},{"id":"f5547369703711b1d6c3e150","modelId":"gpt-5.4-mini","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":25.650000000000002,"warning":null},{"id":"6590cc5a5636c4c28cd7640f","modelId":"gpt-5.4-mini","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":37.46666666666666,"warning":null},{"id":"5352b2fd6acb9f531b953bae","modelId":"gpt-5.4-mini","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":52.0833333333333,"warning":null},{"id":"edcee1bbd3a7ad3470f20bc0","modelId":"gpt-5.4-mini","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":36.5497076023392,"warning":null},{"id":"e02284a264740ec8e4a969e4","modelId":"gpt-5.4-mini","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":23.3918128654971,"warning":null},{"id":"018c19fb8733fd63bd768352","modelId":"gpt-5.4-mini","benchmarkId":"aa-tau2-bench","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":83.3333333333333,"warning":null},{"id":"a187a848fc0ce99eadbd03ad","modelId":"gpt-5.4-mini","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":25.5670103092783,"warning":null},{"id":"b7a2edd91ab0e54985453abe","modelId":"gpt-5.4-mini","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"GPT-5.4 mini (medium)","configuration":"GPT-5.4 mini (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-medium","score":34.0909090909091,"warning":null},{"id":"790a31336a15de7f1c2f3fc7","modelId":"gpt-5.4-mini","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-5.4 mini (Non-Reasoning)","configuration":"GPT-5.4 mini (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini-non-reasoning","score":18.181818181818198,"warning":null},{"id":"57bb57d79d367ebca4969ba8","modelId":"gpt-5.4-mini","benchmarkId":"aa-terminalbench-hard","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":52.2727272727273,"warning":null},{"id":"6d0e3516448fcf9952984320","modelId":"gpt-5.4-mini","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":59.17602996254679,"warning":null},{"id":"7bd37c42f412294161b38513","modelId":"gpt-5.4-mini","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"GPT-5.4 mini (xhigh)","configuration":"GPT-5.4 mini (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-mini","score":2.02020202020202,"warning":null},{"id":"c23a7086cb8ecb85426614bd","modelId":"gpt-5.4-mini","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.4 Mini (High)","configuration":"GPT-5.4 Mini (High); Source model ID: gpt-5-4-mini-high; 120 tasks","score":13.19,"warning":null},{"id":"57762c5e8137a2a5daeba07d","modelId":"gpt-5.4-mini","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.4 Mini (Low)","configuration":"GPT-5.4 Mini (Low); Source model ID: gpt-5-4-mini-low; 120 tasks","score":1.11,"warning":null},{"id":"4da6e2b1da2186d54e3ce949","modelId":"gpt-5.4-mini","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.4 Mini (Medium)","configuration":"GPT-5.4 Mini (Medium); Source model ID: gpt-5-4-mini-medium; 120 tasks","score":4.44,"warning":null},{"id":"ebaca6d5960cef29ea2c77b1","modelId":"gpt-5.4-mini","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.4 Mini (XHigh)","configuration":"GPT-5.4 Mini (XHigh); Source model ID: gpt-5-4-mini-xhigh; 120 tasks","score":18.9,"warning":null},{"id":"6c77624126c7259d8d6689aa","modelId":"gpt-5.4-nano","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":669.58,"warning":null},{"id":"6588a09b2111a94d20040a31","modelId":"gpt-5.4-nano","benchmarkId":"aa-apex-agents-aa","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":24.9262536873156,"warning":null},{"id":"72cfc790291a15bea1f469a0","modelId":"gpt-5.4-nano","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":67.3333333333333,"warning":null},{"id":"a30b6a299803a8c53fc386f6","modelId":"gpt-5.4-nano","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":29.666666666666703,"warning":null},{"id":"cfb7893aafefa95f0bf57eba","modelId":"gpt-5.4-nano","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":76.6666666666667,"warning":null},{"id":"01522a0eb397abe9a4b3e7ad","modelId":"gpt-5.4-nano","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":5.9606130748688075,"warning":null},{"id":"257a53ade2ec0f11fcf6427b","modelId":"gpt-5.4-nano","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":5.14285714285714,"warning":null},{"id":"42418946a505191ef5a70b2d","modelId":"gpt-5.4-nano","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":0,"warning":null},{"id":"f2db0c825f02a829812d96d8","modelId":"gpt-5.4-nano","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":9.253061224489791,"warning":null},{"id":"4878e09873eba784cd6fa9cc","modelId":"gpt-5.4-nano","benchmarkId":"aa-enterprise-ops-gym-aa","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":31.48313936138466,"warning":null},{"id":"28f8e45073342629cbcd1f04","modelId":"gpt-5.4-nano","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":7.8,"warning":null},{"id":"41e3fdfa813ae60884da5e6b","modelId":"gpt-5.4-nano","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":680.74,"warning":null},{"id":"d96b030853fe3babef9db93b","modelId":"gpt-5.4-nano","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":1035.42,"warning":null},{"id":"9cb30bf867f5c1f5053b7a68","modelId":"gpt-5.4-nano","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":76.06060606060609,"warning":null},{"id":"e32c91e5d573f8a290fc9551","modelId":"gpt-5.4-nano","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":55.75757575757579,"warning":null},{"id":"5a42fe3f89a9b765429303d8","modelId":"gpt-5.4-nano","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":81.7171717171717,"warning":null},{"id":"b35fad67d00760fd20d97e51","modelId":"gpt-5.4-nano","benchmarkId":"aa-harvey-lab-aa","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":52.236213634389905,"warning":null},{"id":"8b68876c858e31ea44d4a6e1","modelId":"gpt-5.4-nano","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":15.940685820203901,"warning":null},{"id":"6afbef4b4803b50cde7c41bf","modelId":"gpt-5.4-nano","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":4.07784986098239,"warning":null},{"id":"c5396f9036343c5dd9cd9cda","modelId":"gpt-5.4-nano","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":28.2669138090825,"warning":null},{"id":"957da9c906905cbe92dbeb4b","modelId":"gpt-5.4-nano","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":64.421768707483,"warning":null},{"id":"0b5803afc0439a3888bb92cf","modelId":"gpt-5.4-nano","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":32.7210884353741,"warning":null},{"id":"f9257050d4bc850e6c5e2ecf","modelId":"gpt-5.4-nano","benchmarkId":"aa-ifbench","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":75.9183673469388,"warning":null},{"id":"392fdb79124099bb95eb2e2b","modelId":"gpt-5.4-nano","benchmarkId":"aa-itbench-aa","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":12.909604519774001,"warning":null},{"id":"edfe6c94aa68b7f9c2f45609","modelId":"gpt-5.4-nano","benchmarkId":"aa-itbench-aa","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":24.3879472693032,"warning":null},{"id":"d5ba40fb088648f40631c495","modelId":"gpt-5.4-nano","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":5,"warning":null},{"id":"64edc39fc6734975a7219f93","modelId":"gpt-5.4-nano","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":59.5375722543353,"warning":null},{"id":"0dd63508597a2e4abdeaf990","modelId":"gpt-5.4-nano","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":43.757225433525996,"warning":null},{"id":"4fe52f111e50218f32b63354","modelId":"gpt-5.4-nano","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":65.3757225433526,"warning":null},{"id":"2278d8f84915981206e7d284","modelId":"gpt-5.4-nano","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":-18.0333333333333,"warning":null},{"id":"3ff8dee9b631894975c131fd","modelId":"gpt-5.4-nano","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":-37.4833333333333,"warning":null},{"id":"c4db83fda20000c64985fe3b","modelId":"gpt-5.4-nano","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":-29.4666666666667,"warning":null},{"id":"d29bcef5ace537227fcc55c4","modelId":"gpt-5.4-nano","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":21.9,"warning":null},{"id":"23ff2687c585c8fe5f3e5714","modelId":"gpt-5.4-nano","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":14.883333333333335,"warning":null},{"id":"cc8cd3289013634e97f64c0b","modelId":"gpt-5.4-nano","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":25.666666666666664,"warning":null},{"id":"f36909f44f6bd6e3d03934c3","modelId":"gpt-5.4-nano","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":47.2222222222222,"warning":null},{"id":"52c9b8ac34bbd17642c99bdd","modelId":"gpt-5.4-nano","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":52.631578947368396,"warning":null},{"id":"403a6d3e1ac200e730c8728d","modelId":"gpt-5.4-nano","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":34.7953216374269,"warning":null},{"id":"d71279bf2dc97982cc5495b2","modelId":"gpt-5.4-nano","benchmarkId":"aa-tau2-bench","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":76.0233918128655,"warning":null},{"id":"a7ec7fb8c26351288b7ea90a","modelId":"gpt-5.4-nano","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":27.422680412371097,"warning":null},{"id":"da9ed3465f84dcb583c05cce","modelId":"gpt-5.4-nano","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"GPT-5.4 nano (medium)","configuration":"GPT-5.4 nano (medium); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-medium","score":33.3333333333333,"warning":null},{"id":"e1b9a2e80cbf15c34406293a","modelId":"gpt-5.4-nano","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-5.4 nano (Non-Reasoning)","configuration":"GPT-5.4 nano (Non-Reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning","score":24.2424242424242,"warning":null},{"id":"6bef2b5724ff17eeab4b5045","modelId":"gpt-5.4-nano","benchmarkId":"aa-terminalbench-hard","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":42.4242424242424,"warning":null},{"id":"f7d514c904e2ec6161fae584","modelId":"gpt-5.4-nano","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":60.674157303370805,"warning":null},{"id":"2246eae6e2997e08c4d65de9","modelId":"gpt-5.4-nano","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"GPT-5.4 nano (xhigh)","configuration":"GPT-5.4 nano (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-nano","score":0.505050505050505,"warning":null},{"id":"42f871c2b906d38c584a352f","modelId":"gpt-5.4-nano","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.4 Nano (High)","configuration":"GPT-5.4 Nano (High); Source model ID: gpt-5-4-nano-high; 120 tasks","score":3.61,"warning":null},{"id":"469ea5fe99e4ed4a10b50a81","modelId":"gpt-5.4-nano","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.4 Nano (Low)","configuration":"GPT-5.4 Nano (Low); Source model ID: gpt-5-4-nano-low; 120 tasks","score":1.53,"warning":null},{"id":"04abf124fc7c57207ee66816","modelId":"gpt-5.4-nano","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.4 Nano (Medium)","configuration":"GPT-5.4 Nano (Medium); Source model ID: gpt-5-4-nano-medium; 120 tasks","score":1.94,"warning":null},{"id":"a7b73b0067ddb6090993cb88","modelId":"gpt-5.4-nano","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.4 Nano (XHigh)","configuration":"GPT-5.4 Nano (XHigh); Source model ID: gpt-5-4-nano-xhigh; 120 tasks","score":5.6899999999999995,"warning":null},{"id":"27e4e952645d00a7f8a7d955","modelId":"gpt-5.4-pro","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.4 Pro (xhigh)","configuration":"GPT-5.4 Pro (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-4-pro","score":30,"warning":null},{"id":"eccabedcc721af9865bf90fa","modelId":"gpt-5.4-pro","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.4 Pro (XHigh)","configuration":"GPT-5.4 Pro (XHigh); Source model ID: gpt-5-4-pro-xhigh; 120 tasks","score":83.33,"warning":null},{"id":"6e174c25c1c54ebe5c182868","modelId":"gpt-5.5","benchmarkId":"aa-aa-analyst-agent","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":7.5,"warning":null},{"id":"1555c983a243a17510b40dc4","modelId":"gpt-5.5","benchmarkId":"aa-aa-analyst-agent","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":50,"warning":null},{"id":"d0152373f98f2f553016fc2a","modelId":"gpt-5.5","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":1088.84,"warning":null},{"id":"69efa434ae02e80b795fbbb5","modelId":"gpt-5.5","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":1000,"warning":null},{"id":"7047715ae9bc7a865daf3ed2","modelId":"gpt-5.5","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":1135.79,"warning":null},{"id":"1c8b2c146c296dac71ee160c","modelId":"gpt-5.5","benchmarkId":"aa-apex-agents-aa","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":37.6843657817109,"warning":null},{"id":"90e2155ee6574cbfb408bba6","modelId":"gpt-5.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":84.3333333333333,"warning":null},{"id":"ab8a89f60798f3987c2b7439","modelId":"gpt-5.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":81,"warning":null},{"id":"4fead76f801e079bc637ab4d","modelId":"gpt-5.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":83,"warning":null},{"id":"5cc54c913f0c3c5fd1bfbe8e","modelId":"gpt-5.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":64,"warning":null},{"id":"db1c449553c526c3c0266728","modelId":"gpt-5.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":84.3333333333333,"warning":null},{"id":"0102948a1581c1564f0ee927","modelId":"gpt-5.5","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":44.346163232163846,"warning":null},{"id":"08caf68c49dc84001e718cf3","modelId":"gpt-5.5","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":40.068834155236424,"warning":null},{"id":"b511394630e5ebcd27d413b8","modelId":"gpt-5.5","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":47.300565872933134,"warning":null},{"id":"ee1edf2b4c024e6b6d38419a","modelId":"gpt-5.5","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":25.428571428571402,"warning":null},{"id":"9b1809ab0bd1db8eaddee70f","modelId":"gpt-5.5","benchmarkId":"aa-critpt","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":8,"warning":null},{"id":"2c972a4925d752a97ea28660","modelId":"gpt-5.5","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":18.5714285714286,"warning":null},{"id":"c0135d32f920a750ca394238","modelId":"gpt-5.5","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":1.42857142857143,"warning":null},{"id":"1b28b889a3898a56c690b349","modelId":"gpt-5.5","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":27.142857142857103,"warning":null},{"id":"b5a79a77704aa637fd9795ab","modelId":"gpt-5.5","benchmarkId":"aa-enterprise-ops-gym-aa","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":44.106236944195764,"warning":null},{"id":"d75515c5eac922ebe333874d","modelId":"gpt-5.5","benchmarkId":"aa-enterprise-ops-gym-aa","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":46.64279319606088,"warning":null},{"id":"5abfa43f7467e27e111f92f3","modelId":"gpt-5.5","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":22.6,"warning":null},{"id":"0205ab4d4424d47ea961a60e","modelId":"gpt-5.5","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":20.599999999999998,"warning":null},{"id":"9ddb11bcc92124d67baaef78","modelId":"gpt-5.5","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":21.2,"warning":null},{"id":"4022f7aae075849e8205d262","modelId":"gpt-5.5","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":1371.51,"warning":null},{"id":"9d152fbc61d352c9b84ff711","modelId":"gpt-5.5","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":1112.71,"warning":null},{"id":"4686881dc0789cc81968120c","modelId":"gpt-5.5","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":1288.18,"warning":null},{"id":"6b208e8e21bc42a8199de8c6","modelId":"gpt-5.5","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":1054.41,"warning":null},{"id":"b40075d5b2e59191a241eadc","modelId":"gpt-5.5","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":1395.85,"warning":null},{"id":"09a711065a797c504b74f99c","modelId":"gpt-5.5","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":93.2323232323232,"warning":null},{"id":"a36d0ff8afb79dbbdbfb0f4d","modelId":"gpt-5.5","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":91.010101010101,"warning":null},{"id":"548462147dea4c436e05bcec","modelId":"gpt-5.5","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":92.6262626262626,"warning":null},{"id":"b28eee79d55650b860a152f1","modelId":"gpt-5.5","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":76.76767676767679,"warning":null},{"id":"434bd0d5c4a5bb430cd9f3eb","modelId":"gpt-5.5","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":93.53535353535351,"warning":null},{"id":"2a195cc6518912d9182efcef","modelId":"gpt-5.5","benchmarkId":"aa-harvey-lab-aa","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":86.2787668258793,"warning":null},{"id":"3853cf819c86f900ecd527df","modelId":"gpt-5.5","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":45.0417052826691,"warning":null},{"id":"8d4c21f8dab02b0247fffde8","modelId":"gpt-5.5","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":32.6691380908248,"warning":null},{"id":"78170a0f6e0ee17187ad77d5","modelId":"gpt-5.5","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":42.354031510658004,"warning":null},{"id":"be62a02da138b9b14310aa5d","modelId":"gpt-5.5","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":13.7164040778499,"warning":null},{"id":"0fe44efd80ab7373d4a0b6d0","modelId":"gpt-5.5","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":45.783132530120504,"warning":null},{"id":"7a58774ec1fb4cbf14aaac7e","modelId":"gpt-5.5","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":71.6326530612245,"warning":null},{"id":"2eb0409f9da6a0ee0929913b","modelId":"gpt-5.5","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":64.3537414965986,"warning":null},{"id":"ffde0f1dd99c1c6271ce3439","modelId":"gpt-5.5","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":70.952380952381,"warning":null},{"id":"3e3eb1a94f0b4480f8138f70","modelId":"gpt-5.5","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":46.1224489795918,"warning":null},{"id":"18fa03bfd44b7cfa49c6e776","modelId":"gpt-5.5","benchmarkId":"aa-ifbench","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":75.8503401360544,"warning":null},{"id":"86d356377d78fd0604c1c3c2","modelId":"gpt-5.5","benchmarkId":"aa-itbench-aa","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":45.8097928436911,"warning":null},{"id":"3e715eafe935599163304f3f","modelId":"gpt-5.5","benchmarkId":"aa-mlcr-aa","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":11.1111111111111,"warning":null},{"id":"70f15d54df23ca3059f38070","modelId":"gpt-5.5","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":15,"warning":null},{"id":"264295f63d7a32bebf53fc80","modelId":"gpt-5.5","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":17.7777777777778,"warning":null},{"id":"35fbabaad9b8688274150578","modelId":"gpt-5.5","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":81.0982658959538,"warning":null},{"id":"dfefacfe1b5abecc9a5307fc","modelId":"gpt-5.5","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":79.0173410404624,"warning":null},{"id":"8f840c6e9b5ddcec51c48ee2","modelId":"gpt-5.5","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":81.1560693641619,"warning":null},{"id":"f3711a13a54eefb292d276f3","modelId":"gpt-5.5","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":71.38728323699421,"warning":null},{"id":"3f7b2ffe7858c791c7cb06cf","modelId":"gpt-5.5","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":79.8843930635838,"warning":null},{"id":"66b92c7f427f88d6d7904ffa","modelId":"gpt-5.5","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":18.75,"warning":null},{"id":"77b7eba99ad5a5fc3fec1ac5","modelId":"gpt-5.5","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":15.1,"warning":null},{"id":"02e59ffc919ccd6442705b12","modelId":"gpt-5.5","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":18.1,"warning":null},{"id":"631dd98cd9c042f570e09cdd","modelId":"gpt-5.5","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":-4.75,"warning":null},{"id":"c69cdc7db016bd0188152763","modelId":"gpt-5.5","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":20.5166666666667,"warning":null},{"id":"cdfb469fcfd42ec46534c3e6","modelId":"gpt-5.5","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":57.03333333333334,"warning":null},{"id":"938728d28eadcc0276c3067f","modelId":"gpt-5.5","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":54.85,"warning":null},{"id":"97f48ea80a1054889428f5e9","modelId":"gpt-5.5","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":56.8,"warning":null},{"id":"390acde9b4dd20f84fcd6e76","modelId":"gpt-5.5","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":45.63333333333333,"warning":null},{"id":"f194b42101817c7b5720086d","modelId":"gpt-5.5","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":57.95,"warning":null},{"id":"3f9c3bab82f67b9b5df4c67c","modelId":"gpt-5.5","benchmarkId":"aa-scicode","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":56.1342592592593,"warning":null},{"id":"96bdaef9215773ad68035c89","modelId":"gpt-5.5","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":54.51388888888889,"warning":null},{"id":"debaf5299891f9f141fe4cc2","modelId":"gpt-5.5","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":55.787037037037,"warning":null},{"id":"78f55495a92e1dd015dfa7e2","modelId":"gpt-5.5","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":92.9824561403509,"warning":null},{"id":"9dd16646ebd62ab48b2e0e28","modelId":"gpt-5.5","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":83.9181286549708,"warning":null},{"id":"6c1df08526cb67f7263b2be4","modelId":"gpt-5.5","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":91.812865497076,"warning":null},{"id":"e02f2d421477234c78032860","modelId":"gpt-5.5","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":69.2982456140351,"warning":null},{"id":"9aebf349d59b3cc886404354","modelId":"gpt-5.5","benchmarkId":"aa-tau2-bench","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":93.859649122807,"warning":null},{"id":"febb481ed447a56ff687695d","modelId":"gpt-5.5","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":36.701030927835,"warning":null},{"id":"2a520295b72b53f9c88bde2b","modelId":"gpt-5.5","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":24.9484536082474,"warning":null},{"id":"142188041f1e2ebff8fe4d2c","modelId":"gpt-5.5","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":29.8969072164948,"warning":null},{"id":"3588eb89e953dc5abe08662f","modelId":"gpt-5.5","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":14.8453608247423,"warning":null},{"id":"b4625d73442d6f82dfb89fe0","modelId":"gpt-5.5","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":38.9690721649485,"warning":null},{"id":"a898fd86243ca3a79676c56b","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":59.848484848484894,"warning":null},{"id":"05a390053ae415339bb8f54c","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":52.2727272727273,"warning":null},{"id":"375daa7952f0321b6fb177fb","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":57.5757575757576,"warning":null},{"id":"7d2fcfb4c90f4384817d28c2","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":49.2424242424242,"warning":null},{"id":"5086da290a2b683a13289e77","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-hard","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":60.606060606060595,"warning":null},{"id":"755ecb13869cad91fe1c0123","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":79.40074906367039,"warning":null},{"id":"b1346726febc4a85d3a200f5","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"GPT-5.5 (low); Model source: https://artificialanalysis.ai/models/gpt-5-5-low","score":65.5430711610487,"warning":null},{"id":"67e2b8836084dff484d7b8a0","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":80.5243445692884,"warning":null},{"id":"111185a60b03a16824fda31d","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"GPT-5.5 (Non-reasoning)","configuration":"GPT-5.5 (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-5-non-reasoning","score":61.0486891385768,"warning":null},{"id":"5a487dc8f09788c69c77af1b","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":84.2696629213483,"warning":null},{"id":"1226618afa18c4bbed26581a","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"GPT-5.5 (high); Model source: https://artificialanalysis.ai/models/gpt-5-5-high","score":9.09090909090909,"warning":null},{"id":"7bbd40220411ff27bc823fcd","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"GPT-5.5 (medium); Model source: https://artificialanalysis.ai/models/gpt-5-5-medium","score":5.05050505050505,"warning":null},{"id":"abd5e28d69db084a66ab35ba","modelId":"gpt-5.5","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"GPT-5.5 (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5","score":14.6464646464646,"warning":null},{"id":"bc45f7c6e1d0aab8b73e7aec","modelId":"gpt-5.5","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.5 (High)","configuration":"GPT-5.5 (High); Source model ID: gpt-5-5-2026-04-22-thinking-high; 120 tasks","score":83.33,"warning":null},{"id":"205dbfe9537d5cfd1c612317","modelId":"gpt-5.5","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.5 (Low)","configuration":"GPT-5.5 (Low); Source model ID: gpt-5-5-2026-04-22-thinking-low; 120 tasks","score":33.33,"warning":null},{"id":"58c732552823494e3e219dc6","modelId":"gpt-5.5","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.5 (Medium)","configuration":"GPT-5.5 (Medium); Source model ID: gpt-5-5-2026-04-22-thinking-medium; 120 tasks","score":70.42,"warning":null},{"id":"e082fe244b558a6479f48c03","modelId":"gpt-5.5","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.5 (XHigh)","configuration":"GPT-5.5 (XHigh); Source model ID: gpt-5-5-2026-04-22-thinking-xhigh; 120 tasks","score":85,"warning":null},{"id":"073ccc861e30db90aaf28ba0","modelId":"gpt-5.5","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gpt-5-5","configuration":"gpt-5-5; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":64.4,"warning":null},{"id":"552921ea13a22c9abdd154aa","modelId":"gpt-5.5","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"gpt-5-5","configuration":"gpt-5-5; Reported effort: low; 113 unique tasks; 452 attempts; 4 runs","score":27,"warning":null},{"id":"83db8e5e910b00269a48317e","modelId":"gpt-5.5","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"gpt-5-5","configuration":"gpt-5-5; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs","score":54,"warning":null},{"id":"2171f2252c414c3ccf229887","modelId":"gpt-5.5","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"gpt-5-5","configuration":"gpt-5-5; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs","score":67,"warning":null},{"id":"e58e8485712a3d724ce4a879","modelId":"gpt-5.5","benchmarkId":"terminal-codex","level":"xhigh","sourceLabel":"GPT-5.5","configuration":"GPT-5.5; Reported effort: xhigh; 445 trials; recorded 2026-04-23","score":83.15,"warning":null},{"id":"084e9dff682a86761c6ade08","modelId":"gpt-5.5","benchmarkId":"terminal-terminus2","level":"xhigh","sourceLabel":"GPT-5.5","configuration":"GPT-5.5; Reported effort: xhigh; 445 trials; recorded 2026-04-23","score":77.98,"warning":null},{"id":"2721170b729aceff41261c98","modelId":"gpt-5.5-pro","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.5 Pro (xhigh)","configuration":"GPT-5.5 Pro (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-5-pro","score":30.571428571428598,"warning":null},{"id":"4e24cf58ae552e5e1cac37b5","modelId":"gpt-5.5-pro","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.5 Pro (High)","configuration":"GPT-5.5 Pro (High); Source model ID: gpt-5-5-pro-2026-04-23-high; 120 tasks","score":84.58,"warning":null},{"id":"4e4b0ebdcce2198efad4878e","modelId":"gpt-5.5-pro","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.5 Pro (XHigh)","configuration":"GPT-5.5 Pro (XHigh); Source model ID: gpt-5-5-pro-2026-04-23-xhigh; 120 tasks","score":84.16,"warning":null},{"id":"cce8835bdd40983dc9813222","modelId":"gpt-5.6-luna","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":1173.05,"warning":null},{"id":"9ae52eb4cf2880f7bd01c7cb","modelId":"gpt-5.6-luna","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":743.81,"warning":null},{"id":"3167b8d747931de751cae0b5","modelId":"gpt-5.6-luna","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":1339.38,"warning":null},{"id":"8a726b6dcf749c9acb5c7bbf","modelId":"gpt-5.6-luna","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":934,"warning":null},{"id":"02d05c7abe22fa3285c9ac71","modelId":"gpt-5.6-luna","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":704.43,"warning":null},{"id":"72bda9ee03ada887ab9f5873","modelId":"gpt-5.6-luna","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":1268.01,"warning":null},{"id":"130fcdb5555e8dfecd1cabbe","modelId":"gpt-5.6-luna","benchmarkId":"aa-apex-agents-aa","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":35.8407079646018,"warning":null},{"id":"e83b4b8dc25bfbb27019e9cb","modelId":"gpt-5.6-luna","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":80.3333333333333,"warning":null},{"id":"b5216268e146e799b95dc99c","modelId":"gpt-5.6-luna","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":70,"warning":null},{"id":"856ab16a48655ff4a36054f5","modelId":"gpt-5.6-luna","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":83.6666666666667,"warning":null},{"id":"c7efe6c725ad52ac72d679bb","modelId":"gpt-5.6-luna","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":75,"warning":null},{"id":"86b4187194a5b9f269e16b79","modelId":"gpt-5.6-luna","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":42.6666666666667,"warning":null},{"id":"998c622e7ca5d74bf4f0b53f","modelId":"gpt-5.6-luna","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":81.6666666666667,"warning":null},{"id":"6729e09b403ab4e0dcf0338e","modelId":"gpt-5.6-luna","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":35.58794293060383,"warning":null},{"id":"75bc8e752d3bcda5970ca8d7","modelId":"gpt-5.6-luna","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":11.692162258271626,"warning":null},{"id":"8e5f958068d23d661d725ec6","modelId":"gpt-5.6-luna","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":50.208617637561936,"warning":null},{"id":"a4a9161028703eb2351ca812","modelId":"gpt-5.6-luna","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":23.074538803075942,"warning":null},{"id":"3f206c44a226d2e55701f09e","modelId":"gpt-5.6-luna","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":42.597767374285944,"warning":null},{"id":"9a94ce2ae1cce557c73c568f","modelId":"gpt-5.6-luna","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":16.5714285714286,"warning":null},{"id":"0089ecdcaccc9d09718807ed","modelId":"gpt-5.6-luna","benchmarkId":"aa-critpt","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":2.57142857142857,"warning":null},{"id":"8224f9cb2cbb8895671c5d44","modelId":"gpt-5.6-luna","benchmarkId":"aa-critpt","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":20.571428571428598,"warning":null},{"id":"bfb1abf53ef39946b34f5e34","modelId":"gpt-5.6-luna","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":4.857142857142859,"warning":null},{"id":"db6c8eebd3a0ec57c7656dd0","modelId":"gpt-5.6-luna","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":0.28571428571428603,"warning":null},{"id":"34b547f008ed398a4df7fd80","modelId":"gpt-5.6-luna","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":20.571428571428598,"warning":null},{"id":"ea69d1020a5393a70c8173fb","modelId":"gpt-5.6-luna","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":40.82363473589973,"warning":null},{"id":"2ba86fac5921f386eb9c9a42","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":22.2,"warning":null},{"id":"ca6f41331539c64b2a525ffa","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":14.2,"warning":null},{"id":"6bb1f94024cf4ce3880a9396","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":24,"warning":null},{"id":"ba744ce31ce9f95019e58b0e","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":15.2,"warning":null},{"id":"d58bd2f729dc96c19ee00f4c","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":23.799999999999997,"warning":null},{"id":"5288a983e0221cdb92143a89","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":1375.25,"warning":null},{"id":"a815bbcac49bec64b4d06b0c","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":1075.16,"warning":null},{"id":"d58c9fcb89c2bd7055e1606a","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":1489.33,"warning":null},{"id":"694fa4b4d2530aecbf590015","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":1190.16,"warning":null},{"id":"0d72c6dd5da8de1be61882fe","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":1007.01,"warning":null},{"id":"d1e54282b4f1f8f519b7278f","modelId":"gpt-5.6-luna","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":1428.47,"warning":null},{"id":"76e60c891e3116396dcc7618","modelId":"gpt-5.6-luna","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":89.1919191919192,"warning":null},{"id":"59949b95f1534a3748990225","modelId":"gpt-5.6-luna","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":83.5353535353535,"warning":null},{"id":"3ee7116910b9330ff78fc872","modelId":"gpt-5.6-luna","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":91.1111111111111,"warning":null},{"id":"46ea87c1942d502b2b579cef","modelId":"gpt-5.6-luna","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":85.8585858585859,"warning":null},{"id":"c15d04aa1dd9a38f265a487b","modelId":"gpt-5.6-luna","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":64.54545454545459,"warning":null},{"id":"8dc7c87546ca68ccc7831299","modelId":"gpt-5.6-luna","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":89.49494949494951,"warning":null},{"id":"303cc2990f189d9882c8659d","modelId":"gpt-5.6-luna","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":87.8998407873788,"warning":null},{"id":"4b59c440fd89debc23cade9c","modelId":"gpt-5.6-luna","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":33.4105653382762,"warning":null},{"id":"ecdf8537de73a65fbe62cb3a","modelId":"gpt-5.6-luna","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":19.8331788693234,"warning":null},{"id":"ad38303a78643d9e6c5e4560","modelId":"gpt-5.6-luna","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":39.4810009267841,"warning":null},{"id":"0e39c449a599e4b624e70a50","modelId":"gpt-5.6-luna","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":25.7645968489342,"warning":null},{"id":"47864eccd9ca9b39975cabb8","modelId":"gpt-5.6-luna","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":7.228915662650599,"warning":null},{"id":"8d4ee4765d6cb757e51572ec","modelId":"gpt-5.6-luna","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":36.9786839666358,"warning":null},{"id":"a8209490ef6f3208cc77978c","modelId":"gpt-5.6-luna","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":40.3201506591337,"warning":null},{"id":"4975272e5acbc2aa940a99c7","modelId":"gpt-5.6-luna","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":12.2222222222222,"warning":null},{"id":"fc7d08143c8ee816bb7af3bb","modelId":"gpt-5.6-luna","benchmarkId":"aa-mlcr-aa","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":6.11111111111111,"warning":null},{"id":"dda6ee7aafcb2845bf15f032","modelId":"gpt-5.6-luna","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":19.4444444444444,"warning":null},{"id":"dc0813a1a59d8d5b98332926","modelId":"gpt-5.6-luna","benchmarkId":"aa-mlcr-aa","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":8.33333333333333,"warning":null},{"id":"3d0b5c2f9b2912655f6b841c","modelId":"gpt-5.6-luna","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":16.1111111111111,"warning":null},{"id":"cf832ff3fdefad9e9307166e","modelId":"gpt-5.6-luna","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":77.5722543352601,"warning":null},{"id":"72086a54f01ad01620ebe237","modelId":"gpt-5.6-luna","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":73.9884393063584,"warning":null},{"id":"c8db81fa541ba661730e3ca7","modelId":"gpt-5.6-luna","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":78.5549132947977,"warning":null},{"id":"ddfa3e041821424b91b3d610","modelId":"gpt-5.6-luna","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":75.8381502890173,"warning":null},{"id":"0dfef61c8d999d26f5ea98c9","modelId":"gpt-5.6-luna","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":60.346820809248605,"warning":null},{"id":"c4a092c3788d5c3b17dee941","modelId":"gpt-5.6-luna","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":78.5549132947977,"warning":null},{"id":"dfc8b492223a91f50b185df9","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":-12,"warning":null},{"id":"7d33a31cfbe100e831b57b44","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":-14.65,"warning":null},{"id":"5d9a53e8e9e01657919bbbeb","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":-10.2833333333333,"warning":null},{"id":"715aacb5bd2e20f8cce59472","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":-13.1833333333333,"warning":null},{"id":"150c85bb1557c00c7a6d1ffe","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":-24.95,"warning":null},{"id":"0c21ef5ec77360271acb025c","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":-10.7666666666667,"warning":null},{"id":"3af8b4a0b3967e921bd5faf3","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":41.78333333333333,"warning":null},{"id":"97d73e26297cc5a04b0a10bd","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":39.61666666666667,"warning":null},{"id":"197ae704485f6de2c1c7af50","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":42.733333333333334,"warning":null},{"id":"620c20db96c65c82d77d6437","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":40.699999999999996,"warning":null},{"id":"d46bbeaeae22d52a50c1fecc","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":28.599999999999998,"warning":null},{"id":"f1eb3c4388a173c7eeedd53c","modelId":"gpt-5.6-luna","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":42.449999999999996,"warning":null},{"id":"ce6f3b545cf65ab839014640","modelId":"gpt-5.6-luna","benchmarkId":"aa-scicode","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":51.6203703703704,"warning":null},{"id":"d95bfc8437fd7cf311431cb1","modelId":"gpt-5.6-luna","benchmarkId":"aa-scicode","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":46.064814814814795,"warning":null},{"id":"1b1b538a23511ce91127777b","modelId":"gpt-5.6-luna","benchmarkId":"aa-scicode","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":53.587962962963,"warning":null},{"id":"b05f1a4dd27368185ebfd113","modelId":"gpt-5.6-luna","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":46.7592592592593,"warning":null},{"id":"f032e1b501645e98f29247a2","modelId":"gpt-5.6-luna","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":50.462962962963,"warning":null},{"id":"182c267f7b8e72d819bdef01","modelId":"gpt-5.6-luna","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":25.1546391752577,"warning":null},{"id":"c61935922062d074c492d80f","modelId":"gpt-5.6-luna","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":12.7835051546392,"warning":null},{"id":"905e6d83a9a976db0cea7fff","modelId":"gpt-5.6-luna","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":31.1340206185567,"warning":null},{"id":"001bd78a610f1da56b52d85e","modelId":"gpt-5.6-luna","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":17.7319587628866,"warning":null},{"id":"34aa71f8070e9a1e6ef3977f","modelId":"gpt-5.6-luna","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":9.69072164948454,"warning":null},{"id":"d843e67fd6f0d17091736af0","modelId":"gpt-5.6-luna","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":28.659793814432998,"warning":null},{"id":"17f8252b564348eeb47626ed","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":69.6629213483146,"warning":null},{"id":"5cc464ae02f3e9f2da643da7","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":43.4456928838951,"warning":null},{"id":"3a69ede28148beb260bb5f32","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":80.8988764044944,"warning":null},{"id":"22aeeafcd445d2a241516ed7","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":53.1835205992509,"warning":null},{"id":"4d5b3002c73d51ef146aa99d","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"GPT-5.6 Luna (Non-reasoning)","configuration":"GPT-5.6 Luna (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning","score":38.9513108614232,"warning":null},{"id":"8e45a986273b02dc7f81df27","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":77.9026217228464,"warning":null},{"id":"6a3bb3e493e12f67a8c96ad3","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"GPT-5.6 Luna (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-high","score":2.52525252525253,"warning":null},{"id":"da420896895bc43bf8c2a41b","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"GPT-5.6 Luna (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-low","score":0,"warning":null},{"id":"b9c8d7ace58f0ccdc08bf59c","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"GPT-5.6 Luna (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna","score":11.6161616161616,"warning":null},{"id":"69606b281be372d0c8f5060d","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"GPT-5.6 Luna (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-medium","score":0.505050505050505,"warning":null},{"id":"14294eb2fb3509916b51e379","modelId":"gpt-5.6-luna","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"GPT-5.6 Luna (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh","score":3.53535353535354,"warning":null},{"id":"5d5408de712e8c20684fe7d9","modelId":"gpt-5.6-luna","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.6 Luna (High)","configuration":"GPT-5.6 Luna (High); Source model ID: openai-gpt-5-6-luna-high; 120 tasks","score":29.310000000000002,"warning":null},{"id":"6ffbc8e19c59582d10c22554","modelId":"gpt-5.6-luna","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.6 Luna (Low)","configuration":"GPT-5.6 Luna (Low); Source model ID: openai-gpt-5-6-luna-low; 120 tasks","score":5.140000000000001,"warning":null},{"id":"b2854ee06891af72b895e0a6","modelId":"gpt-5.6-luna","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"GPT-5.6 Luna (Max)","configuration":"GPT-5.6 Luna (Max); Source model ID: openai-gpt-5-6-luna-max; 120 tasks","score":59.540000000000006,"warning":null},{"id":"58b2a2ac3a81857ae37fac17","modelId":"gpt-5.6-luna","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.6 Luna (Medium)","configuration":"GPT-5.6 Luna (Medium); Source model ID: openai-gpt-5-6-luna-medium; 120 tasks","score":7.359999999999999,"warning":null},{"id":"d97b14ae64e526fca71b0f14","modelId":"gpt-5.6-luna","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.6 Luna (XHigh)","configuration":"GPT-5.6 Luna (XHigh); Source model ID: openai-gpt-5-6-luna-xhigh; 120 tasks","score":47.64,"warning":null},{"id":"d581184225be8abecad4b42a","modelId":"gpt-5.6-luna","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gpt-5-6-luna","configuration":"gpt-5-6-luna; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":44.2,"warning":null},{"id":"b56c7ef4cb20e19925c7bcbd","modelId":"gpt-5.6-luna","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"gpt-5-6-luna","configuration":"gpt-5-6-luna; Reported effort: low; 113 unique tasks; 452 attempts; 4 runs","score":1.5,"warning":null},{"id":"41d96fb8508ef9bd7eca956c","modelId":"gpt-5.6-luna","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"gpt-5-6-luna","configuration":"gpt-5-6-luna; Reported effort: max; 113 unique tasks; 448 attempts; 4 runs","score":67.2,"warning":null},{"id":"ce146c74890ffa309e9e6ac3","modelId":"gpt-5.6-luna","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"gpt-5-6-luna","configuration":"gpt-5-6-luna; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs","score":11.3,"warning":null},{"id":"2b08fc13fce99f9456b958dd","modelId":"gpt-5.6-luna","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"gpt-5-6-luna","configuration":"gpt-5-6-luna; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs","score":56.9,"warning":null},{"id":"d6552d55b1ffb5a8f8cd5cc5","modelId":"gpt-5.6-luna","benchmarkId":"terminal-codex","level":"max","sourceLabel":"GPT-5.6 Luna","configuration":"GPT-5.6 Luna; Reported effort: max; 445 trials; recorded 2026-06-26","score":75.73,"warning":null},{"id":"dbb6678796a098c465ad7693","modelId":"gpt-5.6-sol","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":47.5,"warning":null},{"id":"3e13b0797df057f018b4ac2e","modelId":"gpt-5.6-sol","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":1360.88,"warning":null},{"id":"b3f6ddba7d18a254e6a01bfa","modelId":"gpt-5.6-sol","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":1042.06,"warning":null},{"id":"26a18cb1592fa063905e6ed3","modelId":"gpt-5.6-sol","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":1475,"warning":null},{"id":"1ba5a8dbc615b784ccded444","modelId":"gpt-5.6-sol","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":1240.36,"warning":null},{"id":"a1fe717e190f981f5aa05822","modelId":"gpt-5.6-sol","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":1012.78,"warning":null},{"id":"4b3de29f0db37a207872753c","modelId":"gpt-5.6-sol","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":1434.68,"warning":null},{"id":"43e8b61e20fdb59c20e6462f","modelId":"gpt-5.6-sol","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":81.6666666666667,"warning":null},{"id":"4fc71784b9a3eb4248ff7395","modelId":"gpt-5.6-sol","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":78,"warning":null},{"id":"7f264d81d73e1d61369a091b","modelId":"gpt-5.6-sol","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":84,"warning":null},{"id":"fbfdfab14c4b164ffec16ce6","modelId":"gpt-5.6-sol","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":80.3333333333333,"warning":null},{"id":"5b477cc013715702362456cb","modelId":"gpt-5.6-sol","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":62.33333333333329,"warning":null},{"id":"aacce64036ec0f0d8e84e89f","modelId":"gpt-5.6-sol","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":82.3333333333333,"warning":null},{"id":"d31e56c6568b45ad1761e422","modelId":"gpt-5.6-sol","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":55.31220357393729,"warning":null},{"id":"4a79a1eff2db294d172ed855","modelId":"gpt-5.6-sol","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":40.985670113448045,"warning":null},{"id":"afc9edcf049516f411971faa","modelId":"gpt-5.6-sol","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":60.08114996276329,"warning":null},{"id":"3023783527b567d2a67e3b4c","modelId":"gpt-5.6-sol","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":51.327511588639865,"warning":null},{"id":"1d0179989b5bf4843fd20b3d","modelId":"gpt-5.6-sol","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":55.311672693269884,"warning":null},{"id":"374b31984c9bfc5328ef0769","modelId":"gpt-5.6-sol","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":25.7142857142857,"warning":null},{"id":"ac91c9769eb3daff01abac6e","modelId":"gpt-5.6-sol","benchmarkId":"aa-critpt","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":14.857142857142899,"warning":null},{"id":"04c71a7ca3f8e9d23016f19b","modelId":"gpt-5.6-sol","benchmarkId":"aa-critpt","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":32.2857142857143,"warning":null},{"id":"fe671423347370d5fbfd1685","modelId":"gpt-5.6-sol","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":22.8571428571429,"warning":null},{"id":"9b9dbe4777c1a4c323eb5d01","modelId":"gpt-5.6-sol","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":5.14285714285714,"warning":null},{"id":"0934bf143e987370e42469fb","modelId":"gpt-5.6-sol","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":28.571428571428598,"warning":null},{"id":"33c85549be25373443706bce","modelId":"gpt-5.6-sol","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":42.9125634139063,"warning":null},{"id":"0310a1aaf6347a09fede947a","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":27.800000000000004,"warning":null},{"id":"7ed9dbf3e31a81649cfd02ec","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":21,"warning":null},{"id":"875adc69f4aa8909b13bf19e","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":27.200000000000003,"warning":null},{"id":"2a5e7ac9815b8499f396808b","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":26.200000000000003,"warning":null},{"id":"5fa8772d66054f3eee51e969","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":27.6,"warning":null},{"id":"f5b508d43827d30796284beb","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":1524.01,"warning":null},{"id":"4fc514d918600938d56ae075","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":1354.85,"warning":null},{"id":"6c2ef83d138ab32b93ef88d7","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":1624.11,"warning":null},{"id":"d9528e218990bfecc472a95e","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":1456.1,"warning":null},{"id":"e663c8f3737238fb9d6e347b","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":1299.14,"warning":null},{"id":"a56abe5bfd97bb76792c1893","modelId":"gpt-5.6-sol","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":1584.88,"warning":null},{"id":"96ff192b147ad396e888ae9a","modelId":"gpt-5.6-sol","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":92.82828282828281,"warning":null},{"id":"9f5704a90ff59264335a0fbc","modelId":"gpt-5.6-sol","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":89.79797979797979,"warning":null},{"id":"00f3ed01079864e0a71ddb7e","modelId":"gpt-5.6-sol","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":94.1414141414141,"warning":null},{"id":"4b02c53f17931e0611130b75","modelId":"gpt-5.6-sol","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":92.6262626262626,"warning":null},{"id":"5c89f4aedb58325a99416195","modelId":"gpt-5.6-sol","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":78.989898989899,"warning":null},{"id":"734e78470097075663683c6f","modelId":"gpt-5.6-sol","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":93.13131313131309,"warning":null},{"id":"985f2998ffeb8bda69255f09","modelId":"gpt-5.6-sol","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":87.1761470545665,"warning":null},{"id":"ddc38dc05a8c2148da4d0b49","modelId":"gpt-5.6-sol","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":46.014828544949,"warning":null},{"id":"48f0cd2d5fb346e209366d47","modelId":"gpt-5.6-sol","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":39.3883225208526,"warning":null},{"id":"e48011239d82bdd7eecb7877","modelId":"gpt-5.6-sol","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":49.4902687673772,"warning":null},{"id":"1a14c93bba5879e21154eb3c","modelId":"gpt-5.6-sol","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":42.2150139017609,"warning":null},{"id":"46dab6b30ddf4f6a6277b5bb","modelId":"gpt-5.6-sol","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":16.682113067655198,"warning":null},{"id":"cdd519b2333828133a5ed982","modelId":"gpt-5.6-sol","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":47.3123262279889,"warning":null},{"id":"18ede9f6bd90825a01e9163d","modelId":"gpt-5.6-sol","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":69.1836734693878,"warning":null},{"id":"c8c6b3afce23ad69ce7ee3c1","modelId":"gpt-5.6-sol","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":66.53061224489801,"warning":null},{"id":"5351d2eecf30c83b35817587","modelId":"gpt-5.6-sol","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":72.6530612244898,"warning":null},{"id":"5248437a4fabf5fb53c069a5","modelId":"gpt-5.6-sol","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":69.5918367346939,"warning":null},{"id":"9360c47d82412d751eec04a0","modelId":"gpt-5.6-sol","benchmarkId":"aa-ifbench","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":71.0204081632653,"warning":null},{"id":"3dfc7cea1f17f5b6c9939d76","modelId":"gpt-5.6-sol","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":56.2146892655367,"warning":null},{"id":"4938b0cfad18d1bcbfd8413c","modelId":"gpt-5.6-sol","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":17.2222222222222,"warning":null},{"id":"1d039a2600471fdd98591aeb","modelId":"gpt-5.6-sol","benchmarkId":"aa-mlcr-aa","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":12.7777777777778,"warning":null},{"id":"c49c48c890b3be06f4a43ffe","modelId":"gpt-5.6-sol","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":26.1111111111111,"warning":null},{"id":"65616cc744847daa5af4b6f8","modelId":"gpt-5.6-sol","benchmarkId":"aa-mlcr-aa","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":15,"warning":null},{"id":"e05ceac233710b02ca5fba32","modelId":"gpt-5.6-sol","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":18.3333333333333,"warning":null},{"id":"6c16e8f935fc3fbc0cc1bfd4","modelId":"gpt-5.6-sol","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":81.84971098265899,"warning":null},{"id":"7dc7485ae3112a509863bacb","modelId":"gpt-5.6-sol","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":80.9826589595376,"warning":null},{"id":"6e4ef7a0d80b54b2b4f40df8","modelId":"gpt-5.6-sol","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":83.4104046242775,"warning":null},{"id":"9e1214963abbedfbd236f1d7","modelId":"gpt-5.6-sol","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":81.38728323699421,"warning":null},{"id":"eaf5836dc0d624ab48f5d238","modelId":"gpt-5.6-sol","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":71.90751445086701,"warning":null},{"id":"7af2d5b89b2876daaa95166a","modelId":"gpt-5.6-sol","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":82.6589595375723,"warning":null},{"id":"a3575021ed42f7eefce75c85","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":20.3666666666667,"warning":null},{"id":"8a235fa1b4c25978fa241e47","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":18.8666666666667,"warning":null},{"id":"280829df0609ed1382ed4a5d","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":21.9666666666667,"warning":null},{"id":"7e0039eb395cbe91e7c8810d","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":19.4,"warning":null},{"id":"52cbe7096d25c4e59ae6c392","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":1.1,"warning":null},{"id":"6e384940f06acf726078ee36","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":20.9833333333333,"warning":null},{"id":"cabcf5c45622732e23c417fd","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":58.35,"warning":null},{"id":"6681f350443008f8fceefd48","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":57.166666666666664,"warning":null},{"id":"632ef0e8d2883b55e55e1c3a","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":59.4,"warning":null},{"id":"17566693e8a8fbb09dbf7cbe","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":57.75,"warning":null},{"id":"d8c39b5b1f8cffe20bc488a4","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":48.699999999999996,"warning":null},{"id":"bbbe310343957c43bc35b785","modelId":"gpt-5.6-sol","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":58.81666666666666,"warning":null},{"id":"ef3791ef2791a9849a7cc230","modelId":"gpt-5.6-sol","benchmarkId":"aa-scicode","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":57.7546296296296,"warning":null},{"id":"edf5d917eca3ccce858fedd4","modelId":"gpt-5.6-sol","benchmarkId":"aa-scicode","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":56.3657407407407,"warning":null},{"id":"a2acf89349f68435cd22ccde","modelId":"gpt-5.6-sol","benchmarkId":"aa-scicode","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":57.0601851851852,"warning":null},{"id":"d7451fad1dff4c15ecdcbebe","modelId":"gpt-5.6-sol","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":57.4074074074074,"warning":null},{"id":"3b319780d68012d2aa8b2b8d","modelId":"gpt-5.6-sol","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":57.0601851851852,"warning":null},{"id":"ac708520fd129a87e0711859","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":83.3333333333333,"warning":null},{"id":"07b7ecc7d47057f40710f618","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":76.0233918128655,"warning":null},{"id":"b5839a1f4954b5ac6747e3a4","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":85.0877192982456,"warning":null},{"id":"0fcf67e993f0a396e4bd615e","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":80.9941520467836,"warning":null},{"id":"1c17d26923573df115fbe521","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau2-bench","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":84.7953216374269,"warning":null},{"id":"d229dde6dba74ddd2adfedae","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":36.701030927835,"warning":null},{"id":"af6ff9f9a7007f68a56908df","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":29.0721649484536,"warning":null},{"id":"974f6bd0bff5e3a6f76e05ea","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":44.3298969072165,"warning":null},{"id":"5b14b8bbad5f6e66599f14fa","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":36.4948453608247,"warning":null},{"id":"08b420cc86ad300f73cb6ece","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":19.5876288659794,"warning":null},{"id":"2f0420d7590f84996d2ea9d9","modelId":"gpt-5.6-sol","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":38.144329896907195,"warning":null},{"id":"4ebc9090dbe06e85cc04ef19","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":62.121212121212096,"warning":null},{"id":"0f97d02e06ce3b15733d575a","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":60.606060606060595,"warning":null},{"id":"c678da667a6203b26e10bae0","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":65.90909090909089,"warning":null},{"id":"ccb8868cd62c35d4ada53758","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":62.878787878787904,"warning":null},{"id":"424bfb7f9a3e98f06a09af81","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-hard","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":61.363636363636395,"warning":null},{"id":"dca4fe966c9bade5a782bbe3","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":87.2659176029963,"warning":null},{"id":"7bdff50e874a09b8eb58d148","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":76.77902621722849,"warning":null},{"id":"e82c94bca1327e12e4c3458a","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":88.0149812734082,"warning":null},{"id":"f0a5454443397c5905ef4d54","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":86.1423220973783,"warning":null},{"id":"3dd6efbb347ef62f98104dbb","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"GPT-5.6 Sol (Non-reasoning)","configuration":"GPT-5.6 Sol (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning","score":74.1573033707865,"warning":null},{"id":"98f6e9db1815d631c07dc6a0","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":89.5131086142322,"warning":null},{"id":"ecb1e1f34aa85b54b5bf67a4","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-high","score":20.7070707070707,"warning":null},{"id":"c982eec64beba458859ce0cd","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-low","score":1.01010101010101,"warning":null},{"id":"6dd9cabb0925f9fe971ca60a","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"GPT-5.6 Sol (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol","score":39.8989898989899,"warning":null},{"id":"e737a7759ccb7886c36e2835","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-medium","score":14.6464646464646,"warning":null},{"id":"908118dc12cb8a5c5991be3e","modelId":"gpt-5.6-sol","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"GPT-5.6 Sol (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh","score":24.747474747474698,"warning":null},{"id":"44d14513877192a9ab52ca19","modelId":"gpt-5.6-sol","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.6 Sol (High)","configuration":"GPT-5.6 Sol (High); Source model ID: openai-gpt-5-6-sol-high; 120 tasks","score":85.42,"warning":null},{"id":"807ea1d13e6eff4620060049","modelId":"gpt-5.6-sol","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.6 Sol (Low)","configuration":"GPT-5.6 Sol (Low); Source model ID: openai-gpt-5-6-sol-low; 120 tasks","score":42.5,"warning":null},{"id":"2b83cb97a7ce702b83c5f1a1","modelId":"gpt-5.6-sol","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"GPT-5.6 Sol (Max)","configuration":"GPT-5.6 Sol (Max); Source model ID: openai-gpt-5-6-sol-max; 120 tasks","score":92.5,"warning":null},{"id":"c14d5d98e2ac0c35e12373b0","modelId":"gpt-5.6-sol","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.6 Sol (Medium)","configuration":"GPT-5.6 Sol (Medium); Source model ID: openai-gpt-5-6-sol-medium; 120 tasks","score":67.08,"warning":null},{"id":"b9714ddbf13fb44d8cbb4989","modelId":"gpt-5.6-sol","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.6 Sol (XHigh)","configuration":"GPT-5.6 Sol (XHigh); Source model ID: openai-gpt-5-6-sol-xhigh; 120 tasks","score":90,"warning":null},{"id":"3289fff293acd220d866101d","modelId":"gpt-5.6-sol","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gpt-5-6-sol","configuration":"gpt-5-6-sol; Reported effort: high; 113 unique tasks; 451 attempts; 4 runs","score":69.4,"warning":null},{"id":"f7154b7752b50075526308bc","modelId":"gpt-5.6-sol","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"gpt-5-6-sol","configuration":"gpt-5-6-sol; Reported effort: low; 113 unique tasks; 452 attempts; 4 runs","score":45.4,"warning":null},{"id":"8ee05b294998d24ac869adf8","modelId":"gpt-5.6-sol","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"gpt-5-6-sol","configuration":"gpt-5-6-sol; Reported effort: max; 113 unique tasks; 450 attempts; 4 runs","score":72.7,"warning":null},{"id":"fd0b93e69454c6e0b78551ea","modelId":"gpt-5.6-sol","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"gpt-5-6-sol","configuration":"gpt-5-6-sol; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs","score":61.1,"warning":null},{"id":"045b52fd58198f20f15b3ce9","modelId":"gpt-5.6-sol","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"gpt-5-6-sol","configuration":"gpt-5-6-sol; Reported effort: xhigh; 113 unique tasks; 451 attempts; 4 runs","score":70.7,"warning":null},{"id":"f837b509fff80b3fd9db2ed8","modelId":"gpt-5.6-terra","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":1201.36,"warning":null},{"id":"fad35c7386624c2a0c2ac667","modelId":"gpt-5.6-terra","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":1014.49,"warning":null},{"id":"62794428b0bd5556f2e3b55d","modelId":"gpt-5.6-terra","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":1330,"warning":null},{"id":"f69d5838266c7bec7767e88e","modelId":"gpt-5.6-terra","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":1040.72,"warning":null},{"id":"b0bb3e44bfba219e986f640d","modelId":"gpt-5.6-terra","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":946.69,"warning":null},{"id":"9cf9b8871f98f2f3dc6e9717","modelId":"gpt-5.6-terra","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":1337.28,"warning":null},{"id":"a40b0840d2c40ef5cde0e911","modelId":"gpt-5.6-terra","benchmarkId":"aa-apex-agents-aa","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":38.9380530973451,"warning":null},{"id":"3e918305b007fc81bea460c3","modelId":"gpt-5.6-terra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":77.6666666666667,"warning":null},{"id":"a7a9d82047bd5fde60daa5eb","modelId":"gpt-5.6-terra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":71.3333333333333,"warning":null},{"id":"7f7d02623829941ccc857e01","modelId":"gpt-5.6-terra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":83,"warning":null},{"id":"d9411741547a9ce320fc3b7c","modelId":"gpt-5.6-terra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":74,"warning":null},{"id":"558071cbc1fad71c429098b9","modelId":"gpt-5.6-terra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":58.6666666666667,"warning":null},{"id":"137c3a9aa2b092d9dbdc6f1c","modelId":"gpt-5.6-terra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":79,"warning":null},{"id":"3000072f94bc4328db441f14","modelId":"gpt-5.6-terra","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":42.02038295182785,"warning":null},{"id":"037c70d5b9f11f368b0b0598","modelId":"gpt-5.6-terra","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":29.106376138008166,"warning":null},{"id":"5fad8351a8fe27cddc29e147","modelId":"gpt-5.6-terra","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":59.64995802534495,"warning":null},{"id":"73d74bc56842a1d8b5be5c1c","modelId":"gpt-5.6-terra","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":33.536040384184965,"warning":null},{"id":"d85f1b4a2a8201a16399f3cf","modelId":"gpt-5.6-terra","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":47.13631340597769,"warning":null},{"id":"a40b76164fe807dfafb5a7c4","modelId":"gpt-5.6-terra","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":22.8571428571429,"warning":null},{"id":"3bcddbf64272cee4d28baf5d","modelId":"gpt-5.6-terra","benchmarkId":"aa-critpt","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":9.42857142857143,"warning":null},{"id":"e2d291031635829ba6765af0","modelId":"gpt-5.6-terra","benchmarkId":"aa-critpt","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":30,"warning":null},{"id":"273cbfb2e0ade778457c9c4a","modelId":"gpt-5.6-terra","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":17.4285714285714,"warning":null},{"id":"4c1370b3f65b8ad3d1b78deb","modelId":"gpt-5.6-terra","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":2,"warning":null},{"id":"3aaf828ef24beba259257923","modelId":"gpt-5.6-terra","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":27.142857142857103,"warning":null},{"id":"26bd50204ef69387ae04ab34","modelId":"gpt-5.6-terra","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":38.49597135183527,"warning":null},{"id":"b1c1c81c51606d8460545c60","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":20.8,"warning":null},{"id":"ae746b151e814f96138c1d79","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":17.599999999999998,"warning":null},{"id":"32c2e9ca6aae5be333bec8d5","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":24,"warning":null},{"id":"244c6efc802a0039e056a8cd","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":17,"warning":null},{"id":"1370d186b2f7ecf637dbea90","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":24.6,"warning":null},{"id":"24922a66c0b217def3fc86dc","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":1415.36,"warning":null},{"id":"176963c027b7fb0794676ca2","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":1177.99,"warning":null},{"id":"a35d51953f6500b174cac323","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":1476.96,"warning":null},{"id":"e225af0afd77797f02e985af","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":1318.34,"warning":null},{"id":"62790fb3721d24b15758fb54","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":1168.63,"warning":null},{"id":"008864bec446e487e855b794","modelId":"gpt-5.6-terra","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":1478.6,"warning":null},{"id":"314e6e1525729ed3edf53d23","modelId":"gpt-5.6-terra","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":89.5959595959596,"warning":null},{"id":"6a50ebe54c39cf58f5033a93","modelId":"gpt-5.6-terra","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":84.3434343434343,"warning":null},{"id":"b98e3c88455d2dbfb7f82b5b","modelId":"gpt-5.6-terra","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":92.5252525252525,"warning":null},{"id":"2372abd3a60a271d0abd9477","modelId":"gpt-5.6-terra","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":87.1717171717172,"warning":null},{"id":"33c3d386b31ffb1ebcf6d165","modelId":"gpt-5.6-terra","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":74.64646464646461,"warning":null},{"id":"9ec772f0a1718febe4c6d844","modelId":"gpt-5.6-terra","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":90.8080808080808,"warning":null},{"id":"c95672aeee283b5fef342d8d","modelId":"gpt-5.6-terra","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":85.17875235200461,"warning":null},{"id":"5ba4b2be874ab19488769110","modelId":"gpt-5.6-terra","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":38.5078776645042,"warning":null},{"id":"ba683fd42c10375f40797b41","modelId":"gpt-5.6-terra","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":29.1936978683967,"warning":null},{"id":"29a07ed0747163fa9f389e83","modelId":"gpt-5.6-terra","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":42.9101019462465,"warning":null},{"id":"aee60a93dc8fe876e4049c53","modelId":"gpt-5.6-terra","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":33.271547729379094,"warning":null},{"id":"38cef7b62412ad7e99c933fd","modelId":"gpt-5.6-terra","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":11.3994439295644,"warning":null},{"id":"6d0247f50e656831ea9aabde","modelId":"gpt-5.6-terra","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":41.8906394810009,"warning":null},{"id":"5ed56a539484a5f73e9ff3f8","modelId":"gpt-5.6-terra","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":64.421768707483,"warning":null},{"id":"b9f8a6ced8874b25dffbcb42","modelId":"gpt-5.6-terra","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":59.659863945578195,"warning":null},{"id":"91476fa189b93b0776f1bdf4","modelId":"gpt-5.6-terra","benchmarkId":"aa-ifbench","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":71.2244897959184,"warning":null},{"id":"42fb3a4f851acfa22744a55d","modelId":"gpt-5.6-terra","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":62.176870748299294,"warning":null},{"id":"ce1052f4ad2d977687334955","modelId":"gpt-5.6-terra","benchmarkId":"aa-ifbench","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":66.2585034013605,"warning":null},{"id":"63378eab3084fec4da7ca85e","modelId":"gpt-5.6-terra","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":51.035781544256096,"warning":null},{"id":"91cd264955f778eb91b1e72e","modelId":"gpt-5.6-terra","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":12.2222222222222,"warning":null},{"id":"b51f8fa2004ba1eb88914187","modelId":"gpt-5.6-terra","benchmarkId":"aa-mlcr-aa","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":8.888888888888891,"warning":null},{"id":"b9c26ca9b33d9a30127d7187","modelId":"gpt-5.6-terra","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":31.6666666666667,"warning":null},{"id":"e3bee327932a8a0599e6b585","modelId":"gpt-5.6-terra","benchmarkId":"aa-mlcr-aa","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":12.2222222222222,"warning":null},{"id":"c51b0c5bea9242071dea9961","modelId":"gpt-5.6-terra","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":21.6666666666667,"warning":null},{"id":"9680f81c64b5caa7a869f5c0","modelId":"gpt-5.6-terra","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":79.0751445086705,"warning":null},{"id":"c5524ea51493c56e06fba4eb","modelId":"gpt-5.6-terra","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":76.1271676300578,"warning":null},{"id":"6b2e849d7082de02f0431086","modelId":"gpt-5.6-terra","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":80.6936416184971,"warning":null},{"id":"5581c0c0fe2eec4cc56afc3d","modelId":"gpt-5.6-terra","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":76.7630057803468,"warning":null},{"id":"ea99a5d3d1870424b5f5826f","modelId":"gpt-5.6-terra","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":66.7052023121387,"warning":null},{"id":"2e5114e5e94150ac97017ef7","modelId":"gpt-5.6-terra","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":79.47976878612721,"warning":null},{"id":"9e70e59a6c4a148a62a6807b","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":-3.46666666666667,"warning":null},{"id":"db529af327cadbebe82b4ea7","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":-6.83333333333333,"warning":null},{"id":"64b892a9ca7a6bbcc0c53e7e","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":0.05,"warning":null},{"id":"42f39e504fc7276c2c18798c","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":-5.13333333333333,"warning":null},{"id":"acb6eaf0788afbef68320415","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":-23.2166666666667,"warning":null},{"id":"ec4c04a5ed6eda9a62523050","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":-2.98333333333333,"warning":null},{"id":"c158bb5391dfbc5e2a3fed8e","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":45.483333333333334,"warning":null},{"id":"4df55542bb4bc82e99db4ef7","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":43.733333333333334,"warning":null},{"id":"18975919769d79c2f7aabe27","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":46.800000000000004,"warning":null},{"id":"756d177bada59c09b067ba79","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":44.6,"warning":null},{"id":"0cf0c4cefc218ea3fcfed10b","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":36.81666666666666,"warning":null},{"id":"22b78f1948d47dc36cd93ab4","modelId":"gpt-5.6-terra","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":45.516666666666666,"warning":null},{"id":"3a51313008ff68cd29a5f767","modelId":"gpt-5.6-terra","benchmarkId":"aa-scicode","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":52.4305555555556,"warning":null},{"id":"1fe3c0b12b2dfb5a6fb8eff3","modelId":"gpt-5.6-terra","benchmarkId":"aa-scicode","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":49.8842592592593,"warning":null},{"id":"9b0554906366f0cc341dab75","modelId":"gpt-5.6-terra","benchmarkId":"aa-scicode","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":54.976851851851805,"warning":null},{"id":"63c5560222549737f2e0e88c","modelId":"gpt-5.6-terra","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":50.462962962963,"warning":null},{"id":"8de910ba2d29fa18f668fbe2","modelId":"gpt-5.6-terra","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":52.3148148148148,"warning":null},{"id":"2fa4671d195156dd4be0fadf","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":78.3625730994152,"warning":null},{"id":"62279a52d639f31937928cea","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":60.52631578947369,"warning":null},{"id":"073ceaaed64a3cb558696e32","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau2-bench","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":86.2573099415205,"warning":null},{"id":"d3cf6f26849ddc64f37fdd32","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":72.8070175438596,"warning":null},{"id":"0d920f106407fcc40c28ca6a","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau2-bench","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":80.4093567251462,"warning":null},{"id":"9c541bd9c7c101116ab98982","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":28.659793814432998,"warning":null},{"id":"504d18053fe74d158c33aa73","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":18.7628865979381,"warning":null},{"id":"22920056114cab28593ad293","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":40.2061855670103,"warning":null},{"id":"d2128cf2168abe6660486280","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":25.5670103092783,"warning":null},{"id":"cc2e0c6125fc70488c1fc96a","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":15.6701030927835,"warning":null},{"id":"d7a2f490d85a68b29c409a12","modelId":"gpt-5.6-terra","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":29.6907216494845,"warning":null},{"id":"bea096f36c115182b9981251","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":57.5757575757576,"warning":null},{"id":"98b78d65faff3684e0d83b45","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":43.9393939393939,"warning":null},{"id":"06d278dbab87f1de97c29cec","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-hard","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":57.5757575757576,"warning":null},{"id":"e46a92f2078a80f376c15d27","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-hard","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":62.878787878787904,"warning":null},{"id":"f62d1c0f70617c2ce6f41103","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":75.6554307116105,"warning":null},{"id":"de4c360a76fcf8f1e9238e88","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":62.546816479400704,"warning":null},{"id":"8fe60085a81d28d43dd1087f","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":88.0149812734082,"warning":null},{"id":"5d90f3d960aa67c0446b46ce","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":72.2846441947566,"warning":null},{"id":"3ec836beaabc8142f018c103","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"GPT-5.6 Terra (Non-reasoning)","configuration":"GPT-5.6 Terra (Non-reasoning); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning","score":56.1797752808989,"warning":null},{"id":"0582a202960b97fa05e18a5f","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":80.1498127340824,"warning":null},{"id":"73ef0228f016101a421c4e50","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"GPT-5.6 Terra (high); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-high","score":1.51515151515152,"warning":null},{"id":"7be981f3349a9a949db3cd3c","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"GPT-5.6 Terra (low); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-low","score":1.51515151515152,"warning":null},{"id":"ac862758f3c982bc745691e3","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"GPT-5.6 Terra (max); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra","score":35.3535353535354,"warning":null},{"id":"0bbae9a1b4d67b1fa44fd55d","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"GPT-5.6 Terra (medium); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-medium","score":1.01010101010101,"warning":null},{"id":"027112d02ce9fab19994b1da","modelId":"gpt-5.6-terra","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"GPT-5.6 Terra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh","score":10.1010101010101,"warning":null},{"id":"a3ab01caf6d0687478a0ce49","modelId":"gpt-5.6-terra","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-5.6 Terra (High)","configuration":"GPT-5.6 Terra (High); Source model ID: openai-gpt-5-6-terra-high; 120 tasks","score":67.08,"warning":null},{"id":"b818dce06c0fb558e7d7167a","modelId":"gpt-5.6-terra","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-5.6 Terra (Low)","configuration":"GPT-5.6 Terra (Low); Source model ID: openai-gpt-5-6-terra-low; 120 tasks","score":18.75,"warning":null},{"id":"853bc246193f33df5eea54f8","modelId":"gpt-5.6-terra","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"GPT-5.6 Terra (Max)","configuration":"GPT-5.6 Terra (Max); Source model ID: openai-gpt-5-6-terra-max; 120 tasks","score":83.89999999999999,"warning":null},{"id":"0a8c913b486b6fffe98e5acb","modelId":"gpt-5.6-terra","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-5.6 Terra (Medium)","configuration":"GPT-5.6 Terra (Medium); Source model ID: openai-gpt-5-6-terra-medium; 120 tasks","score":37.5,"warning":null},{"id":"e4620c3a04edefbb34c222e8","modelId":"gpt-5.6-terra","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-5.6 Terra (XHigh)","configuration":"GPT-5.6 Terra (XHigh); Source model ID: openai-gpt-5-6-terra-xhigh; 120 tasks","score":74.17,"warning":null},{"id":"d998a419297ba93aa26c6ef6","modelId":"gpt-5.6-terra","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gpt-5-6-terra","configuration":"gpt-5-6-terra; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":53.8,"warning":null},{"id":"b2a027bcbbe350e83bb9379f","modelId":"gpt-5.6-terra","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"gpt-5-6-terra","configuration":"gpt-5-6-terra; Reported effort: low; 113 unique tasks; 449 attempts; 4 runs","score":24.1,"warning":null},{"id":"8af3e2d0812a9e3c0e993ce1","modelId":"gpt-5.6-terra","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"gpt-5-6-terra","configuration":"gpt-5-6-terra; Reported effort: max; 113 unique tasks; 451 attempts; 4 runs","score":69.6,"warning":null},{"id":"5b1b840c7e90fab89305a587","modelId":"gpt-5.6-terra","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"gpt-5-6-terra","configuration":"gpt-5-6-terra; Reported effort: medium; 113 unique tasks; 450 attempts; 4 runs","score":35.1,"warning":null},{"id":"2ca3b5887af025e030617db6","modelId":"gpt-5.6-terra","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"gpt-5-6-terra","configuration":"gpt-5-6-terra; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs","score":60.2,"warning":null},{"id":"e0e6da3e67b23e17eb3133aa","modelId":"gpt-5.6-terra","benchmarkId":"terminal-codex","level":"max","sourceLabel":"GPT-5.6 Terra","configuration":"GPT-5.6 Terra; Reported effort: max; 445 trials; recorded 2026-06-26","score":78.43,"warning":null},{"id":"db85413fe9209e2b0de5cf0d","modelId":"gpt-6-astra","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":51.24999999999999,"warning":null},{"id":"755a966fab65185fe86a6a3f","modelId":"gpt-6-astra","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":1493.87,"warning":null},{"id":"b3ece1ff77463962fde604f4","modelId":"gpt-6-astra","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":1253.1,"warning":null},{"id":"ad79ebd59f8f5d834f4842cc","modelId":"gpt-6-astra","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":1562.01,"warning":null},{"id":"c7b1fe48660acc637ac33074","modelId":"gpt-6-astra","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":1450.6,"warning":null},{"id":"aaff5027a5f7e208e6c185c3","modelId":"gpt-6-astra","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":1533.73,"warning":null},{"id":"c740aea5a9c9e66b074bf005","modelId":"gpt-6-astra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":80,"warning":null},{"id":"59c29e213b13058e1d392cad","modelId":"gpt-6-astra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":80,"warning":null},{"id":"31a8d7d0aa0db25528ac2b90","modelId":"gpt-6-astra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":80.6666666666667,"warning":null},{"id":"ef56f4ff0a4a4be8bfdf8ba1","modelId":"gpt-6-astra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":79.6666666666667,"warning":null},{"id":"bc7508dbb3bdcdb821d33dc3","modelId":"gpt-6-astra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":80,"warning":null},{"id":"2590ff6ad112a045406a0318","modelId":"gpt-6-astra","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":66.6122174975011,"warning":null},{"id":"d3a1a5f0185c6dc703f03e14","modelId":"gpt-6-astra","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":59.09672610445402,"warning":null},{"id":"41f6a229e3c6ba9c944807c9","modelId":"gpt-6-astra","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":68.49174806688876,"warning":null},{"id":"9556c116d9ba6cd9674311a2","modelId":"gpt-6-astra","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":64.59498850561177,"warning":null},{"id":"19b6f84e00cca14dab4e4fca","modelId":"gpt-6-astra","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":67.17778020215393,"warning":null},{"id":"949137762feb62cabd539e6e","modelId":"gpt-6-astra","benchmarkId":"aa-critpt","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":28.857142857142897,"warning":null},{"id":"230415b4ae666279d98496a1","modelId":"gpt-6-astra","benchmarkId":"aa-critpt","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":26.285714285714302,"warning":null},{"id":"92bb39ae21e69a4c49047131","modelId":"gpt-6-astra","benchmarkId":"aa-critpt","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":31.7142857142857,"warning":null},{"id":"fc9f1bd4a67db549d887eaef","modelId":"gpt-6-astra","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":29.1428571428571,"warning":null},{"id":"61f09bee008d98058c42f4bd","modelId":"gpt-6-astra","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":31.4285714285714,"warning":null},{"id":"78e47a74727f6a0a7b418e1d","modelId":"gpt-6-astra","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":31,"warning":null},{"id":"df752fdca1226a27fd5c1a2e","modelId":"gpt-6-astra","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":30.4,"warning":null},{"id":"4b29f5b940ffa1a99be3c0d5","modelId":"gpt-6-astra","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":31,"warning":null},{"id":"c424f776c3f2564a289da5fa","modelId":"gpt-6-astra","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":30.4,"warning":null},{"id":"271459a981fa3bee871a0b22","modelId":"gpt-6-astra","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":32.2,"warning":null},{"id":"5ccbfdb9df90f7cc5072208c","modelId":"gpt-6-astra","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":1529.7,"warning":null},{"id":"573a6e35711e9767dd69f9b1","modelId":"gpt-6-astra","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":1419.29,"warning":null},{"id":"9c33190449930ca4e4225fc5","modelId":"gpt-6-astra","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":1580.2,"warning":null},{"id":"80eb32120b91725a61382370","modelId":"gpt-6-astra","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":1500.67,"warning":null},{"id":"fae24ca39aeba9192224ce1b","modelId":"gpt-6-astra","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":1555.23,"warning":null},{"id":"402d36c960ead254290f0768","modelId":"gpt-6-astra","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":94.94949494949499,"warning":null},{"id":"e610fdd88c714cb30d3da16a","modelId":"gpt-6-astra","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":93.13131313131309,"warning":null},{"id":"e0ab245e5ac013b082e6631c","modelId":"gpt-6-astra","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":96.0606060606061,"warning":null},{"id":"509266bfc25d269b8b5a31f6","modelId":"gpt-6-astra","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":93.9393939393939,"warning":null},{"id":"248d5b9d9353a7711dd6b98a","modelId":"gpt-6-astra","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":96.2626262626263,"warning":null},{"id":"179197f8c2324342b4bee44f","modelId":"gpt-6-astra","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":53.058387395736794,"warning":null},{"id":"80e9c426918b7f08c57c829f","modelId":"gpt-6-astra","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":49.2122335495829,"warning":null},{"id":"c22d718b307d5bf6ed04a7cc","modelId":"gpt-6-astra","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":54.6802594995366,"warning":null},{"id":"4f7d3bf6b13392365eae0d7f","modelId":"gpt-6-astra","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":52.73401297497679,"warning":null},{"id":"82b3ff8257025e7f86fad034","modelId":"gpt-6-astra","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":54.587581093605195,"warning":null},{"id":"16384903800f91c29ce6cec4","modelId":"gpt-6-astra","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":35,"warning":null},{"id":"47a30e262a004b8e8fa788cd","modelId":"gpt-6-astra","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":86.4161849710983,"warning":null},{"id":"3df17843bd35fea92a10f84d","modelId":"gpt-6-astra","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":84.6242774566474,"warning":null},{"id":"f8ad3d59cda0b382e1b99b4c","modelId":"gpt-6-astra","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":86.878612716763,"warning":null},{"id":"f55dd30444f88d31ff3696c4","modelId":"gpt-6-astra","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":85.08670520231209,"warning":null},{"id":"92aa0a7d9adc26688902769b","modelId":"gpt-6-astra","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":86.242774566474,"warning":null},{"id":"7f3b750498047bc39d9bfb71","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":43.7333333333333,"warning":null},{"id":"dfb7acba10dca5fc82abe032","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":40.55,"warning":null},{"id":"d30acb40bb5196501ac2761d","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":43.4,"warning":null},{"id":"3642c13a42011ffb84ffeb73","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":42.2166666666667,"warning":null},{"id":"100886d649a4b50d59ef79b2","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":43.4166666666667,"warning":null},{"id":"04a342a30a8f1280e4a629b7","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":61.133333333333326,"warning":null},{"id":"8df8efb4fda9da9b4fb82f8f","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":59.53333333333334,"warning":null},{"id":"6716ef13baf122440d53c71e","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":62.6,"warning":null},{"id":"c1a2e86cc234d929ff53ab07","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":60.56666666666667,"warning":null},{"id":"915654deed8702ab05055898","modelId":"gpt-6-astra","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":61.85000000000001,"warning":null},{"id":"335a849a2fb438ec4bde5168","modelId":"gpt-6-astra","benchmarkId":"aa-scicode","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":55.4398148148148,"warning":null},{"id":"303c651e520abbafb2c40136","modelId":"gpt-6-astra","benchmarkId":"aa-scicode","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":54.050925925925895,"warning":null},{"id":"a5fa66a096a038191288912b","modelId":"gpt-6-astra","benchmarkId":"aa-scicode","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":56.4814814814815,"warning":null},{"id":"19deff1c8e90e34d79f61ba5","modelId":"gpt-6-astra","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":54.1666666666667,"warning":null},{"id":"a2593f0183e54fb2f104a565","modelId":"gpt-6-astra","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":55.671296296296305,"warning":null},{"id":"c0777683eb17c6897536a177","modelId":"gpt-6-astra","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":40,"warning":null},{"id":"408d3f3efd0b6cf374a543c1","modelId":"gpt-6-astra","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":31.958762886597903,"warning":null},{"id":"ffe7d8651a092d9145619e25","modelId":"gpt-6-astra","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":41.4432989690722,"warning":null},{"id":"136c5da4e66b0acedfec718c","modelId":"gpt-6-astra","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":35.4639175257732,"warning":null},{"id":"359ea8551779850d884aa1cc","modelId":"gpt-6-astra","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":43.0927835051546,"warning":null},{"id":"a66add5ac66c7147bb42a309","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":89.8876404494382,"warning":null},{"id":"ce32ece08b025d45757eca86","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":88.0149812734082,"warning":null},{"id":"e53011a45e167017437eb4c7","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":88.38951310861421,"warning":null},{"id":"bf3b4f7295e1a5a836532224","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":89.5131086142322,"warning":null},{"id":"784760cd062750b782d324c7","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":89.1385767790262,"warning":null},{"id":"fee066836b00e916e060c936","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"GPT-6 Astra (high); Model source: https://artificialanalysis.ai/models/gpt-6-astra-high","score":54.040404040404,"warning":null},{"id":"126131a8129e9a9ab4523922","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"GPT-6 Astra (low); Model source: https://artificialanalysis.ai/models/gpt-6-astra-low","score":41.9191919191919,"warning":null},{"id":"fc2e317c662765899635e709","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"GPT-6 Astra (max); Model source: https://artificialanalysis.ai/models/gpt-6-astra","score":59.09090909090911,"warning":null},{"id":"8e08cbd0435533452bc89eae","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"GPT-6 Astra (medium); Model source: https://artificialanalysis.ai/models/gpt-6-astra-medium","score":49.494949494949495,"warning":null},{"id":"fea2051b45d1aeaab254e09e","modelId":"gpt-6-astra","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"GPT-6 Astra (xhigh); Model source: https://artificialanalysis.ai/models/gpt-6-astra-xhigh","score":59.5959595959596,"warning":null},{"id":"0c5432a88a6429cd53ba80de","modelId":"gpt-6-astra","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"GPT-6 Astra (High)","configuration":"GPT-6 Astra (High); Source model ID: openai-gpt-6-astra-high; 120 tasks","score":92.08333333333333,"warning":null},{"id":"aff9b666a1cca3b3ee07c2ea","modelId":"gpt-6-astra","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"GPT-6 Astra (Low)","configuration":"GPT-6 Astra (Low); Source model ID: openai-gpt-6-astra-low; 120 tasks","score":85.41666666666666,"warning":null},{"id":"34add3a000b32e26d7ba251e","modelId":"gpt-6-astra","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"GPT-6 Astra (Max)","configuration":"GPT-6 Astra (Max); Source model ID: openai-gpt-6-astra-max; 120 tasks","score":95,"warning":null},{"id":"6f7f64f65d746e4beebd2d85","modelId":"gpt-6-astra","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"GPT-6 Astra (Medium)","configuration":"GPT-6 Astra (Medium); Source model ID: openai-gpt-6-astra-medium; 120 tasks","score":92.08333333333333,"warning":null},{"id":"b5faeccd54fcda2954357a39","modelId":"gpt-6-astra","benchmarkId":"arc-v2semiprivate","level":"none","sourceLabel":"GPT-6 Astra (None)","configuration":"GPT-6 Astra (None); Source model ID: openai-gpt-6-astra-none; 120 tasks","score":59.583333333333336,"warning":"Source-reported label. OpenAI documents Low through Max for Astra; this does not establish a supported non-reasoning API setting."},{"id":"8a7b9cc900bc1e48522b2d77","modelId":"gpt-6-astra","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"GPT-6 Astra (XHigh)","configuration":"GPT-6 Astra (XHigh); Source model ID: openai-gpt-6-astra-xhigh; 120 tasks","score":93.33333333333333,"warning":null},{"id":"192a0a52134befbac5912c90","modelId":"gpt-6-astra","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"gpt-6-astra","configuration":"gpt-6-astra; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":73.2,"warning":null},{"id":"eb733075f994115168315353","modelId":"gpt-6-astra","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"gpt-6-astra","configuration":"gpt-6-astra; Reported effort: low; 113 unique tasks; 452 attempts; 4 runs","score":67,"warning":null},{"id":"fa893735776a86c9eaeeab33","modelId":"gpt-6-astra","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"gpt-6-astra","configuration":"gpt-6-astra; Reported effort: max; 113 unique tasks; 452 attempts; 4 runs","score":73.2,"warning":null},{"id":"eba425fa2243963df9b630e9","modelId":"gpt-6-astra","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"gpt-6-astra","configuration":"gpt-6-astra; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs","score":72.8,"warning":null},{"id":"49b1b70f581245c54e071b3a","modelId":"gpt-6-astra","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"gpt-6-astra","configuration":"gpt-6-astra; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs","score":74.1,"warning":null},{"id":"434544966d1431c1926d52f5","modelId":"gpt-6-astra","benchmarkId":"terminal-codex","level":"high","sourceLabel":"GPT-6 Astra","configuration":"GPT-6 Astra; Reported effort: high; 445 trials; recorded 2026-09-03","score":87.42,"warning":null},{"id":"91bc2d06c970323599005b34","modelId":"gpt-6-astra","benchmarkId":"terminal-codex","level":"low","sourceLabel":"GPT-6 Astra","configuration":"GPT-6 Astra; Reported effort: low; 445 trials; recorded 2026-09-03","score":86.74,"warning":null},{"id":"bf597f8d4309561326a1ef1f","modelId":"gpt-6-astra","benchmarkId":"terminal-codex","level":"max","sourceLabel":"GPT-6 Astra","configuration":"GPT-6 Astra; Reported effort: max; 445 trials; recorded 2026-09-03","score":86.74,"warning":null},{"id":"bb6111da7a05efb610da52fd","modelId":"gpt-6-astra","benchmarkId":"terminal-codex","level":"medium","sourceLabel":"GPT-6 Astra","configuration":"GPT-6 Astra; Reported effort: medium; 445 trials; recorded 2026-09-03","score":86.97,"warning":null},{"id":"cefb2b8c7589ea007cb6a16b","modelId":"gpt-6-astra","benchmarkId":"terminal-codex","level":"xhigh","sourceLabel":"GPT-6 Astra","configuration":"GPT-6 Astra; Reported effort: xhigh; 445 trials; recorded 2026-09-03","score":85.84,"warning":null},{"id":"523b22474bb4399c00f66fd1","modelId":"gpt-oss-120b","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":0,"warning":null},{"id":"abc6e0a169207f03d4d5a0e0","modelId":"gpt-oss-120b","benchmarkId":"aa-aime-2025","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":93.4416666666667,"warning":null},{"id":"8bbc2727f91077b7a22629e2","modelId":"gpt-oss-120b","benchmarkId":"aa-aime-2025","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":66.6666666666667,"warning":null},{"id":"c503933cc53434f0f92b70fc","modelId":"gpt-oss-120b","benchmarkId":"aa-apex-agents-aa","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":3.09734513274336,"warning":null},{"id":"cc1909dc186f18f73c79311e","modelId":"gpt-oss-120b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":52,"warning":null},{"id":"f405bf6233adc95f10658e3f","modelId":"gpt-oss-120b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":46,"warning":null},{"id":"a8ef371ad6fa26792fdbb7f7","modelId":"gpt-oss-120b","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":0.19906990691605594,"warning":null},{"id":"638d7bb3d20aa239038426e8","modelId":"gpt-oss-120b","benchmarkId":"aa-critpt","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":1.1428571428571401,"warning":null},{"id":"eee8c8b605f6997383cbf15e","modelId":"gpt-oss-120b","benchmarkId":"aa-critpt","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":0,"warning":null},{"id":"c40749ff405aba50340cf7a5","modelId":"gpt-oss-120b","benchmarkId":"aa-enterprise-ops-gym-aa","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":25.544613548194565,"warning":null},{"id":"d6a5a2e3ccea877bb2e6db69","modelId":"gpt-oss-120b","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":4,"warning":null},{"id":"a0db19adeacb4445ff814565","modelId":"gpt-oss-120b","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":744.74,"warning":null},{"id":"ee9bd53ac94dfb155f2ea271","modelId":"gpt-oss-120b","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":364.46,"warning":null},{"id":"46bb1061dbb6bfc2f6366ec8","modelId":"gpt-oss-120b","benchmarkId":"aa-global-mmlu-lite","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":82.78125,"warning":null},{"id":"e2651230274052f15b2b3443","modelId":"gpt-oss-120b","benchmarkId":"aa-global-mmlu-lite","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":80.11979166666667,"warning":null},{"id":"7d9de7a169cb83d5e01f7d9f","modelId":"gpt-oss-120b","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":78.1818181818182,"warning":null},{"id":"4dc3723aa579693808cf38f3","modelId":"gpt-oss-120b","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":67.1717171717172,"warning":null},{"id":"5cd6972861ad2dde662f2af8","modelId":"gpt-oss-120b","benchmarkId":"aa-harvey-lab-aa","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":13.894919669995701,"warning":null},{"id":"3341e10e726c8da7b0533867","modelId":"gpt-oss-120b","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":19.6014828544949,"warning":null},{"id":"1f51a3ab140cd5bdf49e8f14","modelId":"gpt-oss-120b","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":5.88507877664504,"warning":null},{"id":"976efab9e73a5b78a9019c7f","modelId":"gpt-oss-120b","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":68.9795918367347,"warning":null},{"id":"adbdcb278184f49397014445","modelId":"gpt-oss-120b","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":58.299319727891195,"warning":null},{"id":"684fb34dba74fd14674a23ec","modelId":"gpt-oss-120b","benchmarkId":"aa-itbench-aa","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":5.649717514124291,"warning":null},{"id":"c084a484b6c8acb146dff42c","modelId":"gpt-oss-120b","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":87.83068783068781,"warning":null},{"id":"9beceb876fccbef7fa802cf7","modelId":"gpt-oss-120b","benchmarkId":"aa-livecodebench","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":70.6878306878307,"warning":null},{"id":"39a6ef4212d041bf06cf764a","modelId":"gpt-oss-120b","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":1.1111111111111098,"warning":null},{"id":"1ba3e86b77e24cff96aeaefb","modelId":"gpt-oss-120b","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":80.79288563829789,"warning":null},{"id":"d6e6c7c03102d2ec5db38d6c","modelId":"gpt-oss-120b","benchmarkId":"aa-mmlu-pro","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":77.47672872340429,"warning":null},{"id":"b31454600a41bac85df8781b","modelId":"gpt-oss-120b","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":-49.25,"warning":null},{"id":"44174058a335a21db34cab7b","modelId":"gpt-oss-120b","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":-53.5,"warning":null},{"id":"0d55b9a126f4a041bcfbb598","modelId":"gpt-oss-120b","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":21.78333333333333,"warning":null},{"id":"dcb24bbb729fd83366ab2bd9","modelId":"gpt-oss-120b","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":19.8,"warning":null},{"id":"01007d88982bbfbb8f529d6f","modelId":"gpt-oss-120b","benchmarkId":"aa-scicode","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":34.0277777777778,"warning":null},{"id":"22231d4d7245b35d3625e3af","modelId":"gpt-oss-120b","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":65.78947368421049,"warning":null},{"id":"612939f9cf2e8c6074b59550","modelId":"gpt-oss-120b","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":45.0292397660819,"warning":null},{"id":"6c4911fd6570f2e07fce07e2","modelId":"gpt-oss-120b","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":12.7835051546392,"warning":null},{"id":"2e655923c9219b67e8a6c1fd","modelId":"gpt-oss-120b","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":2.88659793814433,"warning":null},{"id":"71def977bbcfeb57928495a1","modelId":"gpt-oss-120b","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":23.4848484848485,"warning":null},{"id":"5158abda3c8444a4add0a606","modelId":"gpt-oss-120b","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":5.3030303030303,"warning":null},{"id":"06bbe372969d1260d126de3b","modelId":"gpt-oss-120b","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":26.217228464419502,"warning":null},{"id":"29df99841d606c663c6cba2e","modelId":"gpt-oss-120b","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"gpt-oss-120b (low)","configuration":"gpt-oss-120b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-120b-low","score":13.8576779026217,"warning":null},{"id":"324cbf4c56dbcbc2366d864f","modelId":"gpt-oss-120b","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"gpt-oss-120b (high)","configuration":"gpt-oss-120b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-120b","score":0,"warning":null},{"id":"261cd80255a8f86b29cdc64a","modelId":"gpt-oss-20b","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":0,"warning":null},{"id":"d7ad936a08ee7062350a5949","modelId":"gpt-oss-20b","benchmarkId":"aa-aime-2025","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":89.3333333333333,"warning":null},{"id":"6d25466d9f8bafec004c6e0d","modelId":"gpt-oss-20b","benchmarkId":"aa-aime-2025","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":62.33333333333329,"warning":null},{"id":"a209082ec9bbfa072a58c650","modelId":"gpt-oss-20b","benchmarkId":"aa-apex-agents-aa","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":0.737463126843658,"warning":null},{"id":"af73940d617970fd2fef15bb","modelId":"gpt-oss-20b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":34.6666666666667,"warning":null},{"id":"f8a6e40363d5090f2ad2c7ad","modelId":"gpt-oss-20b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":31,"warning":null},{"id":"cb045928e30dab4357c9599b","modelId":"gpt-oss-20b","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":0.19111706206154658,"warning":null},{"id":"210db506787c6ac19c05794d","modelId":"gpt-oss-20b","benchmarkId":"aa-critpt","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":1.42857142857143,"warning":null},{"id":"bba46d32848e2eef7785b44e","modelId":"gpt-oss-20b","benchmarkId":"aa-critpt","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":0,"warning":null},{"id":"95200cf35a926a4f51ee2775","modelId":"gpt-oss-20b","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":2,"warning":null},{"id":"d2579297fa894b9c2d833764","modelId":"gpt-oss-20b","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":513.93,"warning":null},{"id":"0e6e6e66316d32dd747eba8d","modelId":"gpt-oss-20b","benchmarkId":"aa-global-mmlu-lite","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":75.16145833333333,"warning":null},{"id":"a55d1fa7a6a7c2c5d6953114","modelId":"gpt-oss-20b","benchmarkId":"aa-global-mmlu-lite","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":72.84895833333334,"warning":null},{"id":"d279df6be2703d37479fab78","modelId":"gpt-oss-20b","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":68.7878787878788,"warning":null},{"id":"564986d48d63eaff6ee3a969","modelId":"gpt-oss-20b","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":61.11111111111111,"warning":null},{"id":"9785f3bb2637f59ea5b99c98","modelId":"gpt-oss-20b","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":10.982391102873,"warning":null},{"id":"ca818e3ea19482d3b2454dee","modelId":"gpt-oss-20b","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":5.28266913809083,"warning":null},{"id":"b8b53cc40fd8751a180074b7","modelId":"gpt-oss-20b","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":65.10204081632651,"warning":null},{"id":"7f4fc1b4c1ead78822aa1179","modelId":"gpt-oss-20b","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":57.8231292517007,"warning":null},{"id":"ff8288575593b36e49c877d6","modelId":"gpt-oss-20b","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":77.6719576719577,"warning":null},{"id":"2fcf9d977ea9bcd472708bf9","modelId":"gpt-oss-20b","benchmarkId":"aa-livecodebench","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":65.1851851851852,"warning":null},{"id":"0e0d3cbcdd797311812457e0","modelId":"gpt-oss-20b","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":0.555555555555556,"warning":null},{"id":"a200d1455a5a357504736341","modelId":"gpt-oss-20b","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":74.7672872340426,"warning":null},{"id":"c79b6f15d83991a7ab03c12b","modelId":"gpt-oss-20b","benchmarkId":"aa-mmlu-pro","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":71.8001994680851,"warning":null},{"id":"1127c1a85f619737a188828f","modelId":"gpt-oss-20b","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":-63.05,"warning":null},{"id":"783912f707a26b3b11a91fbc","modelId":"gpt-oss-20b","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":-58.55,"warning":null},{"id":"3bc57c6b44aed57e184220ea","modelId":"gpt-oss-20b","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":16,"warning":null},{"id":"277feeeee0e2bd32670548ad","modelId":"gpt-oss-20b","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":15.083333333333334,"warning":null},{"id":"3068709e4fa6d80249ddda10","modelId":"gpt-oss-20b","benchmarkId":"aa-scicode","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":38.8888888888889,"warning":null},{"id":"4dc0ffd2a175311df4e9b5a2","modelId":"gpt-oss-20b","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":60.23391812865499,"warning":null},{"id":"bae854c8ba6955a5ed0dd327","modelId":"gpt-oss-20b","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":50.2923976608187,"warning":null},{"id":"53d5a25e09a84b9518b95531","modelId":"gpt-oss-20b","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":7.01030927835052,"warning":null},{"id":"050e2e0ea6629b5c9f1cd8d1","modelId":"gpt-oss-20b","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":10.6060606060606,"warning":null},{"id":"26c8fa378df6e0c862ab999c","modelId":"gpt-oss-20b","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"gpt-oss-20b (low)","configuration":"gpt-oss-20b (low); Model source: https://artificialanalysis.ai/models/gpt-oss-20b-low","score":4.545454545454549,"warning":null},{"id":"0f152f80e228c99fb11dff1d","modelId":"gpt-oss-20b","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":13.8576779026217,"warning":null},{"id":"ac1b2b3889ae72ee551cc306","modelId":"gpt-oss-20b","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"gpt-oss-20b (high)","configuration":"gpt-oss-20b (high); Model source: https://artificialanalysis.ai/models/gpt-oss-20b","score":0,"warning":null},{"id":"3e148f07e65bd83da8552afc","modelId":"grok-4.3","benchmarkId":"aa-aa-analyst-agent","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":8.75,"warning":null},{"id":"7a28e521275a8117ae5ab73c","modelId":"grok-4.3","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":761.59,"warning":null},{"id":"332cd4432559a24c1067763a","modelId":"grok-4.3","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":724.4,"warning":null},{"id":"ab02bbad93d66a73317ac504","modelId":"grok-4.3","benchmarkId":"aa-apex-agents-aa","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":17.0353982300885,"warning":null},{"id":"3dd4ab978ed9081e7d2256b1","modelId":"grok-4.3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":73,"warning":null},{"id":"036d3a1334196c80a57915e1","modelId":"grok-4.3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":74,"warning":null},{"id":"1326a222541d5fa16aa3d69f","modelId":"grok-4.3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":75,"warning":null},{"id":"a8c5adb6e6a04bb44455088a","modelId":"grok-4.3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":32.3333333333333,"warning":null},{"id":"33d428149eacb23f8023a22f","modelId":"grok-4.3","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":1.375964614032744,"warning":null},{"id":"90dc9f391ef590950102f348","modelId":"grok-4.3","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":0.9304541594200506,"warning":null},{"id":"f551e9f045bc0b6ac729b202","modelId":"grok-4.3","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":8,"warning":null},{"id":"281d1eb368851122cc17db8f","modelId":"grok-4.3","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":0.571428571428571,"warning":null},{"id":"b2f7b3ce100e19c3b23c1e5b","modelId":"grok-4.3","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":4.857142857142859,"warning":null},{"id":"a58cdd26382eb8561a3891c9","modelId":"grok-4.3","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":0,"warning":null},{"id":"aa53133f053c6453c3b57345","modelId":"grok-4.3","benchmarkId":"aa-enterprise-ops-gym-aa","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":26.260817666368247,"warning":null},{"id":"f896ff4dbb8782a2ad6cd1ef","modelId":"grok-4.3","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":5.800000000000001,"warning":null},{"id":"76697b005c207eca60a37292","modelId":"grok-4.3","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":2.8000000000000003,"warning":null},{"id":"b9a055af1a46fc2841cb4811","modelId":"grok-4.3","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":1018.49,"warning":null},{"id":"7193993644401ada0c561b94","modelId":"grok-4.3","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":1030.8,"warning":null},{"id":"ac16b72863ef9ad38f76746f","modelId":"grok-4.3","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":90.1010101010101,"warning":null},{"id":"31d0696779501c33756e0d41","modelId":"grok-4.3","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":84.3434343434343,"warning":null},{"id":"7551c8c0295e481116b6da40","modelId":"grok-4.3","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":88.98989898989899,"warning":null},{"id":"87938cd53777003184b7326c","modelId":"grok-4.3","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":65.75757575757581,"warning":null},{"id":"2a7ea11c3b23006d2057ffc6","modelId":"grok-4.3","benchmarkId":"aa-harvey-lab-aa","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":68.38905775075989,"warning":null},{"id":"e22732096c5a7cb5e49a22c6","modelId":"grok-4.3","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":37.2103799814643,"warning":null},{"id":"864db222a3748d2576b04d3b","modelId":"grok-4.3","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":18.3503243744208,"warning":null},{"id":"68527a9aa6a80fe2b6b57d58","modelId":"grok-4.3","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":29.9814643188137,"warning":null},{"id":"48b6077c8917596c2ef7209d","modelId":"grok-4.3","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":6.76552363299351,"warning":null},{"id":"39e2717926fbad74a11cd28a","modelId":"grok-4.3","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":81.2925170068027,"warning":null},{"id":"87998076f09f0d9f3a6d9164","modelId":"grok-4.3","benchmarkId":"aa-ifbench","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":80.95238095238099,"warning":null},{"id":"120cd61fa038594ff09377ed","modelId":"grok-4.3","benchmarkId":"aa-ifbench","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":83.3333333333333,"warning":null},{"id":"d6a4bb91832505b0b6e788fd","modelId":"grok-4.3","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":47.6190476190476,"warning":null},{"id":"324617d001eff6640ca1330e","modelId":"grok-4.3","benchmarkId":"aa-itbench-aa","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":32.7212806026365,"warning":null},{"id":"c8c6fa9ba872894ea7ce1c90","modelId":"grok-4.3","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":10,"warning":null},{"id":"0348ca9a6bde4aa27112f9d8","modelId":"grok-4.3","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":78.09248554913299,"warning":null},{"id":"d16467e883bd502ba32d9e0a","modelId":"grok-4.3","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":72.7745664739884,"warning":null},{"id":"ce4626bb5d5d94abcaddd1b0","modelId":"grok-4.3","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":75.8381502890173,"warning":null},{"id":"f6729a1bc7854706665ff871","modelId":"grok-4.3","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":64.7976878612717,"warning":null},{"id":"b15b56bf252797d3b5d91e95","modelId":"grok-4.3","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":17.9833333333333,"warning":null},{"id":"326e7b3889e629aeda2d9b20","modelId":"grok-4.3","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":13.9333333333333,"warning":null},{"id":"abd3c444a2f68677d8e6225b","modelId":"grok-4.3","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":16.7,"warning":null},{"id":"723887484db7ec3fbb615c5c","modelId":"grok-4.3","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":-33.0833333333333,"warning":null},{"id":"a3190a3f384ca2ebc31bb6d7","modelId":"grok-4.3","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":34.78333333333333,"warning":null},{"id":"3b73b3714dde60636c917020","modelId":"grok-4.3","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":26.68333333333333,"warning":null},{"id":"82d2a580c6f40ae99a27fa94","modelId":"grok-4.3","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":28.76666666666667,"warning":null},{"id":"ff80f12b5df368a65cf2f2b9","modelId":"grok-4.3","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":23.716666666666665,"warning":null},{"id":"02504f35bcbb21ae0c5af2ac","modelId":"grok-4.3","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":48.2638888888889,"warning":null},{"id":"0561533dc2911a9c3050e1f3","modelId":"grok-4.3","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":39.3518518518519,"warning":null},{"id":"7221252780a4b1647f643270","modelId":"grok-4.3","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":97.6608187134503,"warning":null},{"id":"3240e8dff8e99f1feec0b685","modelId":"grok-4.3","benchmarkId":"aa-tau2-bench","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":88.8888888888889,"warning":null},{"id":"c7a445e9105703a4a9140142","modelId":"grok-4.3","benchmarkId":"aa-tau2-bench","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":91.2280701754386,"warning":null},{"id":"1676bd960d1324c582d1bb4e","modelId":"grok-4.3","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":65.78947368421049,"warning":null},{"id":"234fdc59aa263bb853ba0c5b","modelId":"grok-4.3","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":12.3711340206186,"warning":null},{"id":"bb11904c98e84a986b9588e1","modelId":"grok-4.3","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":8.04123711340206,"warning":null},{"id":"afd8125af880999aea9ef239","modelId":"grok-4.3","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":37.878787878787904,"warning":null},{"id":"17cbb7437ff01131c310bc9f","modelId":"grok-4.3","benchmarkId":"aa-terminalbench-hard","level":"low","sourceLabel":"Grok 4.3 (low)","configuration":"Grok 4.3 (low); Model source: https://artificialanalysis.ai/models/grok-4-3-low","score":26.5151515151515,"warning":null},{"id":"69351a9c04f817687a4d844e","modelId":"grok-4.3","benchmarkId":"aa-terminalbench-hard","level":"medium","sourceLabel":"Grok 4.3 (medium)","configuration":"Grok 4.3 (medium); Model source: https://artificialanalysis.ai/models/grok-4-3-medium","score":30.303030303030297,"warning":null},{"id":"a316a3c001d815220879252c","modelId":"grok-4.3","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":18.939393939393902,"warning":null},{"id":"e3dea1bc0f28e76fd71c35fd","modelId":"grok-4.3","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":39.700374531835195,"warning":null},{"id":"4f472a30aeb8eaf66deeba1b","modelId":"grok-4.3","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":34.0823970037453,"warning":null},{"id":"a57b0612082bbbf111f35e20","modelId":"grok-4.3","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"Grok 4.3 (high); Model source: https://artificialanalysis.ai/models/grok-4-3","score":0,"warning":null},{"id":"35daaac2931883507e622ad1","modelId":"grok-4.3","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Grok 4.3 (Non-reasoning)","configuration":"Grok 4.3 (Non-reasoning); Model source: https://artificialanalysis.ai/models/grok-4-3-non-reasoning","score":0,"warning":null},{"id":"e04b4c1584c40ead300a6494","modelId":"grok-4.5","benchmarkId":"aa-aa-analyst-agent","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":35,"warning":null},{"id":"54926ad11c502455b00573fe","modelId":"grok-4.5","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":1283.38,"warning":null},{"id":"3fb681f994810c739344b77f","modelId":"grok-4.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":79.3333333333333,"warning":null},{"id":"fa8a12feceedbdedf24b72f3","modelId":"grok-4.5","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":57.93486035084273,"warning":null},{"id":"5f6cab432b7af151e56d72c7","modelId":"grok-4.5","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":15.4285714285714,"warning":null},{"id":"927091b6f30b8898774d9b75","modelId":"grok-4.5","benchmarkId":"aa-enterprise-ops-gym-aa","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":40.82363473589973,"warning":null},{"id":"74d938a06c551969af7cf629","modelId":"grok-4.5","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":18.8,"warning":null},{"id":"8c4189a8314621ca519523e6","modelId":"grok-4.5","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":1429.6,"warning":null},{"id":"cce6b0003a75b934b5ce797d","modelId":"grok-4.5","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":93.13131313131309,"warning":null},{"id":"26e57c4171d8af90ff7c9d8b","modelId":"grok-4.5","benchmarkId":"aa-harvey-lab-aa","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":92.4156896801274,"warning":null},{"id":"dfc2d18c6b5c05d46a2fc38b","modelId":"grok-4.5","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":42.678405931418,"warning":null},{"id":"2b62bae9938cc7ca82751c8a","modelId":"grok-4.5","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":15,"warning":null},{"id":"0d148747c6b768836b3329d1","modelId":"grok-4.5","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":80.4046242774566,"warning":null},{"id":"49ddf105c76cb6c65c9788e6","modelId":"grok-4.5","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":25.3166666666667,"warning":null},{"id":"d472e7944026d02ff693dcbe","modelId":"grok-4.5","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":51.55,"warning":null},{"id":"8b158e8057762eda00e49b8a","modelId":"grok-4.5","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":54.976851851851805,"warning":null},{"id":"91458be076d7e97fd168922a","modelId":"grok-4.5","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":42.0618556701031,"warning":null},{"id":"377fe99391f8f823331313ae","modelId":"grok-4.5","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":81.6479400749064,"warning":null},{"id":"0212dd4561acee977e00400d","modelId":"grok-4.5","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5 (high); Model source: https://artificialanalysis.ai/models/grok-4-5","score":10.6060606060606,"warning":null},{"id":"3db181a4b2c903d1c6f5ca32","modelId":"grok-4.5","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Grok 4.5 (High)","configuration":"Grok 4.5 (High); Source model ID: xai-grok-4-5-high; 120 tasks","score":52.64,"warning":null},{"id":"6b3763ee781610c75ebd4561","modelId":"grok-4.5","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Grok 4.5 (Low)","configuration":"Grok 4.5 (Low); Source model ID: xai-grok-4-5-low; 120 tasks","score":33.06,"warning":null},{"id":"f3dd688412c9fb5675915351","modelId":"grok-4.5","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Grok 4.5 (Medium)","configuration":"Grok 4.5 (Medium); Source model ID: xai-grok-4-5-medium; 120 tasks","score":52.64,"warning":null},{"id":"29895fdf00c54de0c01daedb","modelId":"grok-4.5","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"grok-4-5","configuration":"grok-4-5; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs","score":53.8,"warning":null},{"id":"43896251f67c4560c987eefb","modelId":"grok-4.5","benchmarkId":"terminal-cursorcli","level":"high","sourceLabel":"Grok 4.5","configuration":"Grok 4.5; Reported effort: high; 445 trials; recorded 2026-07-08","score":79.33,"warning":null},{"id":"3c5dd3212c5738aaab0975c9","modelId":"grok-4.6","benchmarkId":"aa-aa-analyst-agent","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":41.25,"warning":null},{"id":"0e717a8621ac7d5e7b83f0c5","modelId":"grok-4.6","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":1534.13,"warning":null},{"id":"d4ded8c8cf842220025c972d","modelId":"grok-4.6","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":1293.13,"warning":null},{"id":"8ee72461e2fd4c2d3a3b9148","modelId":"grok-4.6","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":1490.6,"warning":null},{"id":"7fc29bf0ad8e603f80d34abe","modelId":"grok-4.6","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":1545.11,"warning":null},{"id":"403fbffb3d4c130fe0a9f700","modelId":"grok-4.6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":80.3333333333333,"warning":null},{"id":"e734f89143af4a8c68b167ab","modelId":"grok-4.6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":80.6666666666667,"warning":null},{"id":"a5c886cc36cd42ce59e53418","modelId":"grok-4.6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":81,"warning":null},{"id":"ae37b0844362fac304b68324","modelId":"grok-4.6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":81,"warning":null},{"id":"45f91d7a9b1de993e85a20ce","modelId":"grok-4.6","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":66.67849638121398,"warning":null},{"id":"054c3ab32b6b51e1cacb8e66","modelId":"grok-4.6","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":53.44540059031701,"warning":null},{"id":"f104d2d68e7f44b6e2dccf41","modelId":"grok-4.6","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":63.151269753678996,"warning":null},{"id":"0999469725cecb5b4c543921","modelId":"grok-4.6","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":66.99736836183247,"warning":null},{"id":"45ba7bd68a9e01e37c632257","modelId":"grok-4.6","benchmarkId":"aa-critpt","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":17.1428571428571,"warning":null},{"id":"c73b3845403c26be37e56d16","modelId":"grok-4.6","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":5.71428571428571,"warning":null},{"id":"660f538129047bbe99b9ec11","modelId":"grok-4.6","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":17.714285714285698,"warning":null},{"id":"37e9c27bbdff0ce8078ce069","modelId":"grok-4.6","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":19.7142857142857,"warning":null},{"id":"b1293bc7579eca6bbdab6135","modelId":"grok-4.6","benchmarkId":"aa-enterprise-ops-gym-aa","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":48.343777976723366,"warning":null},{"id":"2a7e2415031e29ef507c8a42","modelId":"grok-4.6","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":17,"warning":null},{"id":"ddf1393612c433158b1f573c","modelId":"grok-4.6","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":15.8,"warning":null},{"id":"f40e905d9f3955576665619b","modelId":"grok-4.6","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":17.8,"warning":null},{"id":"57df6c8e4db31d53d9c4f418","modelId":"grok-4.6","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":17.2,"warning":null},{"id":"efd5e16b51c0ef83d3a54291","modelId":"grok-4.6","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":1642.96,"warning":null},{"id":"5b0518cbb5edec145ab97b52","modelId":"grok-4.6","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":1461.3,"warning":null},{"id":"c3cea65021791dd8aedd62f2","modelId":"grok-4.6","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":1642.56,"warning":null},{"id":"6e5c4070f5e96c65a869fe26","modelId":"grok-4.6","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":1663.07,"warning":null},{"id":"ba76728c38b2f86ca1efc6ad","modelId":"grok-4.6","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":94.94949494949499,"warning":null},{"id":"0c7395dffb6b3896502c73d5","modelId":"grok-4.6","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":87.8787878787879,"warning":null},{"id":"52618fd8fe81fb1041c98953","modelId":"grok-4.6","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":93.53535353535351,"warning":null},{"id":"2d7228aef62f24943be9fa82","modelId":"grok-4.6","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":93.53535353535351,"warning":null},{"id":"477c12bc73aea349f49ef6a6","modelId":"grok-4.6","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":42.9101019462465,"warning":null},{"id":"e12185f9bee54b45c735edf2","modelId":"grok-4.6","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":27.6181649675626,"warning":null},{"id":"e1b87ca46f07d08e805d4eb4","modelId":"grok-4.6","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":42.122335495829496,"warning":null},{"id":"f4b86fdbf8e6fb1c74530ac5","modelId":"grok-4.6","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":44.0685820203893,"warning":null},{"id":"23325239d62a3b8f2f30a348","modelId":"grok-4.6","benchmarkId":"aa-mlcr-aa","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":12.2222222222222,"warning":null},{"id":"bf44cf9030f95307456d203b","modelId":"grok-4.6","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":30.4833333333333,"warning":null},{"id":"8286b65e9f1a497934f4c1a7","modelId":"grok-4.6","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":25.9,"warning":null},{"id":"b887a18f999764706e64138e","modelId":"grok-4.6","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":28,"warning":null},{"id":"2542d8a122e2175ba2a75e90","modelId":"grok-4.6","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":29.3166666666667,"warning":null},{"id":"019b5793b4933474b0e3bd08","modelId":"grok-4.6","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":48.233333333333334,"warning":null},{"id":"b2a59f42331436a81f65fe0e","modelId":"grok-4.6","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":43.28333333333333,"warning":null},{"id":"d21aded68f27a80ed79d5087","modelId":"grok-4.6","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":41.93333333333334,"warning":null},{"id":"01bb8807c7ea19d4b16cc08c","modelId":"grok-4.6","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":43,"warning":null},{"id":"ba5cc0dfeff8c957916898ac","modelId":"grok-4.6","benchmarkId":"aa-scicode","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":56.4814814814815,"warning":null},{"id":"e22a72d808c23e07638f47bf","modelId":"grok-4.6","benchmarkId":"aa-scicode","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":49.421296296296305,"warning":null},{"id":"6ef88b16c55a462f1fbcff3d","modelId":"grok-4.6","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":55.9027777777778,"warning":null},{"id":"3ed711611c036fede0642751","modelId":"grok-4.6","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":53.0092592592593,"warning":null},{"id":"11ed8dc8a72cb1dd225c2d68","modelId":"grok-4.6","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":50.7216494845361,"warning":null},{"id":"1070933d65fc7da9c420831c","modelId":"grok-4.6","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":38.144329896907195,"warning":null},{"id":"7fd9cc7f1f85cfa6226325da","modelId":"grok-4.6","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":44.3298969072165,"warning":null},{"id":"47f25590e81572edc7ae836e","modelId":"grok-4.6","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":43.298969072165,"warning":null},{"id":"d11a73033247919db8e39a28","modelId":"grok-4.6","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":88.38951310861421,"warning":null},{"id":"f359942d0696f4ca296786b6","modelId":"grok-4.6","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":75.2808988764045,"warning":null},{"id":"0f9713ed90ebd9bd4534f929","modelId":"grok-4.6","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":84.2696629213483,"warning":null},{"id":"146b01e3d6b3dd74cf939381","modelId":"grok-4.6","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":88.0149812734082,"warning":null},{"id":"67fb1e447bf3a84a1dc5dfca","modelId":"grok-4.6","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Grok 4.6 (high); Model source: https://artificialanalysis.ai/models/grok-4-6","score":21.2121212121212,"warning":null},{"id":"3fc718ffaea1ef6d8907d374","modelId":"grok-4.6","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"Grok 4.6 (low); Model source: https://artificialanalysis.ai/models/grok-4-6-low","score":3.03030303030303,"warning":null},{"id":"73835b49fe42ab80ec539285","modelId":"grok-4.6","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"Grok 4.6 (medium); Model source: https://artificialanalysis.ai/models/grok-4-6-medium","score":13.1313131313131,"warning":null},{"id":"57abb41c70329a99f77535b3","modelId":"grok-4.6","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"Grok 4.6 (xhigh); Model source: https://artificialanalysis.ai/models/grok-4-6-xhigh","score":17.171717171717198,"warning":null},{"id":"f494121ba1b32eb13d788d7e","modelId":"grok-4.6","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Grok 4.6 (High)","configuration":"Grok 4.6 (High); Source model ID: xai-grok-4-6-high; 120 tasks","score":65.13888888888889,"warning":null},{"id":"c80d116c611cdfdbf0794a0e","modelId":"grok-4.6","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Grok 4.6 (Low)","configuration":"Grok 4.6 (Low); Source model ID: xai-grok-4-6-low; 120 tasks","score":27.63888888888889,"warning":null},{"id":"9cc5971c94263e7ed3b6e5aa","modelId":"grok-4.6","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"Grok 4.6 (Medium)","configuration":"Grok 4.6 (Medium); Source model ID: xai-grok-4-6-medium; 120 tasks","score":61.25000000000001,"warning":null},{"id":"055e2840581f27e7013445b1","modelId":"grok-4.6","benchmarkId":"arc-v2semiprivate","level":"xhigh","sourceLabel":"Grok 4.6 (XHigh)","configuration":"Grok 4.6 (XHigh); Source model ID: xai-grok-4-6-xhigh; 120 tasks","score":67.08333333333333,"warning":null},{"id":"3d4862ebd4d7563b0b815232","modelId":"grok-4.6","benchmarkId":"deepswe-minisweagent","level":"high","sourceLabel":"grok-4-6","configuration":"grok-4-6; Reported effort: high; 113 unique tasks; 451 attempts; 4 runs","score":65.2,"warning":null},{"id":"83e82d34b74f64e32fe5e562","modelId":"grok-4.6","benchmarkId":"deepswe-minisweagent","level":"low","sourceLabel":"grok-4-6","configuration":"grok-4-6; Reported effort: low; 113 unique tasks; 449 attempts; 4 runs","score":41.6,"warning":null},{"id":"dee4caacc80397f92e821c17","modelId":"grok-4.6","benchmarkId":"deepswe-minisweagent","level":"medium","sourceLabel":"grok-4-6","configuration":"grok-4-6; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs","score":67.5,"warning":null},{"id":"bc046d614155011b4f32fd77","modelId":"grok-4.6","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"grok-4-6","configuration":"grok-4-6; Reported effort: xhigh; 113 unique tasks; 451 attempts; 4 runs","score":66.7,"warning":null},{"id":"4b52e57716284a426b20e616","modelId":"hy3","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":949.65,"warning":null},{"id":"dbe2f8f3df27510117453b6d","modelId":"hy3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":79,"warning":null},{"id":"725cf8be083eeea3761a0746","modelId":"hy3","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.409128371172397,"warning":null},{"id":"ed230f269f79598168400161","modelId":"hy3","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.857142857142859,"warning":null},{"id":"875ff8bc105e8938ba3ab493","modelId":"hy3","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.200000000000001,"warning":null},{"id":"6d88716d3f6022775ca0349b","modelId":"hy3","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":1135.96,"warning":null},{"id":"c62d7142b2955f3cccde331b","modelId":"hy3","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":89.6969696969697,"warning":null},{"id":"a7a35fd1ba65fa084a53bfff","modelId":"hy3","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.4569045412419,"warning":null},{"id":"4e3737c70846342ba1f20656","modelId":"hy3","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":-18.4666666666667,"warning":null},{"id":"02867ce545a79d28fdca774c","modelId":"hy3","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.966666666666665,"warning":null},{"id":"05c2f7fcf387f4cfcc374ac1","modelId":"hy3","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.6111111111111,"warning":null},{"id":"42aa341468210b376e09693e","modelId":"hy3","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.886597938144302,"warning":null},{"id":"c802eac5e2f5b0cc14a4b3d2","modelId":"hy3","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":64.4194756554307,"warning":null},{"id":"e9c96fd0e4307f0a3d58c1b2","modelId":"hy3","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Hy3","configuration":"Hy3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/hy3; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.505050505050505,"warning":null},{"id":"ef559fa4c43c26694bf787aa","modelId":"hy3-preview","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":42,"warning":null},{"id":"c68b83e1d7b894a93142c739","modelId":"hy3-preview","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":64.6666666666667,"warning":null},{"id":"0b9583430639861c86d85e2f","modelId":"hy3-preview","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":0.28571428571428603,"warning":null},{"id":"81a106f485bd6b878caf732e","modelId":"hy3-preview","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":4.57142857142857,"warning":null},{"id":"8105b1407e966b7ace150043","modelId":"hy3-preview","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":73.23232323232321,"warning":null},{"id":"c5b5e8eb7d2c919e6919413b","modelId":"hy3-preview","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":86.6666666666667,"warning":null},{"id":"ede59fb652037041ce1a1dd1","modelId":"hy3-preview","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":6.95088044485635,"warning":null},{"id":"fa0d7ae753fb74157d138e17","modelId":"hy3-preview","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":27.757182576459698,"warning":null},{"id":"5a9e1184bb651c83cf370ab6","modelId":"hy3-preview","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":47.959183673469404,"warning":null},{"id":"96069ed2be775a9053422ed9","modelId":"hy3-preview","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":63.1292517006803,"warning":null},{"id":"5c695ae8e66e691e9c8f92ad","modelId":"hy3-preview","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":-34.95,"warning":null},{"id":"79511ae819bfc612c35a390d","modelId":"hy3-preview","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":-35.05,"warning":null},{"id":"e6e605672e21f6d859de5904","modelId":"hy3-preview","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":23.183333333333334,"warning":null},{"id":"3b0fcbd11b64f27c16e87a8d","modelId":"hy3-preview","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":27.933333333333334,"warning":null},{"id":"0695f8b0b910244d05c7a925","modelId":"hy3-preview","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":67.5438596491228,"warning":null},{"id":"9773ef1b60a79df50df32edc","modelId":"hy3-preview","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":92.6900584795322,"warning":null},{"id":"a3c4359e7b3ebe3d66db5807","modelId":"hy3-preview","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Hy3-preview (Non-reasoning)","configuration":"Hy3-preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/hy3-non-reasoning","score":31.818181818181802,"warning":null},{"id":"04ca7fd5e9a8ca87409e10ef","modelId":"hy3-preview","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Hy3-preview (Reasoning)","configuration":"Hy3-preview (Reasoning); Model source: https://artificialanalysis.ai/models/hy3-preview","score":34.0909090909091,"warning":null},{"id":"f87910c78684cc62168b7cb2","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":60,"warning":null},{"id":"9f51ff08dab94ee68cc8a89f","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.857142857142857,"warning":null},{"id":"f8804c0a4c3c7156385284ed","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":918,"warning":null},{"id":"bf662cb6aa3124cc7b4764b8","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.9292929292929,"warning":null},{"id":"e33f42d3c44882cd56cbcd32","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.5820203892493,"warning":null},{"id":"ce73d0e7d12c5a142ddb9708","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":-6.6,"warning":null},{"id":"f4734c61a8de64e23bbc6f36","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.05,"warning":null},{"id":"cfeb7e15ec86982ebaa1def8","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.0138888888889,"warning":null},{"id":"de7217aed61d8cea3b16e724","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.5463917525773,"warning":null},{"id":"a3e0b62512d545bc3197e0e9","modelId":"k-exaone-2.0-750b-a37b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"K-EXAONE 2.0","configuration":"K-EXAONE 2.0; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/k-exaone-2-0-0803; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.4494382022472,"warning":null},{"id":"940370aaedaeafccbaa815dd","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":44,"warning":null},{"id":"248628f25209685f2e813405","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":90.3333333333334,"warning":null},{"id":"4f07384d9d52a7fe91a6f574","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":53.3333333333333,"warning":null},{"id":"3d7800bef3152ab150d04958","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":61.33333333333329,"warning":null},{"id":"368e01788a286f45ff312089","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":0,"warning":null},{"id":"f6d4cdc6f942e0cd40356df3","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":1.11836734693878,"warning":null},{"id":"811654dc8dea47a5dd74e14b","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":539.71,"warning":null},{"id":"e9b96f3441cf2f7569161137","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":71.03125,"warning":null},{"id":"bcb923d99217ff28ee7af856","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":78.86458333333334,"warning":null},{"id":"2c65d6e1561964eea7a2e608","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":69.4949494949495,"warning":null},{"id":"0437fefd7ee49ace79820857","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":78.2828282828283,"warning":null},{"id":"02cc8dd32ee8e6e63cc2728b","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":5.69972196478221,"warning":null},{"id":"d32f54031e59460e2a5ab5da","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":13.9481000926784,"warning":null},{"id":"5835712a4022a343643485e3","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":39.5918367346939,"warning":null},{"id":"be6b8730183dc85bad1c7223","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":64.69387755102039,"warning":null},{"id":"856a3db006f6d9daa745ceac","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":76.8253968253968,"warning":null},{"id":"27271f132873252b7a8add85","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":80.9757313829787,"warning":null},{"id":"0c644501691c892c4d6e6628","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":83.7516622340426,"warning":null},{"id":"8e4b9809a8173b24a6492b4c","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":-65.4,"warning":null},{"id":"577a7a49fdb90fe94610bce7","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":-57.9666666666667,"warning":null},{"id":"b5681c2b592c28e60853de1c","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":13.65,"warning":null},{"id":"2812d3d5ae36f9f251dd27e7","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":16.35,"warning":null},{"id":"8cc243a5909dbf9cbbc8d10a","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":59.0643274853801,"warning":null},{"id":"1a47670629cd21ee68944b7f","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":74.2690058479532,"warning":null},{"id":"30dab2414c4fc919a207dfd0","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"K-EXAONE (Non-reasoning)","configuration":"K-EXAONE (Non-reasoning); Model source: https://artificialanalysis.ai/models/k-exaone-non-reasoning","score":6.81818181818182,"warning":null},{"id":"7a942a894babe14e3d6e64da","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":22.727272727272698,"warning":null},{"id":"5c4b5d8b71c63b017f4596ad","modelId":"k-exaone-236b-a23b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"K-EXAONE (Reasoning)","configuration":"K-EXAONE (Reasoning); Model source: https://artificialanalysis.ai/models/k-exaone","score":30.337078651685403,"warning":null},{"id":"04280450484769a36816bece","modelId":"kimi-k2.6","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":819.92,"warning":null},{"id":"a3064ad7c61c665ff2687f71","modelId":"kimi-k2.6","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.4660766961652,"warning":null},{"id":"9a44dc9f59be8bdd5015a312","modelId":"kimi-k2.6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":69.6666666666667,"warning":null},{"id":"ade312ab0cd2fdc7519d21ca","modelId":"kimi-k2.6","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":81,"warning":null},{"id":"8700ad2ebedb691ad92507ec","modelId":"kimi-k2.6","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.020759856386269,"warning":null},{"id":"8b5dee6f02a84bcfc1521def","modelId":"kimi-k2.6","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":1.42857142857143,"warning":null},{"id":"9194db1885dee526b2ac310a","modelId":"kimi-k2.6","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":8,"warning":null},{"id":"b58e12618e0788c63c62fc22","modelId":"kimi-k2.6","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.525813190092514,"warning":null},{"id":"39447a939e047b385f5d24fa","modelId":"kimi-k2.6","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":13,"warning":null},{"id":"6382bf13bada1216c5053be6","modelId":"kimi-k2.6","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":1115.31,"warning":null},{"id":"8dc00c97fd0d8d4c30d4d3ae","modelId":"kimi-k2.6","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":78.7878787878788,"warning":null},{"id":"dad907f2acd631a78725d840","modelId":"kimi-k2.6","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":91.1111111111111,"warning":null},{"id":"e4629bc4793dd88337221ab1","modelId":"kimi-k2.6","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.1221595020987,"warning":null},{"id":"f8fef2fbfef8abe8215008b5","modelId":"kimi-k2.6","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":19.5551436515292,"warning":null},{"id":"6e9c2097dfe8dc3f5066f5c8","modelId":"kimi-k2.6","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.488415199258604,"warning":null},{"id":"072e7d1bc0df4bb01a626b04","modelId":"kimi-k2.6","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":44.2857142857143,"warning":null},{"id":"fc4c747bf5bef726f47aab98","modelId":"kimi-k2.6","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.9863945578231,"warning":null},{"id":"b11893babf6d0cd6554405b3","modelId":"kimi-k2.6","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.186440677966097,"warning":null},{"id":"b4cfd2aed78613e240f41314","modelId":"kimi-k2.6","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.364161849711,"warning":null},{"id":"ca4100db60d1e0bc35d98c00","modelId":"kimi-k2.6","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":-9.18333333333333,"warning":null},{"id":"3f8fd7e249ce407ffe388a4c","modelId":"kimi-k2.6","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.3,"warning":null},{"id":"e12c88668886777dfadf2dc1","modelId":"kimi-k2.6","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":24.3,"warning":null},{"id":"38692f4ee2f974347e9157bc","modelId":"kimi-k2.6","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.6,"warning":null},{"id":"6dd5d4875b8e76f1b1d8dc49","modelId":"kimi-k2.6","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.5046296296296,"warning":null},{"id":"828fe25b5f302f66f6fc6566","modelId":"kimi-k2.6","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":93.859649122807,"warning":null},{"id":"0d20434e4ad0abf951e6622b","modelId":"kimi-k2.6","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":95.906432748538,"warning":null},{"id":"e2457c88eb0a7fc7b83a3971","modelId":"kimi-k2.6","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.298969072164898,"warning":null},{"id":"7e2e74eb92490b361bfd99bf","modelId":"kimi-k2.6","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Kimi K2.6 (Non-reasoning)","configuration":"Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning","score":37.878787878787904,"warning":null},{"id":"7194781f9e8031ffdea93f56","modelId":"kimi-k2.6","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.9393939393939,"warning":null},{"id":"6584a32b8687b95ca2090b9c","modelId":"kimi-k2.6","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Kimi K2.6","configuration":"Kimi K2.6; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified","score":65.9176029962547,"warning":null},{"id":"c67358f7711396086508ed59","modelId":"kimi-k2.7-code","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":855.7,"warning":null},{"id":"88387229e8cce0c4b453061b","modelId":"kimi-k2.7-code","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.3333333333333,"warning":null},{"id":"ab60dcdf1b0dfcfeb47110b6","modelId":"kimi-k2.7-code","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.454304615216714,"warning":null},{"id":"4f813371d1d4f13c92b30639","modelId":"kimi-k2.7-code","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":10,"warning":null},{"id":"83fe42da8f302edfdb023f08","modelId":"kimi-k2.7-code","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.226797970754994,"warning":null},{"id":"5f4cc4e8c65e4c951ef26ba1","modelId":"kimi-k2.7-code","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.200000000000001,"warning":null},{"id":"515915c2fb3373acf9c6b635","modelId":"kimi-k2.7-code","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":1114.49,"warning":null},{"id":"3e669e225a585809c8dd4fc9","modelId":"kimi-k2.7-code","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":89.5959595959596,"warning":null},{"id":"2c5d34ebc7fc4b2f2c90ddfb","modelId":"kimi-k2.7-code","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":85.0195397307859,"warning":null},{"id":"5a1a5b9db2d6520bd2afa2e7","modelId":"kimi-k2.7-code","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.032437442075995,"warning":null},{"id":"057764867b81c8cbddb8e80c","modelId":"kimi-k2.7-code","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.1292517006803,"warning":null},{"id":"88eae31082764b6f63a7a0fd","modelId":"kimi-k2.7-code","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.1111111111111,"warning":null},{"id":"b0a4a7295832157df8e2a492","modelId":"kimi-k2.7-code","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":-10.2166666666667,"warning":null},{"id":"1f6e336dd0093408d3178e8c","modelId":"kimi-k2.7-code","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.56666666666667,"warning":null},{"id":"fda338029ff27052839f5dbc","modelId":"kimi-k2.7-code","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.8009259259259,"warning":null},{"id":"27d83ba961ef5fc71e6a27ca","modelId":"kimi-k2.7-code","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":90.0584795321637,"warning":null},{"id":"fe217e24de0bc7151b14e323","modelId":"kimi-k2.7-code","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.2061855670103,"warning":null},{"id":"c29648182b4f7975f2c9f0aa","modelId":"kimi-k2.7-code","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.6969696969697,"warning":null},{"id":"472f377c83d4e3dbb7ca25a7","modelId":"kimi-k2.7-code","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.4157303370786,"warning":null},{"id":"40ef2cb1ea3f3e136a7e3b3d","modelId":"kimi-k2.7-code","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Kimi K2.7 Code","configuration":"Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.01010101010101,"warning":null},{"id":"4d676b05a6bfdafc218ee928","modelId":"kimi-k3","benchmarkId":"aa-aa-analyst-agent","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":38.75,"warning":null},{"id":"7a767ce340fca6b1554b4c3f","modelId":"kimi-k3","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":984.78,"warning":null},{"id":"65086c25f5faf83ca3f34bf1","modelId":"kimi-k3","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":1492.58,"warning":null},{"id":"00cd93b578a9e9a08358156b","modelId":"kimi-k3","benchmarkId":"aa-apex-agents-aa","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":41.2979351032448,"warning":null},{"id":"e2ffd875fe769b7e1cd9e9a4","modelId":"kimi-k3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":79.3333333333333,"warning":null},{"id":"c02cbafde90ba09e5f80c872","modelId":"kimi-k3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":88.6666666666667,"warning":null},{"id":"2083991a4b33b7b3436d8b59","modelId":"kimi-k3","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":49.2568024921068,"warning":null},{"id":"7669a82ebf437fb83f3e011f","modelId":"kimi-k3","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":58.272977800152034,"warning":null},{"id":"86e5cbe5af3f685cbf639a80","modelId":"kimi-k3","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":3.14285714285714,"warning":null},{"id":"5e94bffff1490839faca1bbf","modelId":"kimi-k3","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":23.4285714285714,"warning":null},{"id":"005275d385d7aa97c24a77f8","modelId":"kimi-k3","benchmarkId":"aa-enterprise-ops-gym-aa","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":45.329752312742464,"warning":null},{"id":"4186413bd41c45c9968ab3db","modelId":"kimi-k3","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":18.6,"warning":null},{"id":"4348a901c8e332d0564e708c","modelId":"kimi-k3","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":22,"warning":null},{"id":"ce8125990f0e0f3ade0a2250","modelId":"kimi-k3","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":1185.27,"warning":null},{"id":"310c9ef33cf85bdcf514e515","modelId":"kimi-k3","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":1569.47,"warning":null},{"id":"eeca09857f52f6fb22f8ffba","modelId":"kimi-k3","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":84.24242424242419,"warning":null},{"id":"8832707a4ee1b6f2ac875d97","modelId":"kimi-k3","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":93.53535353535351,"warning":null},{"id":"1681a5dc3c366fbdbc9d151b","modelId":"kimi-k3","benchmarkId":"aa-harvey-lab-aa","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":94.6446663771892,"warning":null},{"id":"84bd6e70c12d4a66c0e831d6","modelId":"kimi-k3","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":24.976830398517098,"warning":null},{"id":"4da2f0c4bd40c9a5325848b3","modelId":"kimi-k3","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":46.8952734012975,"warning":null},{"id":"c2382bd3b1567d49bc4ff23e","modelId":"kimi-k3","benchmarkId":"aa-itbench-aa","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":47.6930320150659,"warning":null},{"id":"d364b327127f7dd3cf8f19d3","modelId":"kimi-k3","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":38.3333333333333,"warning":null},{"id":"80061346884d74fbb322cff2","modelId":"kimi-k3","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":78.4971098265896,"warning":null},{"id":"2ed0111313e64d4c0400cc37","modelId":"kimi-k3","benchmarkId":"aa-mmmu-pro","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":80.52023121387279,"warning":null},{"id":"2add98bb74de8a6d6249d272","modelId":"kimi-k3","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":3.91666666666667,"warning":null},{"id":"3cfd24aceb01fe71d063a78e","modelId":"kimi-k3","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":19.7,"warning":null},{"id":"4cb267f6327833c9fc9f39e9","modelId":"kimi-k3","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":45.75,"warning":null},{"id":"cdbbafc18468106417fd813f","modelId":"kimi-k3","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":47.583333333333336,"warning":null},{"id":"de943e45f8b7428cb8550a21","modelId":"kimi-k3","benchmarkId":"aa-scicode","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":52.662037037037,"warning":null},{"id":"964db1dd2b9760b2f77a25ef","modelId":"kimi-k3","benchmarkId":"aa-scicode","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":59.4907407407407,"warning":null},{"id":"432c908a73875ef4d65e834e","modelId":"kimi-k3","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":41.6494845360825,"warning":null},{"id":"34300f035fc030273d01a271","modelId":"kimi-k3","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":45.979381443299,"warning":null},{"id":"edc488017c622cc81eaa9f23","modelId":"kimi-k3","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":82.3970037453184,"warning":null},{"id":"8f6edfd82bcc0576eb4a7ed5","modelId":"kimi-k3","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":85.0187265917603,"warning":null},{"id":"79c5c9a708ff0a48425e70cd","modelId":"kimi-k3","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"Kimi K3 (low)","configuration":"Kimi K3 (low); Model source: https://artificialanalysis.ai/models/kimi-k3-low","score":12.6262626262626,"warning":null},{"id":"df4665280a1fd6c8d394111a","modelId":"kimi-k3","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"Kimi K3 (max); Model source: https://artificialanalysis.ai/models/kimi-k3","score":12.6262626262626,"warning":null},{"id":"98a1e7f8c4f539a73b1ff25c","modelId":"kimi-k3","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"Kimi K3 (High)","configuration":"Kimi K3 (High); Source model ID: moonshot-kimi-k3-high; 120 tasks","score":55.00000000000001,"warning":null},{"id":"b4f3231c817b7f55bb013735","modelId":"kimi-k3","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"Kimi K3 (Low)","configuration":"Kimi K3 (Low); Source model ID: moonshot-kimi-k3-low; 120 tasks","score":12.36111111111111,"warning":null},{"id":"e82af3e6f3c2533aff0ab0d7","modelId":"kimi-k3","benchmarkId":"arc-v2semiprivate","level":"max","sourceLabel":"Kimi K3 (Max)","configuration":"Kimi K3 (Max); Source model ID: moonshot-kimi-k3-max; 120 tasks","score":60.416666666666664,"warning":null},{"id":"50e28ce7104ff5613d31fa3a","modelId":"kimi-k3","benchmarkId":"deepswe-minisweagent","level":"max","sourceLabel":"kimi-k3","configuration":"kimi-k3; Reported effort: max; 113 unique tasks; 451 attempts; 4 runs","score":68.5,"warning":null},{"id":"1187d83dfc7e0cf1c3cb0f1f","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.3333333333333,"warning":null},{"id":"a28e1bf360f6451fb459a28c","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.000000000000004,"warning":null},{"id":"fce6dfd0e81f07cb9544ac4d","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.2121212121212,"warning":null},{"id":"6f77d8d40ab545d0bf411f78","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.45597775718258,"warning":null},{"id":"dd3256ca33a1679f4f21fe4e","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.095238095238102,"warning":null},{"id":"c35ede4aac100ec236173460","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.7777777777778,"warning":null},{"id":"73b3ca32c6c854d2f898cfc4","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.502327127659605,"warning":null},{"id":"c774e01e9fd4a377f1ad3499","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"4e7fa6459cf119043d1b3938","modelId":"kimi-linear-48b-a3b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Kimi Linear 48B A3B Instruct","configuration":"Kimi Linear 48B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.363636363636399,"warning":null},{"id":"7131dec20596d2df6c1be3f2","modelId":"labs-devstral-small-2512","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":495.98,"warning":null},{"id":"4f0df62b80b8c9fb83b0a81e","modelId":"labs-devstral-small-2512","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.3333333333333,"warning":null},{"id":"277826d88691ec9eb915047f","modelId":"labs-devstral-small-2512","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.000000000000004,"warning":null},{"id":"f649238deb9d8f1ed9c39912","modelId":"labs-devstral-small-2512","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.0901842411547693,"warning":null},{"id":"9ccc3445c3156458123a9871","modelId":"labs-devstral-small-2512","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"0e7d98632bdb7b424068a7d8","modelId":"labs-devstral-small-2512","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":1,"warning":null},{"id":"148f96724c8bc1918313cee2","modelId":"labs-devstral-small-2512","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":679.88,"warning":null},{"id":"5dd89b6fd04dc8216937a0a5","modelId":"labs-devstral-small-2512","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.21875,"warning":null},{"id":"fdb350e52c16cc800f8fdb1a","modelId":"labs-devstral-small-2512","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":53.232323232323196,"warning":null},{"id":"0eb124052c0750dd77638fa8","modelId":"labs-devstral-small-2512","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.47544022242817,"warning":null},{"id":"5f3a8b308a46b3d8691e4eb2","modelId":"labs-devstral-small-2512","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.156462585034,"warning":null},{"id":"f58575e3393fbefc53600c5f","modelId":"labs-devstral-small-2512","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.814814814814795,"warning":null},{"id":"81f793d6f2f88bd3529fa166","modelId":"labs-devstral-small-2512","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.7775930851064,"warning":null},{"id":"390f00a5572b8173cd2b52e2","modelId":"labs-devstral-small-2512","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.6242774566474,"warning":null},{"id":"2c975ec825cce37abe4db74e","modelId":"labs-devstral-small-2512","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":-57.7,"warning":null},{"id":"589703a977c33adb0239d69f","modelId":"labs-devstral-small-2512","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.8,"warning":null},{"id":"3d79254e334d06a2ca47d4ed","modelId":"labs-devstral-small-2512","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.407407407407405,"warning":null},{"id":"f52fe8389f1bb8f3ded3aa92","modelId":"labs-devstral-small-2512","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.3918128654971,"warning":null},{"id":"6c90b87546d259a25837a5c2","modelId":"labs-devstral-small-2512","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.7216494845361,"warning":null},{"id":"d988ff2eb76e6caf21e5e2a4","modelId":"labs-devstral-small-2512","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.6666666666667,"warning":null},{"id":"f111753b1bee273c77e6e9e0","modelId":"labs-devstral-small-2512","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.588014981273396,"warning":null},{"id":"0dac65a9f62774845dbe0cc7","modelId":"labs-devstral-small-2512","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Devstral Small 2","configuration":"Devstral Small 2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/devstral-small-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"77dc3e409687fdc4123e7382","modelId":"llama-4-maverick","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"faefecf4982a3c56261456c3","modelId":"llama-4-maverick","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.3333333333333,"warning":null},{"id":"31f2f561fab689277fa32daf","modelId":"llama-4-maverick","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":50,"warning":null},{"id":"cdf57f3e51751d8b1b206f3e","modelId":"llama-4-maverick","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.2121918776569101,"warning":null},{"id":"45aff2671367df91ec82a00d","modelId":"llama-4-maverick","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"a1c45db0f194569fedcfab7e","modelId":"llama-4-maverick","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.8,"warning":null},{"id":"8570e13fa3402d4a1cf0ce49","modelId":"llama-4-maverick","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":-44.77,"warning":null},{"id":"48fc8cf05f6cf5be1916a16f","modelId":"llama-4-maverick","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.46354166666667,"warning":null},{"id":"7b3e6d11f2c08cecf4bbdf7b","modelId":"llama-4-maverick","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.0707070707071,"warning":null},{"id":"0faf4ea29ec7471f2ddc2575","modelId":"llama-4-maverick","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.91195551436515,"warning":null},{"id":"0496ddc71cb780c146897871","modelId":"llama-4-maverick","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.9931972789116,"warning":null},{"id":"cc29361336c4897fbe3e986d","modelId":"llama-4-maverick","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.682539682539705,"warning":null},{"id":"39a00cb8aa14d4a8f1630392","modelId":"llama-4-maverick","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.8666666666667,"warning":null},{"id":"83ab2bc25f0bf5b24ca914e2","modelId":"llama-4-maverick","benchmarkId":"aa-mlcr-aa","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.2222222222222197,"warning":null},{"id":"29bc8ec0528066576e43067c","modelId":"llama-4-maverick","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.8510638297872,"warning":null},{"id":"9aa0ba713cbccb8900465da5","modelId":"llama-4-maverick","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":62.1387283236994,"warning":null},{"id":"7eec6f4e726f2ac2843e4d31","modelId":"llama-4-maverick","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":-41.85,"warning":null},{"id":"f6678979dffdce85c6baa1a4","modelId":"llama-4-maverick","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.9,"warning":null},{"id":"6d6139083fe99c0d47d89705","modelId":"llama-4-maverick","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.712962962962997,"warning":null},{"id":"d78fc2575a1485830285d7e8","modelId":"llama-4-maverick","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.8362573099415,"warning":null},{"id":"dac821c6aa9136a83d875bda","modelId":"llama-4-maverick","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.71134020618557,"warning":null},{"id":"604481ef9f14e63577ee5fd8","modelId":"llama-4-maverick","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.81818181818182,"warning":null},{"id":"354eb159671e8738012a81fa","modelId":"llama-4-maverick","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.86516853932584,"warning":null},{"id":"edfcc29c0deb58a191bb162d","modelId":"llama-4-maverick","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Llama 4 Maverick","configuration":"Llama 4 Maverick; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-maverick; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"555d23d461c05d28e5affaad","modelId":"llama-4-scout","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"4885145006b9e6c516d4941f","modelId":"llama-4-scout","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.000000000000002,"warning":null},{"id":"7581f3a2422117f43b197e4b","modelId":"llama-4-scout","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.700000000000003,"warning":null},{"id":"9353269ebd55ac03ed176358","modelId":"llama-4-scout","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.19111706206154658,"warning":null},{"id":"afc01f597c0079772acb9e3f","modelId":"llama-4-scout","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"d524b4da994ccf7a3136f46d","modelId":"llama-4-scout","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"2ca6b818ad3095ba1fec0cf3","modelId":"llama-4-scout","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":59.71,"warning":null},{"id":"66c9c26050db4c0d8d41b4a8","modelId":"llama-4-scout","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.140625,"warning":null},{"id":"37634d64a31c01e3c55ac3eb","modelId":"llama-4-scout","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.6868686868687,"warning":null},{"id":"ab3e6dc6aee996774804be32","modelId":"llama-4-scout","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.7800000000000002,"warning":null},{"id":"9b5c1e36e87698c0a87d0094","modelId":"llama-4-scout","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.5238095238095,"warning":null},{"id":"e7c19c636a0f224e332b9c1e","modelId":"llama-4-scout","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.9470899470899,"warning":null},{"id":"ebf48949184410fed6f20bb0","modelId":"llama-4-scout","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.39999999999999,"warning":null},{"id":"f2341b5314bd44225e9253b3","modelId":"llama-4-scout","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.1745345744681,"warning":null},{"id":"342b5de48406cc12a0d640cc","modelId":"llama-4-scout","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.9479768786127,"warning":null},{"id":"825b3abf9640fc95590a58b5","modelId":"llama-4-scout","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":-52.15,"warning":null},{"id":"29b51ff314d8015f16d8fd73","modelId":"llama-4-scout","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.166666666666668,"warning":null},{"id":"b3e565fe11b60b81a60483f2","modelId":"llama-4-scout","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.296296296296298,"warning":null},{"id":"6ceeb86bffcbd0f7f1c1cb44","modelId":"llama-4-scout","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.4970760233918,"warning":null},{"id":"b7075f4c91bd36c49bbb5930","modelId":"llama-4-scout","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.29896907216495,"warning":null},{"id":"fe0a313c1be6171f1e933267","modelId":"llama-4-scout","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.51515151515152,"warning":null},{"id":"c7b21db2c6c9de33ab88deb3","modelId":"llama-4-scout","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.7453183520599302,"warning":null},{"id":"12f09ed4b289733513c29184","modelId":"llama-4-scout","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Llama 4 Scout","configuration":"Llama 4 Scout; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/llama-4-scout; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"f863116be3067c64dc4ded17","modelId":"magistral-medium-2509","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":82,"warning":null},{"id":"96fb815ee59686aa6570879b","modelId":"magistral-medium-2509","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":53,"warning":null},{"id":"27e70b3fb728057a74df17b6","modelId":"magistral-medium-2509","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"537afc4af13852943398074a","modelId":"magistral-medium-2509","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":361.94,"warning":null},{"id":"dbfb37115a2ce93f137abe06","modelId":"magistral-medium-2509","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.56770833333333,"warning":null},{"id":"0ed549eecac4ede999a12daa","modelId":"magistral-medium-2509","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.93939393939391,"warning":null},{"id":"37b4571eaeb976c6fe763a9d","modelId":"magistral-medium-2509","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.2873030583874,"warning":null},{"id":"482398fa7f264cd6c99cd143","modelId":"magistral-medium-2509","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.9931972789116,"warning":null},{"id":"ad7ae7e1f65c748e13353d8d","modelId":"magistral-medium-2509","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.026455026455,"warning":null},{"id":"00d28563b1af109ad8f1498d","modelId":"magistral-medium-2509","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.50764627659571,"warning":null},{"id":"f2ea0a245a0ae60d6211be17","modelId":"magistral-medium-2509","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":59.6531791907514,"warning":null},{"id":"b059b84e2446c00ab8d4580f","modelId":"magistral-medium-2509","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":-26.7333333333333,"warning":null},{"id":"07fa28163f5b1f3edc355eed","modelId":"magistral-medium-2509","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.783333333333335,"warning":null},{"id":"40f63a5a594c4ddbf8bb6e60","modelId":"magistral-medium-2509","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.046783625730995,"warning":null},{"id":"86a26110045ab8144e18668e","modelId":"magistral-medium-2509","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.56701030927835,"warning":null},{"id":"f2831b29b79d4466446b9ca7","modelId":"magistral-medium-2509","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.8787878787879,"warning":null},{"id":"f9230a89b29d00bd920b1d0e","modelId":"magistral-medium-2509","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Magistral Medium 1.2","configuration":"Magistral Medium 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-medium-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.3595505617978,"warning":null},{"id":"9557a6f4edfe4134aff16297","modelId":"magistral-small-2509","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.3333333333333,"warning":null},{"id":"754e92a07c653f668b9fd678","modelId":"magistral-small-2509","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.3333333333333,"warning":null},{"id":"b75f74d8527b381f95e1cc00","modelId":"magistral-small-2509","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.19111706206154658,"warning":null},{"id":"7f110124805bb3a2e19625a9","modelId":"magistral-small-2509","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"08ab00b7e42c1ffe38fae226","modelId":"magistral-small-2509","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":212.7,"warning":null},{"id":"7332d47df21579cbd347434c","modelId":"magistral-small-2509","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.3125,"warning":null},{"id":"d912f20d1c509a3f0d54f0b2","modelId":"magistral-small-2509","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.2626262626263,"warning":null},{"id":"21bd6e25c91e8aaf59a9c346","modelId":"magistral-small-2509","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.44114921223355,"warning":null},{"id":"fac1628ad38a1ae32b1a569b","modelId":"magistral-small-2509","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.353741496598595,"warning":null},{"id":"42ee1aa5bdd7a63aa6435d27","modelId":"magistral-small-2509","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.27513227513231,"warning":null},{"id":"da019b5f437710abfa392ded","modelId":"magistral-small-2509","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.845079787234,"warning":null},{"id":"6e4257fe0cfd1b51a80412dd","modelId":"magistral-small-2509","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":55.4913294797688,"warning":null},{"id":"f6035266fb17e74a06d13c9a","modelId":"magistral-small-2509","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":-65.1,"warning":null},{"id":"f107c4759c0944a0c47cc731","modelId":"magistral-small-2509","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.450000000000001,"warning":null},{"id":"d21b8957d999afa9c21c52a4","modelId":"magistral-small-2509","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.7777777777778,"warning":null},{"id":"c7a6909b11ed59de7be2f06c","modelId":"magistral-small-2509","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.5360824742267996,"warning":null},{"id":"582e8eaacbf3fc4faf540335","modelId":"magistral-small-2509","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.545454545454549,"warning":null},{"id":"0f4ae3bfcadfaec9cecbf582","modelId":"magistral-small-2509","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Magistral Small 1.2","configuration":"Magistral Small 1.2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/magistral-small-2509; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.49438202247191,"warning":null},{"id":"0548c4d5205cb671c0f67853","modelId":"mimo-v2-flash","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":67.6666666666667,"warning":null},{"id":"18f2737a5c5e1f7f70b602b1","modelId":"mimo-v2-flash","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":96.3333333333333,"warning":null},{"id":"d0737a6dbd590e665e154bd5","modelId":"mimo-v2-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":36.3333333333333,"warning":null},{"id":"18761c742f092bb12f9d5589","modelId":"mimo-v2-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":70.6666666666667,"warning":null},{"id":"2c6d86385f0499ac90db9b10","modelId":"mimo-v2-flash","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":0,"warning":null},{"id":"b30d2768f6110084619ea391","modelId":"mimo-v2-flash","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":4.28571428571429,"warning":null},{"id":"e4a73d3fd6138fe1e3815707","modelId":"mimo-v2-flash","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":788.18,"warning":null},{"id":"0429ec3293c63221653ac24b","modelId":"mimo-v2-flash","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":62.635416666666664,"warning":null},{"id":"bf092d52c6f3a83f57432b09","modelId":"mimo-v2-flash","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":84.43750000000001,"warning":null},{"id":"d675a347ba1cc300cdd50958","modelId":"mimo-v2-flash","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":65.5555555555556,"warning":null},{"id":"0773db899cdffa4e1ded8ba6","modelId":"mimo-v2-flash","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":84.64646464646471,"warning":null},{"id":"3ad9dff856d49a94cb99de1f","modelId":"mimo-v2-flash","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":8.57275254865616,"warning":null},{"id":"3920da93b773299bcb0edfce","modelId":"mimo-v2-flash","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":22.8452270620945,"warning":null},{"id":"5baca63841da31c57e5ae037","modelId":"mimo-v2-flash","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":39.9319727891157,"warning":null},{"id":"f366555ca241ca7c7571729f","modelId":"mimo-v2-flash","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":64.2176870748299,"warning":null},{"id":"136673bead80a3b356afdee4","modelId":"mimo-v2-flash","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":40.2116402116402,"warning":null},{"id":"7cb51c7248fc435c2871aebc","modelId":"mimo-v2-flash","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":86.7724867724868,"warning":null},{"id":"a1e63baef98defadff1101a6","modelId":"mimo-v2-flash","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":74.4348404255319,"warning":null},{"id":"87b8554680365a774f346ece","modelId":"mimo-v2-flash","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":84.3417553191489,"warning":null},{"id":"25c20a5aaee132cb4c3e9285","modelId":"mimo-v2-flash","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":-48.45,"warning":null},{"id":"f5425b9754a5e445a5236ede","modelId":"mimo-v2-flash","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":-45.35,"warning":null},{"id":"644bce3e0d96665ff5259654","modelId":"mimo-v2-flash","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":15.633333333333333,"warning":null},{"id":"1b6fad8193ad71cc3e2e3c6b","modelId":"mimo-v2-flash","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":24.833333333333332,"warning":null},{"id":"3cc13fc1b52d73266be2282d","modelId":"mimo-v2-flash","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":83.9181286549708,"warning":null},{"id":"9dd928416fa90717a399e327","modelId":"mimo-v2-flash","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":95.0292397660819,"warning":null},{"id":"f6a30fe9e813cbabe7dcdc98","modelId":"mimo-v2-flash","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":25.7575757575758,"warning":null},{"id":"bae7463f2643e0ed3fc2532b","modelId":"mimo-v2-flash","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiMo-V2-Flash (Reasoning)","configuration":"MiMo-V2-Flash (Reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash-reasoning","score":28.030303030303,"warning":null},{"id":"be9cfbf93f75099ff67dd311","modelId":"mimo-v2-flash","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"MiMo-V2-Flash (Non-reasoning)","configuration":"MiMo-V2-Flash (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-flash","score":61.797752808988804,"warning":null},{"id":"9ffb2fbc8acdbb5fa868e907","modelId":"mimo-v2.5","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":750.72,"warning":null},{"id":"6e83c247df799a06891d5c23","modelId":"mimo-v2.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":73,"warning":null},{"id":"2d2e86088b5f8c7b172e4017","modelId":"mimo-v2.5","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.42951233004315,"warning":null},{"id":"064950ae79afc2e1a558cfd4","modelId":"mimo-v2.5","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.7142857142857104,"warning":null},{"id":"7a6c3c90bb654755ab0227ad","modelId":"mimo-v2.5","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":4,"warning":null},{"id":"037febc53053e2dcb9b47a7f","modelId":"mimo-v2.5","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":1079.43,"warning":null},{"id":"dec96f1d4a54fa1a862e15bf","modelId":"mimo-v2.5","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.94949494949499,"warning":null},{"id":"3d0236e6e49d8d8d28e01c73","modelId":"mimo-v2.5","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.201112140871196,"warning":null},{"id":"832157a7f55c7b6cd246f105","modelId":"mimo-v2.5","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.14285714285711,"warning":null},{"id":"1d587cd054a074e2950f881b","modelId":"mimo-v2.5","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.4335260115607,"warning":null},{"id":"dce9246667e76d78df4c7435","modelId":"mimo-v2.5","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":-9.83333333333333,"warning":null},{"id":"adb5cf425682f21a39d89ebd","modelId":"mimo-v2.5","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.75,"warning":null},{"id":"3ad50ec8ea74deb9634c82d7","modelId":"mimo-v2.5","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.8657407407407,"warning":null},{"id":"d41a88e61beaa1a787af3bfb","modelId":"mimo-v2.5","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":90.6432748538012,"warning":null},{"id":"75e18d8f2290eb1f93e4b341","modelId":"mimo-v2.5","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.65979381443299,"warning":null},{"id":"9e3e743e86bb15ebf4c91aa8","modelId":"mimo-v2.5","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.6666666666667,"warning":null},{"id":"8b19ccc651ba74f8d9c9cfc8","modelId":"mimo-v2.5","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.6704119850187,"warning":null},{"id":"5a2f61a9349f73f419db3844","modelId":"mimo-v2.5","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"MiMo-V2.5","configuration":"MiMo-V2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-0424; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"aa8865db70c47bb7dfb128f9","modelId":"mimo-v2.5-pro","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":20,"warning":null},{"id":"10408a3544658e1ddd5de105","modelId":"mimo-v2.5-pro","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":883.43,"warning":null},{"id":"a7d2bcfee55db5a2505b3634","modelId":"mimo-v2.5-pro","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.43362831858407,"warning":null},{"id":"fc1a2332e16a8d2dccb00939","modelId":"mimo-v2.5-pro","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":41.6666666666667,"warning":null},{"id":"39ba4dba44c1102d67baf7a4","modelId":"mimo-v2.5-pro","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.6666666666667,"warning":null},{"id":"ff0c2d45c031c24afe7115b3","modelId":"mimo-v2.5-pro","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.703616508004313,"warning":null},{"id":"b0f93b30c77f797af5ca0bf9","modelId":"mimo-v2.5-pro","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":1.1428571428571401,"warning":null},{"id":"eba41a2659d0c3b4a213133b","modelId":"mimo-v2.5-pro","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":4,"warning":null},{"id":"5f4a0dd5975c36a9ccc0191a","modelId":"mimo-v2.5-pro","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":4,"warning":null},{"id":"69737750e0f7b088fa8e9a5d","modelId":"mimo-v2.5-pro","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":1186.32,"warning":null},{"id":"e62c663d0e43ba6605976071","modelId":"mimo-v2.5-pro","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":76.1616161616162,"warning":null},{"id":"6f278af330e867f97be2f486","modelId":"mimo-v2.5-pro","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":86.5656565656566,"warning":null},{"id":"7eff5dc11f25d736892ffc61","modelId":"mimo-v2.5-pro","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.2522796352584,"warning":null},{"id":"91caea072d8597c8ac5fb15b","modelId":"mimo-v2.5-pro","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":14.7822057460612,"warning":null},{"id":"8bbacd899f7789e32c381c4a","modelId":"mimo-v2.5-pro","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.6811862835959,"warning":null},{"id":"cb3f9696c12ea026ad23ee03","modelId":"mimo-v2.5-pro","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":42.7210884353741,"warning":null},{"id":"4ba4f52ff6dc1ac0a6b4e163","modelId":"mimo-v2.5-pro","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.8639455782313,"warning":null},{"id":"93e1b5c3fa106e34f3235832","modelId":"mimo-v2.5-pro","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.229755178907695,"warning":null},{"id":"a71198824bbba9c01c783584","modelId":"mimo-v2.5-pro","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.44444444444444,"warning":null},{"id":"f20dd3ebb423e6ee03f6caee","modelId":"mimo-v2.5-pro","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":-37.8,"warning":null},{"id":"f8d44cda02c43ae2b8612813","modelId":"mimo-v2.5-pro","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.25,"warning":null},{"id":"21677ace23284fc1d6430259","modelId":"mimo-v2.5-pro","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":27.18333333333333,"warning":null},{"id":"520d70a578e2b68e229d64b4","modelId":"mimo-v2.5-pro","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.416666666666664,"warning":null},{"id":"180a2693d571d25cae080430","modelId":"mimo-v2.5-pro","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.578703703703695,"warning":null},{"id":"e722cf4319818646ca6e10b5","modelId":"mimo-v2.5-pro","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":72.5146198830409,"warning":null},{"id":"9161b5318bd7b88621cad180","modelId":"mimo-v2.5-pro","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":94.15204678362569,"warning":null},{"id":"4fc646e273a89ef9f25b73a4","modelId":"mimo-v2.5-pro","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.896907216494839,"warning":null},{"id":"9c637329ea6a800195133a96","modelId":"mimo-v2.5-pro","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"MiMo-V2.5-Pro (Non-reasoning)","configuration":"MiMo-V2.5-Pro (Non-reasoning); Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning","score":35.6060606060606,"warning":null},{"id":"a75bc34d65079b1a2bf325fd","modelId":"mimo-v2.5-pro","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.1818181818182,"warning":null},{"id":"d2c532f29f3ce520c178e8f8","modelId":"mimo-v2.5-pro","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":65.1685393258427,"warning":null},{"id":"990ac08433bde368141db4a3","modelId":"mimo-v2.5-pro","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"MiMo-V2.5-Pro","configuration":"MiMo-V2.5-Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mimo-v2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"5be0fb393415bc28fc914de1","modelId":"minicpm5-2b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":433.52,"warning":null},{"id":"b2a906d4e7d0bcb771c59190","modelId":"minicpm5-2b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":59.33333333333331,"warning":null},{"id":"eab3ca6e668837d32dbf0f84","modelId":"minicpm5-2b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.8006007862431708,"warning":null},{"id":"d6f50cbeea24cc50749a6588","modelId":"minicpm5-2b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"89fa7cef514475fe6cb85d96","modelId":"minicpm5-2b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.4000000000000001,"warning":null},{"id":"f59a822e8fe0497588720463","modelId":"minicpm5-2b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":827.51,"warning":null},{"id":"7b22165b4cb228728b966f75","modelId":"minicpm5-2b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.2020202020202,"warning":null},{"id":"58c0e4b12f0557e3f0c56eb2","modelId":"minicpm5-2b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.943466172381841,"warning":null},{"id":"97a83445db5e3087c342c4f8","modelId":"minicpm5-2b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-11.65,"warning":null},{"id":"9da5239ef85d9ee0a317f40f","modelId":"minicpm5-2b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.416666666666666,"warning":null},{"id":"b37840fcc4887b193a7da1b9","modelId":"minicpm5-2b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.273148148148103,"warning":null},{"id":"dff041001a0b378a9dc8c1ff","modelId":"minicpm5-2b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.8247422680412,"warning":null},{"id":"0c83b7be0704c58f9f95b8b9","modelId":"minicpm5-2b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.61423220973783,"warning":null},{"id":"30eccba22a3fc77326f6a727","modelId":"minicpm5-2b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"MiniCPM5-2B","configuration":"MiniCPM5-2B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minicpm5-2b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"6a9234ac9a3f32d0ebc2abf0","modelId":"minimax-m1-40k","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.6666666666667,"warning":null},{"id":"788f2e240a00d67b9967bfe3","modelId":"minimax-m1-40k","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.1818181818182,"warning":null},{"id":"1c98715ed4f5b7aa5cacd5fb","modelId":"minimax-m1-40k","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.83132530120482,"warning":null},{"id":"c47fefff4069984b5210ed42","modelId":"minimax-m1-40k","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.2244897959184,"warning":null},{"id":"7a456ca77982a503622aef14","modelId":"minimax-m1-40k","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":65.71428571428571,"warning":null},{"id":"eec2171903ac55545a6ef3bb","modelId":"minimax-m1-40k","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":97.2,"warning":null},{"id":"c03e16d248d044b91a74c874","modelId":"minimax-m1-40k","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.8261303191489,"warning":null},{"id":"500f48b1cccab1db90df44b5","modelId":"minimax-m1-40k","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.5789473684211,"warning":null},{"id":"763cf25103d998af4d1f28fc","modelId":"minimax-m1-40k","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiniMax M1 40k","configuration":"MiniMax M1 40k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-40k; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.27272727272727,"warning":null},{"id":"baa673fd7f683726d8a5dda4","modelId":"minimax-m1-80k","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":61,"warning":null},{"id":"7d6db873825a7618efbd9abb","modelId":"minimax-m1-80k","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":57.6666666666667,"warning":null},{"id":"e82a3c3e3750d84732cf515e","modelId":"minimax-m1-80k","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"569994eadbf73e950041b1f9","modelId":"minimax-m1-80k","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.6969696969697,"warning":null},{"id":"1551ef2a33f01b47020ef547","modelId":"minimax-m1-80k","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.89712696941613,"warning":null},{"id":"35517fb9c2159a955b38a320","modelId":"minimax-m1-80k","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.7687074829932,"warning":null},{"id":"76e122aa7a3557f5540aa180","modelId":"minimax-m1-80k","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.1111111111111,"warning":null},{"id":"bf49f69842e743085d3b29d4","modelId":"minimax-m1-80k","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":98,"warning":null},{"id":"707035a3df53472cb7e55178","modelId":"minimax-m1-80k","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.6240026595745,"warning":null},{"id":"32652eb449f7c6cb3047e850","modelId":"minimax-m1-80k","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":-48.5,"warning":null},{"id":"7bd753242e76b19ea002e45b","modelId":"minimax-m1-80k","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.466666666666665,"warning":null},{"id":"3b570ef41663865b99bb5f67","modelId":"minimax-m1-80k","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.2105263157895,"warning":null},{"id":"70b65a26ecb30426a99bbd11","modelId":"minimax-m1-80k","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiniMax M1 80k","configuration":"MiniMax M1 80k; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m1-80k; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.03030303030303,"warning":null},{"id":"15e173c41fc9f2886eb66b86","modelId":"minimax-m2","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.3333333333333,"warning":null},{"id":"4b2a76acf855c3e0dc2d8d5b","modelId":"minimax-m2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":64.3333333333333,"warning":null},{"id":"6b058f286079d54d349739c0","modelId":"minimax-m2","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.857142857142857,"warning":null},{"id":"c8ceb595a568197b84bb8dcf","modelId":"minimax-m2","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.91666666666666,"warning":null},{"id":"d5a6567b3645829fc2a3454f","modelId":"minimax-m2","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.6767676767677,"warning":null},{"id":"e93f40e73566ac13cdce81f1","modelId":"minimax-m2","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.670064874884199,"warning":null},{"id":"46c99f54bc78b97ddd3fca48","modelId":"minimax-m2","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.312925170068,"warning":null},{"id":"cb9c2d9b8a2a2cbceac239dc","modelId":"minimax-m2","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.6455026455027,"warning":null},{"id":"8dffa85148103a6fbf5866f2","modelId":"minimax-m2","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.0229388297872,"warning":null},{"id":"511c96d55ac43f5883ed839a","modelId":"minimax-m2","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":-46.55,"warning":null},{"id":"a8c566f58d9598384af26fad","modelId":"minimax-m2","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.233333333333334,"warning":null},{"id":"294e3daadab33e631e294791","modelId":"minimax-m2","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":86.8421052631579,"warning":null},{"id":"20afbe1ed17985e55a8f213e","modelId":"minimax-m2","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiniMax-M2","configuration":"MiniMax-M2; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2; Mode from evaluator isReasoning metadata; effort budget not specified","score":25.7575757575758,"warning":null},{"id":"012ec764d84111d300f13dac","modelId":"minimax-m2.1","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.6666666666667,"warning":null},{"id":"415c1a5b1c6ee36b839c2b75","modelId":"minimax-m2.1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.6666666666667,"warning":null},{"id":"706205dd32d2865bdad3c837","modelId":"minimax-m2.1","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"f89ac3dfe86a385c12009ee9","modelId":"minimax-m2.1","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.00000000000001,"warning":null},{"id":"06bba500a66ed5571b158392","modelId":"minimax-m2.1","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":83.030303030303,"warning":null},{"id":"bac805b323fcd165819d80b9","modelId":"minimax-m2.1","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.1696014828545,"warning":null},{"id":"63fcf0b40ce80d3935457cc3","modelId":"minimax-m2.1","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.8639455782313,"warning":null},{"id":"42d6364f9e1e5af2e60567ba","modelId":"minimax-m2.1","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.95238095238099,"warning":null},{"id":"607ba4f5a3bc386b9243147d","modelId":"minimax-m2.1","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":87.4916888297872,"warning":null},{"id":"c5300b173b3b63c3bb16dbd2","modelId":"minimax-m2.1","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":-32.8666666666667,"warning":null},{"id":"63491bdbc3d101722d1e08b6","modelId":"minimax-m2.1","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.166666666666668,"warning":null},{"id":"ca2ec2abdaaeae0bda0f8bf1","modelId":"minimax-m2.1","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":85.3801169590643,"warning":null},{"id":"49baf6fa212628aa4d1c49eb","modelId":"minimax-m2.1","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiniMax-M2.1","configuration":"MiniMax-M2.1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.7878787878788,"warning":null},{"id":"fdd30d2c9b426a753f20b9be","modelId":"minimax-m2.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.3333333333333,"warning":null},{"id":"a1617509d3cbb2fd7d00a142","modelId":"minimax-m2.5","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.1428571428571401,"warning":null},{"id":"9ce6c4532cb91f00ecbfccda","modelId":"minimax-m2.5","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.23958333333333,"warning":null},{"id":"32c51132daff11e2ed08e2f7","modelId":"minimax-m2.5","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.8484848484848,"warning":null},{"id":"e5ce79cceaa2a277376cead9","modelId":"minimax-m2.5","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.5282669138091,"warning":null},{"id":"7e865e71141b2c84968e7539","modelId":"minimax-m2.5","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.6326530612245,"warning":null},{"id":"aa77f8427f177890a4cbbdd7","modelId":"minimax-m2.5","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":-38.8666666666667,"warning":null},{"id":"c0846c958c8a9391b1607a28","modelId":"minimax-m2.5","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.18333333333333,"warning":null},{"id":"d891e4daf4fb77148b30e881","modelId":"minimax-m2.5","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":95.3216374269006,"warning":null},{"id":"79f3006b495cd426a1b73144","modelId":"minimax-m2.5","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiniMax-M2.5","configuration":"MiniMax-M2.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.8484848484849,"warning":null},{"id":"321b203cb1bcd8963cb0d3f1","modelId":"minimax-m2.7","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.25,"warning":null},{"id":"2f29c7dafb579787394c73bb","modelId":"minimax-m2.7","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":715.25,"warning":null},{"id":"0a2ca8def46f136850189c8d","modelId":"minimax-m2.7","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.6194690265487,"warning":null},{"id":"fb3d618157a3f1a25a01a961","modelId":"minimax-m2.7","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.3333333333333,"warning":null},{"id":"26a788cce0f3865839b1a6a3","modelId":"minimax-m2.7","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.435290250372898,"warning":null},{"id":"794fb014d2eb798e8b2998f4","modelId":"minimax-m2.7","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.571428571428571,"warning":null},{"id":"567794a1ed9be3483b007022","modelId":"minimax-m2.7","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":6,"warning":null},{"id":"b89c3f9dc6e1bcc60f60a946","modelId":"minimax-m2.7","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":1087.02,"warning":null},{"id":"f0c7870f4e72d890a6e64bb4","modelId":"minimax-m2.7","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":87.3737373737374,"warning":null},{"id":"d5472132d9679cc02891ff10","modelId":"minimax-m2.7","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.610750695088,"warning":null},{"id":"ee98703c061223da691631e2","modelId":"minimax-m2.7","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.7142857142857,"warning":null},{"id":"b5993fc570c20cd787f9e13a","modelId":"minimax-m2.7","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.459510357815404,"warning":null},{"id":"b989c5a8f886f6da83a747a2","modelId":"minimax-m2.7","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.33333333333333,"warning":null},{"id":"e4e76f6bd4e0359ded238ed2","modelId":"minimax-m2.7","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.766666666666667,"warning":null},{"id":"c4cc58c4b043d4096f9904e6","modelId":"minimax-m2.7","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.8,"warning":null},{"id":"ffed6553b2632c7198bffaf9","modelId":"minimax-m2.7","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.1157407407407,"warning":null},{"id":"11881577f9e60c3849db70ae","modelId":"minimax-m2.7","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.7953216374269,"warning":null},{"id":"30e77a7107692ba54da4230b","modelId":"minimax-m2.7","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.896907216494839,"warning":null},{"id":"787cc9d04ef43d1609bcd3bd","modelId":"minimax-m2.7","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.3939393939394,"warning":null},{"id":"f8ae42068ed742b6900a2f63","modelId":"minimax-m2.7","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":55.4307116104869,"warning":null},{"id":"eee673418f1fbd3067f5fc74","modelId":"minimax-m2.7","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"MiniMax-M2.7","configuration":"MiniMax-M2.7; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m2-7; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"1b190b8dbfc16399d02b9178","modelId":"minimax-m3","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":10,"warning":null},{"id":"ca1e3276277c91cd2ba305b8","modelId":"minimax-m3","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":1096.03,"warning":null},{"id":"c2e74f20e737aa48dad4c020","modelId":"minimax-m3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":83,"warning":null},{"id":"248b861b8fed37090c1f8c0b","modelId":"minimax-m3","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.25125760074941,"warning":null},{"id":"1f198b5e25c25ed5607f80d6","modelId":"minimax-m3","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.7142857142857104,"warning":null},{"id":"951a4a9311deecbd1ebfeba8","modelId":"minimax-m3","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.10981796478663,"warning":null},{"id":"658dddbeb79c99f8170b45c6","modelId":"minimax-m3","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.8,"warning":null},{"id":"aa7c570ef6685ffd1d23a3b8","modelId":"minimax-m3","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":1303.96,"warning":null},{"id":"256f9459d7bae8c1220d17aa","modelId":"minimax-m3","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":92.9292929292929,"warning":null},{"id":"8017c016e002a36286acd506","modelId":"minimax-m3","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.4064264003474,"warning":null},{"id":"e81c6a6abc1d601d7c3cc6e5","modelId":"minimax-m3","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.9712696941613,"warning":null},{"id":"1215dcb06b2956ad29b293d1","modelId":"minimax-m3","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.85714285714289,"warning":null},{"id":"b71623bbe996f6dabd9c34c8","modelId":"minimax-m3","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.2222222222222,"warning":null},{"id":"309e3a0e336f395747e154e9","modelId":"minimax-m3","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.5549132947977,"warning":null},{"id":"4fe2dbb70cb706ac86051368","modelId":"minimax-m3","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.35,"warning":null},{"id":"c8a6c5af1be278d8485103a7","modelId":"minimax-m3","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.7,"warning":null},{"id":"ca3f36ad153ea45bc8abefbe","modelId":"minimax-m3","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.1064814814815,"warning":null},{"id":"dfa5db0c68d02042c0e75111","modelId":"minimax-m3","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.8888888888889,"warning":null},{"id":"5ec3544112e3145637229862","modelId":"minimax-m3","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.2577319587629,"warning":null},{"id":"28e428e681b3d40c5d5bd4b7","modelId":"minimax-m3","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.4242424242424,"warning":null},{"id":"2daf109e7eda8d8d1b90de72","modelId":"minimax-m3","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":65.1685393258427,"warning":null},{"id":"ceeed623352a3b0afbc75255","modelId":"minimax-m3","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"MiniMax-M3","configuration":"MiniMax-M3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/minimax-m3; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.02020202020202,"warning":null},{"id":"8fbe85f123d76d9d2586135f","modelId":"ministral-3-14b","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":149.57,"warning":null},{"id":"42349f526e6d0332bf405daf","modelId":"ministral-3-14b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":30,"warning":null},{"id":"a0c8321b9301b9f1798b9cfc","modelId":"ministral-3-14b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.333333333333297,"warning":null},{"id":"0070a33608cc4dff46bd33ae","modelId":"ministral-3-14b","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.5512132673736124,"warning":null},{"id":"846b8d7e1064ca9b051085c7","modelId":"ministral-3-14b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"cda2910501e76db2d2736f56","modelId":"ministral-3-14b","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.2,"warning":null},{"id":"24e35412de2028573d8e1019","modelId":"ministral-3-14b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":432.06,"warning":null},{"id":"6a3eca23d8d091c16f3cfd1c","modelId":"ministral-3-14b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.32291666666667,"warning":null},{"id":"6b2250ddf133129bcae06578","modelId":"ministral-3-14b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":57.1717171717172,"warning":null},{"id":"587f9758a421063bc87f1bd3","modelId":"ministral-3-14b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.6339202965709,"warning":null},{"id":"8e84b419d65d216d6cbfa5af","modelId":"ministral-3-14b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.0408163265306,"warning":null},{"id":"5fb5342b1e2722933a4b16a0","modelId":"ministral-3-14b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.1322751322751,"warning":null},{"id":"f87c3cd084923ae9b2c7f4ce","modelId":"ministral-3-14b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.3234707446808,"warning":null},{"id":"0e5192b6eba15650e9b5f30b","modelId":"ministral-3-14b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":49.8265895953757,"warning":null},{"id":"7d6441354088c9ffdd6ef7a3","modelId":"ministral-3-14b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-66.3666666666667,"warning":null},{"id":"8fea1cc0e155ab32e6483df1","modelId":"ministral-3-14b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.583333333333334,"warning":null},{"id":"41e2bdc01aaf88a7862f9af3","modelId":"ministral-3-14b","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.842592592592602,"warning":null},{"id":"97bfb615237aae3a3c921741","modelId":"ministral-3-14b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.192982456140403,"warning":null},{"id":"a7b6b01c635f177b41f7ae72","modelId":"ministral-3-14b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.5979381443299,"warning":null},{"id":"a19663d7c4239500d8bf6258","modelId":"ministral-3-14b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.545454545454549,"warning":null},{"id":"c19f710109a638e2159d0164","modelId":"ministral-3-14b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.73782771535581,"warning":null},{"id":"36a15daaabc73dc6d5977ead","modelId":"ministral-3-14b","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Ministral 3 14B","configuration":"Ministral 3 14B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-14b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"a0cdd6b1bc45df086f827bb9","modelId":"ministral-3-3b","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.01,"warning":null},{"id":"9a944bda300cc996ed6055a5","modelId":"ministral-3-3b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":22,"warning":null},{"id":"377e02abab9d9b855350cd51","modelId":"ministral-3-3b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":17,"warning":null},{"id":"843d9648b3e5e036b0acb2be","modelId":"ministral-3-3b","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.6658657772309807,"warning":null},{"id":"8ed0c4631ac65f1f25e3f7ca","modelId":"ministral-3-3b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"cb5b018f13832c2363fbacae","modelId":"ministral-3-3b","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"06fa32a04d01bcf836b82456","modelId":"ministral-3-3b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":233.97,"warning":null},{"id":"b537260129d057deead47b8d","modelId":"ministral-3-3b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":56.72916666666667,"warning":null},{"id":"58e5a9f2cd204be72403efef","modelId":"ministral-3-3b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.7575757575758,"warning":null},{"id":"d1a4aca9ced7ddd73ed98e8c","modelId":"ministral-3-3b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.37534754402224,"warning":null},{"id":"0bf69fe4d67896af5c1f65c8","modelId":"ministral-3-3b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.802721088435398,"warning":null},{"id":"5bcb8f2f21bc3ebaf7da173c","modelId":"ministral-3-3b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.6560846560847,"warning":null},{"id":"283f4b4a8c76f509c6d422e7","modelId":"ministral-3-3b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.35206117021281,"warning":null},{"id":"3b5a9373617c66fda5b546f0","modelId":"ministral-3-3b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.092485549132896,"warning":null},{"id":"928da08d1319107c56189f07","modelId":"ministral-3-3b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-64,"warning":null},{"id":"7a796ce9f7d23b28986ff5e8","modelId":"ministral-3-3b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.983333333333334,"warning":null},{"id":"719ae7fb0aa3a8f58828d8ad","modelId":"ministral-3-3b","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.277777777777802,"warning":null},{"id":"83db4f32b2b311f3f83c14d5","modelId":"ministral-3-3b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.8538011695906,"warning":null},{"id":"c9c4e289cdf58ffe5ffa14b4","modelId":"ministral-3-3b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.74226804123711,"warning":null},{"id":"4f010862ca6747cc6d8401ce","modelId":"ministral-3-3b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"77514ba2a733e772619ec66b","modelId":"ministral-3-3b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"7009edb8b996cc961ae08907","modelId":"ministral-3-3b","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Ministral 3 3B","configuration":"Ministral 3 3B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"9a43ec3849995da12ffe283e","modelId":"ministral-3-8b","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":99.22,"warning":null},{"id":"3dd4f3c338791cdbb4285fe1","modelId":"ministral-3-8b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.6666666666667,"warning":null},{"id":"6007b52d64bc356c474923d7","modelId":"ministral-3-8b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":25.6666666666667,"warning":null},{"id":"605bc0d7c72327162c223151","modelId":"ministral-3-8b","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.516749466666553,"warning":null},{"id":"a8ad5cdcd0e1929baa7929f2","modelId":"ministral-3-8b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"dea8abc42d6581d240a14318","modelId":"ministral-3-8b","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.8,"warning":null},{"id":"3275de864af51270520134c1","modelId":"ministral-3-8b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":404.6,"warning":null},{"id":"7183c2052a20887069af7aa7","modelId":"ministral-3-8b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.32291666666667,"warning":null},{"id":"41188e61e8f63338df1815bf","modelId":"ministral-3-8b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.0707070707071,"warning":null},{"id":"b6bf00c2a753272d88d86510","modelId":"ministral-3-8b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.2632066728452305,"warning":null},{"id":"05a6e30b5856ecc160d17ae0","modelId":"ministral-3-8b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.115646258503403,"warning":null},{"id":"e7c5d463ec1b8d046eeeffef","modelId":"ministral-3-8b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.264550264550298,"warning":null},{"id":"e640a3de368a7ff58a8b9410","modelId":"ministral-3-8b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":64.1539228723404,"warning":null},{"id":"faad5ca0d804e52efc4f202b","modelId":"ministral-3-8b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":45.9537572254335,"warning":null},{"id":"75e22a9892b66c0e65dfd55d","modelId":"ministral-3-8b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-68.95,"warning":null},{"id":"edcff04c2243d437ad690a4d","modelId":"ministral-3-8b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.983333333333333,"warning":null},{"id":"60d1bb31feedab5df58faad3","modelId":"ministral-3-8b","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.717592592592602,"warning":null},{"id":"43a3d3fe9aa6ddda6930bd0e","modelId":"ministral-3-8b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.6081871345029,"warning":null},{"id":"4d95912317d4bb5d72f9b21d","modelId":"ministral-3-8b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.71134020618557,"warning":null},{"id":"d5d3b3be768714fdf63001cf","modelId":"ministral-3-8b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.545454545454549,"warning":null},{"id":"0c7d5dd66f6c30384d34f3fd","modelId":"ministral-3-8b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.11985018726592,"warning":null},{"id":"345253b8f88be2712721eb6a","modelId":"ministral-3-8b","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Ministral 3 8B","configuration":"Ministral 3 8B; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/ministral-3-8b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"dbe2eeeed1d775de800dcb31","modelId":"mistral-large-2407","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"348a6de2555440e02838cb61","modelId":"mistral-large-2407","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":2,"warning":null},{"id":"b7a16d7e8dee63f9d55e9d63","modelId":"mistral-large-2407","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.1717171717172,"warning":null},{"id":"d63bb6149699d19daa535c35","modelId":"mistral-large-2407","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.9499999999999997,"warning":null},{"id":"28e7e03881e741b0ee543153","modelId":"mistral-large-2407","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.632653061224502,"warning":null},{"id":"b0ca3209dcb5204b311ef0d3","modelId":"mistral-large-2407","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.6666666666667,"warning":null},{"id":"381cfdc71bbd8167f239652c","modelId":"mistral-large-2407","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.39999999999999,"warning":null},{"id":"13edbb09a0d6f48740227bf4","modelId":"mistral-large-2407","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.2596409574468,"warning":null},{"id":"05576a4ab91490da5b5f7e76","modelId":"mistral-large-2407","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Mistral Large 2 (Jul '24)","configuration":"Mistral Large 2 (Jul '24); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-2407; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.0409356725146,"warning":null},{"id":"fe50bbf18ffd82f1cdb29fa8","modelId":"mistral-large-3","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":245.84,"warning":null},{"id":"2819c29ad8fdb7646a035be2","modelId":"mistral-large-3","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":38,"warning":null},{"id":"bab6a467560df59ccde7382d","modelId":"mistral-large-3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":36,"warning":null},{"id":"42b857e698d4260f5223208e","modelId":"mistral-large-3","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.4974701708193463,"warning":null},{"id":"3437f9bc1e0ac1692f5c5bda","modelId":"mistral-large-3","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"1a823311b9704e57063bf129","modelId":"mistral-large-3","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.2,"warning":null},{"id":"7ae2c33625f94d5842ef6f4c","modelId":"mistral-large-3","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":588.39,"warning":null},{"id":"07149ebe5716925ff1f2d43b","modelId":"mistral-large-3","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.33333333333333,"warning":null},{"id":"d565292efd326186f35512e8","modelId":"mistral-large-3","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.979797979798,"warning":null},{"id":"e982d1f0c2e679c26443a26c","modelId":"mistral-large-3","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.17052826691381,"warning":null},{"id":"b95857dee1e294d54839285f","modelId":"mistral-large-3","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.190476190476204,"warning":null},{"id":"118e84cb8fab9c3a1fb4fa3b","modelId":"mistral-large-3","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.4550264550264,"warning":null},{"id":"00443aa27838a4d61aa17081","modelId":"mistral-large-3","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.6515957446808,"warning":null},{"id":"04902275b4289db5be2e8909","modelId":"mistral-large-3","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":55.6647398843931,"warning":null},{"id":"fe1a4682c062f12dbe7de410","modelId":"mistral-large-3","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":-39.5666666666667,"warning":null},{"id":"fac9bcbdc0f81c8e44b0ac55","modelId":"mistral-large-3","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.95,"warning":null},{"id":"4eccbe09a60fef497d086249","modelId":"mistral-large-3","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.5740740740741,"warning":null},{"id":"55e1c75933ec7e8373537acd","modelId":"mistral-large-3","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.5614035087719,"warning":null},{"id":"9a30580079b16a6231c310bb","modelId":"mistral-large-3","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.77319587628866,"warning":null},{"id":"d5906c4f5d64bad2845778a8","modelId":"mistral-large-3","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.909090909090901,"warning":null},{"id":"f223a37edff3ec7188daa1f8","modelId":"mistral-large-3","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.9850187265918,"warning":null},{"id":"5bb842631418e84f512ae48a","modelId":"mistral-large-3","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Mistral Large 3","configuration":"Mistral Large 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-large-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"8598ad2d6ffa40f68ee3112e","modelId":"mistral-medium-2505","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.3333333333333,"warning":null},{"id":"cd3eea1dc8c7bbb962e269d1","modelId":"mistral-medium-2505","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.3333333333333,"warning":null},{"id":"dda57f94dfcd00bf84f043f2","modelId":"mistral-medium-2505","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"5c500f8d1d9109499173dc22","modelId":"mistral-medium-2505","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":57.77777777777779,"warning":null},{"id":"8a627e4cf810decf4c58ca18","modelId":"mistral-medium-2505","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.05,"warning":null},{"id":"32fb52a7ef7e80c24bf51218","modelId":"mistral-medium-2505","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.2517006802721,"warning":null},{"id":"b7ecce4ab23d7e0b1d66c046","modelId":"mistral-medium-2505","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":40,"warning":null},{"id":"e80fbfd55ae35c4506737fb1","modelId":"mistral-medium-2505","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":90.6666666666667,"warning":null},{"id":"77cc970d5bca332420c6f124","modelId":"mistral-medium-2505","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.9724069148936,"warning":null},{"id":"366f3b0107c0572f5d49886f","modelId":"mistral-medium-2505","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":53.0057803468208,"warning":null},{"id":"98b8086ecdd729adb943befa","modelId":"mistral-medium-2505","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":-31.4,"warning":null},{"id":"ef1572ebbb7db6d1d5e0ea19","modelId":"mistral-medium-2505","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.333333333333332,"warning":null},{"id":"853fba57bc04b7caeed6606b","modelId":"mistral-medium-2505","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.269005847953203,"warning":null},{"id":"54ae2b40694a6eddf2507953","modelId":"mistral-medium-2505","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Mistral Medium 3","configuration":"Mistral Medium 3; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.78787878787879,"warning":null},{"id":"9e4899ebbe0be74cfcc04447","modelId":"mistral-medium-2508","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":532.28,"warning":null},{"id":"e7008acf3eac0efcb0ed528e","modelId":"mistral-medium-2508","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.3333333333333,"warning":null},{"id":"0060828c4561c3146a4d2fbe","modelId":"mistral-medium-2508","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.146227762526245,"warning":null},{"id":"8b3ef38d2b5d2fc9f19a3ed9","modelId":"mistral-medium-2508","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"ab90f51570bba0df1c889314","modelId":"mistral-medium-2508","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.2,"warning":null},{"id":"640e064de235da086716563e","modelId":"mistral-medium-2508","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":555.23,"warning":null},{"id":"350c2c641e04fcb49688e650","modelId":"mistral-medium-2508","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.7878787878788,"warning":null},{"id":"ba265b790d9a002b971910c1","modelId":"mistral-medium-2508","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.68025949953661,"warning":null},{"id":"3a8b8a4a21798fb14026769d","modelId":"mistral-medium-2508","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.7959183673469,"warning":null},{"id":"53fa70129bf83f83ab6219a3","modelId":"mistral-medium-2508","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.634920634920604,"warning":null},{"id":"3f9dfe82f4892e139fabc3f4","modelId":"mistral-medium-2508","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.3261303191489,"warning":null},{"id":"dae076a0eacaa63ec8f192c9","modelId":"mistral-medium-2508","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.1618497109827,"warning":null},{"id":"98f555a90b9ec68d099b3ccf","modelId":"mistral-medium-2508","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":-46.2833333333333,"warning":null},{"id":"07b15db546d50bc3a15c79c9","modelId":"mistral-medium-2508","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.75,"warning":null},{"id":"0bc62ae3ef77f27ee9feb8c3","modelId":"mistral-medium-2508","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.407407407407405,"warning":null},{"id":"02e0fffe433bd9bbb17718ce","modelId":"mistral-medium-2508","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.643274853801195,"warning":null},{"id":"96d61f35ce89c5e402b475d3","modelId":"mistral-medium-2508","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.24742268041237,"warning":null},{"id":"bcef63b769b65103b4ee5212","modelId":"mistral-medium-2508","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.6060606060606,"warning":null},{"id":"8ff2dfac5f466e44c25543b3","modelId":"mistral-medium-2508","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.8576779026217,"warning":null},{"id":"b13b890114b7d4270d307654","modelId":"mistral-medium-2508","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Mistral Medium 3.1","configuration":"Mistral Medium 3.1; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-1; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"ddec1a46d0c8daa3d68bf673","modelId":"mistral-medium-3.5","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.5,"warning":null},{"id":"30ef61afef7db6403f95ad14","modelId":"mistral-medium-3.5","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":523.63,"warning":null},{"id":"567e2e221b95563a85e802ed","modelId":"mistral-medium-3.5","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.3333333333333,"warning":null},{"id":"3104fceb9c278740e37b41b3","modelId":"mistral-medium-3.5","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.299648656993127,"warning":null},{"id":"d258144824b33f3d3324f00a","modelId":"mistral-medium-3.5","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"5df2fd6f09a89049a344da89","modelId":"mistral-medium-3.5","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.72127723067741,"warning":null},{"id":"5bdde6072a786cea090d962b","modelId":"mistral-medium-3.5","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.8000000000000003,"warning":null},{"id":"6a4cfaa2b8cd211a9881e756","modelId":"mistral-medium-3.5","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":875.14,"warning":null},{"id":"c1df964d67d6a114f0ae15fc","modelId":"mistral-medium-3.5","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.8484848484849,"warning":null},{"id":"222ddda5db002b07344766ca","modelId":"mistral-medium-3.5","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.09827760891591,"warning":null},{"id":"0e63c2ddb3ce5bb283ced808","modelId":"mistral-medium-3.5","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.7627432808156,"warning":null},{"id":"a46292af76538ed9cd457f74","modelId":"mistral-medium-3.5","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.7755102040816,"warning":null},{"id":"ed8f320f4381500052c687c9","modelId":"mistral-medium-3.5","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.66666666666667,"warning":null},{"id":"103f44c413960d3a1373d498","modelId":"mistral-medium-3.5","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":64.8554913294798,"warning":null},{"id":"df8c0054af3ea000e16148ed","modelId":"mistral-medium-3.5","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":-36.8,"warning":null},{"id":"fe26eeb3eee7044147e39ad9","modelId":"mistral-medium-3.5","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.666666666666668,"warning":null},{"id":"46f40618c1d6eceefad11b5e","modelId":"mistral-medium-3.5","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.162037037037,"warning":null},{"id":"b8f431b7af5ced6f9c6ffda2","modelId":"mistral-medium-3.5","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":94.15204678362569,"warning":null},{"id":"80753495b3c7881924eaa865","modelId":"mistral-medium-3.5","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.051546391752598,"warning":null},{"id":"54f2e07eae2bee6eeebe5743","modelId":"mistral-medium-3.5","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.3333333333333,"warning":null},{"id":"a1e4976e556451286cd3bdcf","modelId":"mistral-medium-3.5","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.561797752809,"warning":null},{"id":"8696355798a7473fc208ccd1","modelId":"mistral-medium-3.5","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Mistral Medium 3.5","configuration":"Mistral Medium 3.5; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/mistral-medium-3-5; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"a1ecc289157138b5f8e71437","modelId":"mistral-small-2506","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"6da1b8d1b2167564bf428fb0","modelId":"mistral-small-2506","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":27,"warning":null},{"id":"53bc5a579aa23fead108267c","modelId":"mistral-small-2506","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.3333333333333,"warning":null},{"id":"e63a9f1379393c3cc66d6071","modelId":"mistral-small-2506","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.2854023922677291,"warning":null},{"id":"821ded825d6af49adc589ec6","modelId":"mistral-small-2506","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"f90922973ea706908ad9cc65","modelId":"mistral-small-2506","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"f66851101e2ef688b6c97a17","modelId":"mistral-small-2506","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.2,"warning":null},{"id":"c46cb1fb5b137f1522f36b9e","modelId":"mistral-small-2506","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.078125,"warning":null},{"id":"39d3bdb6484f58e20f1c50fe","modelId":"mistral-small-2506","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.5050505050505,"warning":null},{"id":"167f1a758c5db842ce1feca6","modelId":"mistral-small-2506","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.30954587581094,"warning":null},{"id":"68d2c1aeb87f2c629ac7672d","modelId":"mistral-small-2506","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.469387755102,"warning":null},{"id":"b84c0ce3c4a5433cf625b30f","modelId":"mistral-small-2506","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.513227513227502,"warning":null},{"id":"891301aed44b6f2989b8b04d","modelId":"mistral-small-2506","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.26666666666671,"warning":null},{"id":"2d02db7530f0e9d255d63470","modelId":"mistral-small-2506","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.05186170212771,"warning":null},{"id":"34bd5ae77357e239d89ce014","modelId":"mistral-small-2506","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.9768786127168,"warning":null},{"id":"be0fd3096da38b78e3aef989","modelId":"mistral-small-2506","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":-50.5833333333333,"warning":null},{"id":"27cf85547226acfd3effbbb7","modelId":"mistral-small-2506","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.833333333333334,"warning":null},{"id":"7a032bb7d27ac4f4a54dc043","modelId":"mistral-small-2506","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.587962962962997,"warning":null},{"id":"93d03cab54cbb7dfc0b435ab","modelId":"mistral-small-2506","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.5321637426901,"warning":null},{"id":"f595e0feb6f1773fe5a6fc61","modelId":"mistral-small-2506","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.18556701030928,"warning":null},{"id":"340512192be278774e77e5da","modelId":"mistral-small-2506","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.81818181818182,"warning":null},{"id":"832c778cd48cdca55f1c79c3","modelId":"mistral-small-2506","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.61797752808989,"warning":null},{"id":"6e9568251c46a4d7f2d38ad5","modelId":"mistral-small-2506","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Mistral Small 3.2","configuration":"Mistral Small 3.2; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/mistral-small-3-2; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"9188eefd377f2e9c23d9a8b6","modelId":"mistral-small-4","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":1.25,"warning":null},{"id":"1247fc165d860e12ba33ff29","modelId":"mistral-small-4","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":255.96,"warning":null},{"id":"213e91745b08c415820c541d","modelId":"mistral-small-4","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":28.3333333333333,"warning":null},{"id":"979d64a0eb75ed822e25c686","modelId":"mistral-small-4","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":49.6666666666667,"warning":null},{"id":"4f6658801d33d9c4bbf58519","modelId":"mistral-small-4","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":0.9635410038882158,"warning":null},{"id":"8b914ad32f7c9e5f7d244d1d","modelId":"mistral-small-4","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":0.28571428571428603,"warning":null},{"id":"bf81d819d89c15dd4fe6b89b","modelId":"mistral-small-4","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":0.28571428571428603,"warning":null},{"id":"8f94ed73fa6de47d55b25077","modelId":"mistral-small-4","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":0,"warning":null},{"id":"42a91169a22c22e7eed2f268","modelId":"mistral-small-4","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":536.71,"warning":null},{"id":"6680a21e2f5f81331071ba82","modelId":"mistral-small-4","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":57.07070707070711,"warning":null},{"id":"2f6bef1401dd3c874f04eef8","modelId":"mistral-small-4","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":76.8686868686869,"warning":null},{"id":"ae1fa7961d49d684f2981dff","modelId":"mistral-small-4","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":3.79981464318814,"warning":null},{"id":"c8e3afa3aef8179b40e448f0","modelId":"mistral-small-4","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":9.870250231696021,"warning":null},{"id":"1175374611f43823a69bb917","modelId":"mistral-small-4","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":32.7891156462585,"warning":null},{"id":"5231791d1c29e104c93e1247","modelId":"mistral-small-4","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":48.1632653061224,"warning":null},{"id":"f06380625c147eb9e14efb36","modelId":"mistral-small-4","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":46.4739884393064,"warning":null},{"id":"81f942ea40a39fe097e24d66","modelId":"mistral-small-4","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":56.8208092485549,"warning":null},{"id":"2af0431ee57da42eb9cd13d5","modelId":"mistral-small-4","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":-48.5166666666667,"warning":null},{"id":"50d33b56ae65630b7fd1e35d","modelId":"mistral-small-4","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":-30.4,"warning":null},{"id":"5bf3b46928f29139d0cfdd0e","modelId":"mistral-small-4","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":16.566666666666666,"warning":null},{"id":"301e793977c259094f7093c7","modelId":"mistral-small-4","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":21.683333333333334,"warning":null},{"id":"f2789b044f471f6a2756d4f1","modelId":"mistral-small-4","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":38.7731481481481,"warning":null},{"id":"211745cfecdb17b01d94607f","modelId":"mistral-small-4","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":18.4210526315789,"warning":null},{"id":"70cdd67007153234faacd560","modelId":"mistral-small-4","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":41.2280701754386,"warning":null},{"id":"206a3af7332c726f2d612cb0","modelId":"mistral-small-4","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":4.948453608247419,"warning":null},{"id":"5e4e6f1b78b4531611aa9a8d","modelId":"mistral-small-4","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Mistral Small 4 (Non-reasoning)","configuration":"Mistral Small 4 (Non-reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4-non-reasoning","score":10.6060606060606,"warning":null},{"id":"e6390ae449afa5ff6fecfd51","modelId":"mistral-small-4","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":17.4242424242424,"warning":null},{"id":"2599f4ee8ffaec96bbf2b7aa","modelId":"mistral-small-4","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":20.9737827715356,"warning":null},{"id":"f7c7c53f6cba7efa0c09fcb8","modelId":"mistral-small-4","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Mistral Small 4 (Reasoning)","configuration":"Mistral Small 4 (Reasoning); Model source: https://artificialanalysis.ai/models/mistral-small-4","score":0,"warning":null},{"id":"3d28104ab178b34670aa619c","modelId":"muse-spark-1.1","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":860.36,"warning":null},{"id":"b0c09f33ec395a21dfca2ae2","modelId":"muse-spark-1.1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":77.6666666666667,"warning":null},{"id":"90f826dbdab369b8d36e712e","modelId":"muse-spark-1.1","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":38.84891624542286,"warning":null},{"id":"3db9f37231f6969e5af916c8","modelId":"muse-spark-1.1","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":15.1428571428571,"warning":null},{"id":"6099fc5a6c629d98c4017a6a","modelId":"muse-spark-1.1","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":14.399999999999999,"warning":null},{"id":"77cb0921403bb8eea32f98e2","modelId":"muse-spark-1.1","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":1294.15,"warning":null},{"id":"674c189b99daf251023acc62","modelId":"muse-spark-1.1","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":89.79797979797979,"warning":null},{"id":"69c92bbf50967acf2ddea1e6","modelId":"muse-spark-1.1","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":46.2001853568119,"warning":null},{"id":"1155696d61f97ace1c6685cb","modelId":"muse-spark-1.1","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":28.0833333333333,"warning":null},{"id":"e482487bec614ab5161ed411","modelId":"muse-spark-1.1","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":52.05,"warning":null},{"id":"6d5c35ac642c8328a56d2cb1","modelId":"muse-spark-1.1","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":58.796296296296305,"warning":null},{"id":"51ae435e2accf7c476e8b700","modelId":"muse-spark-1.1","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":31.752577319587598,"warning":null},{"id":"e2ce1bb7d2f24ac399b6dd2e","modelId":"muse-spark-1.1","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":77.9026217228464,"warning":null},{"id":"fa4da6d45fc3c9e23c5e0a1d","modelId":"muse-spark-1.1","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"Muse Spark 1.1 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1","score":6.06060606060606,"warning":null},{"id":"8fa6b5f2d5612bc7ff3ca112","modelId":"muse-spark-1.1","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"muse-spark-1-1","configuration":"muse-spark-1-1; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs","score":53.3,"warning":null},{"id":"4db8c7b47a313e0e8d926986","modelId":"muse-spark-1.1","benchmarkId":"terminal-minisweagent","level":"xhigh","sourceLabel":"Muse Spark 1.1","configuration":"Muse Spark 1.1; Reported effort: xhigh; 445 trials; recorded 2026-07-09","score":76.18,"warning":null},{"id":"5a5c40dc8bfa7420c7a73337","modelId":"muse-spark-1.2","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":1343.5,"warning":null},{"id":"7f054375dfae2880d425145e","modelId":"muse-spark-1.2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":79,"warning":null},{"id":"545c640a1e97c757398c4c09","modelId":"muse-spark-1.2","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":40.61337838423964,"warning":null},{"id":"77a5b3ed91707a9a184b6c15","modelId":"muse-spark-1.2","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":17.714285714285698,"warning":null},{"id":"c0c29d3596152a94d0cb8ed7","modelId":"muse-spark-1.2","benchmarkId":"aa-enterprise-ops-gym-aa","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":47.26947179946285,"warning":null},{"id":"41b9ba5b3cc128b9746727fe","modelId":"muse-spark-1.2","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":17.4,"warning":null},{"id":"536612d6ef75df4fe26d8799","modelId":"muse-spark-1.2","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":1523.32,"warning":null},{"id":"b798a8a82c6bbbfe0f4543fe","modelId":"muse-spark-1.2","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":90.4040404040404,"warning":null},{"id":"1598edcef4c4dc72d168db18","modelId":"muse-spark-1.2","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":45.458758109360495,"warning":null},{"id":"900af26141c1715a5245156e","modelId":"muse-spark-1.2","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":31.1111111111111,"warning":null},{"id":"0ae131704ad1ec5583eb3702","modelId":"muse-spark-1.2","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":27.2,"warning":null},{"id":"7778904266b2d0dafc5de1c3","modelId":"muse-spark-1.2","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":45.38333333333333,"warning":null},{"id":"e1ae73029fc1423754ddc150","modelId":"muse-spark-1.2","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":57.4074074074074,"warning":null},{"id":"5a4630ffdeb77234b578ed4c","modelId":"muse-spark-1.2","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":34.8453608247423,"warning":null},{"id":"2150abdc6bed127d186f4fb9","modelId":"muse-spark-1.2","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":80.1498127340824,"warning":null},{"id":"e8ebf2449ddbb9b4d37ddf99","modelId":"muse-spark-1.2","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"Muse Spark 1.2 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-2","score":7.07070707070707,"warning":null},{"id":"1585a41209b88f2db63e82f8","modelId":"muse-spark-1.2","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"muse-spark-1-2","configuration":"muse-spark-1-2; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs","score":54.9,"warning":null},{"id":"6ce030d578bd60f3206f0e5d","modelId":"muse-spark-1.3","benchmarkId":"aa-aa-briefcase","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":1589.18,"warning":null},{"id":"34a9bfb4a0aefff342dd0692","modelId":"muse-spark-1.3","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":1483.22,"warning":null},{"id":"6bd6e35126e4ccd32c1da6ca","modelId":"muse-spark-1.3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":83,"warning":null},{"id":"e8808b1d5e98602370d89e65","modelId":"muse-spark-1.3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":83,"warning":null},{"id":"68786c1903a88657f8d41e6f","modelId":"muse-spark-1.3","benchmarkId":"aa-automationbench-aa","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":57.853437865386134,"warning":null},{"id":"a0c9af85c9501b1277d66dcc","modelId":"muse-spark-1.3","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":56.83609003249621,"warning":null},{"id":"b9b9ca830f4b083ec0d3a19a","modelId":"muse-spark-1.3","benchmarkId":"aa-critpt","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":24.8571428571429,"warning":null},{"id":"78635a322a120fc8164e338e","modelId":"muse-spark-1.3","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":26,"warning":null},{"id":"96a191b13b418f3ffe2a1619","modelId":"muse-spark-1.3","benchmarkId":"aa-gdp-pdf","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":26.6,"warning":null},{"id":"5ee44f567df8a617d3b7d8b2","modelId":"muse-spark-1.3","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":24.2,"warning":null},{"id":"48d29f3f8db310a3a1875a50","modelId":"muse-spark-1.3","benchmarkId":"aa-gdpval-aa","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":1703.34,"warning":null},{"id":"bc6505e1b9377dac2b6b31d6","modelId":"muse-spark-1.3","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":1662.34,"warning":null},{"id":"185633bd5d56a99bfbf2d82d","modelId":"muse-spark-1.3","benchmarkId":"aa-gpqa-diamond","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":93.53535353535351,"warning":null},{"id":"33e20049c7e71a9ff1607422","modelId":"muse-spark-1.3","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":94.1414141414141,"warning":null},{"id":"13797d3b6606164f2eb92c9c","modelId":"muse-spark-1.3","benchmarkId":"aa-harvey-lab-aa","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":95.4841511072514,"warning":null},{"id":"ac6602798f51bcec5389b88e","modelId":"muse-spark-1.3","benchmarkId":"aa-humanitys-last-exam","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":48.7025023169602,"warning":null},{"id":"6366fd59f1a721ddd6257c9d","modelId":"muse-spark-1.3","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":47.451343836886004,"warning":null},{"id":"efb8e8efd155fca2f7ea6622","modelId":"muse-spark-1.3","benchmarkId":"aa-mlcr-aa","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":41.1111111111111,"warning":null},{"id":"b8f618b1aaa8468a3b541214","modelId":"muse-spark-1.3","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":82.0231213872832,"warning":null},{"id":"0ee617d3b595752a50038d11","modelId":"muse-spark-1.3","benchmarkId":"aa-omniscience","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":25,"warning":null},{"id":"87a7cbeaeaa3a7635be20077","modelId":"muse-spark-1.3","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":23.1166666666667,"warning":null},{"id":"42853f38a1511935e572b88b","modelId":"muse-spark-1.3","benchmarkId":"aa-omniscience-accuracy","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":43.583333333333336,"warning":null},{"id":"38e66e19ced3d6f24c66d82a","modelId":"muse-spark-1.3","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":41.516666666666666,"warning":null},{"id":"ff504fc7288017403c059f79","modelId":"muse-spark-1.3","benchmarkId":"aa-scicode","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":58.796296296296305,"warning":null},{"id":"2056dd44c9f84527842f5e5b","modelId":"muse-spark-1.3","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":59.7222222222222,"warning":null},{"id":"b339e4aa1d209e870cb52722","modelId":"muse-spark-1.3","benchmarkId":"aa-tau3-banking","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":50.51546391752581,"warning":null},{"id":"540c30f12f3af6a7b01f51b6","modelId":"muse-spark-1.3","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":47.2164948453608,"warning":null},{"id":"0991fa8c74148bd87a523f4c","modelId":"muse-spark-1.3","benchmarkId":"aa-terminalbench-v2-1","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":84.2696629213483,"warning":null},{"id":"05006804f6c11dff2fd76a84","modelId":"muse-spark-1.3","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":85.3932584269663,"warning":null},{"id":"7cd4630bb2973d2baeec9fbf","modelId":"muse-spark-1.3","benchmarkId":"aa-terminalbench-v4-0","level":"max","sourceLabel":"Muse Spark 1.3 (max)","configuration":"Muse Spark 1.3 (max); Model source: https://artificialanalysis.ai/models/muse-spark-1-3","score":33.3333333333333,"warning":null},{"id":"29450743db5e9631e277eae8","modelId":"muse-spark-1.3","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"Muse Spark 1.3 (xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-3-xhigh","score":16.6666666666667,"warning":null},{"id":"3df372e3699dbb72d0107949","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.6666666666667,"warning":null},{"id":"7794c31b12edebaf055cadae","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"2093de0699953b27771c5c06","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":415.52,"warning":null},{"id":"eb0cd457f42770f092325384","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.8686868686869,"warning":null},{"id":"b8891413ad5cd82d8d171e25","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.81927710843374,"warning":null},{"id":"cb4b24a95d446b8f38f48a4f","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.1972789115646,"warning":null},{"id":"be2d9f71ad2fc32c4685a3e8","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":53.179190751445105,"warning":null},{"id":"ac0a28355ceae30603057943","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-57.4333333333333,"warning":null},{"id":"141eae2f30ceb3d7b2bde165","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.2,"warning":null},{"id":"b46e094398644f85af26779b","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":45.3216374269006,"warning":null},{"id":"c9b7eeb3faf1de8c8d016598","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.33333333333333,"warning":null},{"id":"baf677e18985ef29d7904ae8","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Nemotron 3 Nano Omni 30B A3B Reasoning","configuration":"Nemotron 3 Nano Omni 30B A3B Reasoning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.741573033707859,"warning":null},{"id":"330c9ea34b512489404a52c8","modelId":"nemotron-3-ultra","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":6.25,"warning":null},{"id":"174357a19f43211840703ac1","modelId":"nemotron-3-ultra","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":878.22,"warning":null},{"id":"5ab4998706916204907bddaf","modelId":"nemotron-3-ultra","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":79.3333333333333,"warning":null},{"id":"8a53396aab5b755f3de4dee6","modelId":"nemotron-3-ultra","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":2.986349541593992,"warning":null},{"id":"33379178b6158f7ad04022e6","modelId":"nemotron-3-ultra","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":3.14285714285714,"warning":null},{"id":"034db885626e3df3ca80c3b4","modelId":"nemotron-3-ultra","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":28.886899433005077,"warning":null},{"id":"6ea2a53159a414f21eb5080f","modelId":"nemotron-3-ultra","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":5,"warning":null},{"id":"40e8b5d63690240383d7d403","modelId":"nemotron-3-ultra","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":1090.88,"warning":null},{"id":"4cbe7ebbe159a64df52897d4","modelId":"nemotron-3-ultra","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":86.6666666666667,"warning":null},{"id":"697a91584fa0dc97d799e81e","modelId":"nemotron-3-ultra","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":81.719496309162,"warning":null},{"id":"51ea81ebfbd4d73fa92af147","modelId":"nemotron-3-ultra","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":28.405931417979602,"warning":null},{"id":"9896e0be3fe5460d4ed0ea51","modelId":"nemotron-3-ultra","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":81.3605442176871,"warning":null},{"id":"14ac5ca3a74e93eeb0b5d4ea","modelId":"nemotron-3-ultra","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":11.1111111111111,"warning":null},{"id":"5d823713f33e043edf26a0f7","modelId":"nemotron-3-ultra","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":-0.4,"warning":null},{"id":"d3fc36c3f92168bc3ee1be8e","modelId":"nemotron-3-ultra","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":22.583333333333332,"warning":null},{"id":"30b7b7ecf698984e25f319d1","modelId":"nemotron-3-ultra","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":40.2777777777778,"warning":null},{"id":"b9c479a24e769b4d00767391","modelId":"nemotron-3-ultra","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":83.3333333333333,"warning":null},{"id":"25ac32575044be41804c364b","modelId":"nemotron-3-ultra","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":14.2268041237113,"warning":null},{"id":"d3a5cd1a45f812308f2df5f7","modelId":"nemotron-3-ultra","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":36.363636363636395,"warning":null},{"id":"857c5f249a729e596ef2a8e4","modelId":"nemotron-3-ultra","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":53.9325842696629,"warning":null},{"id":"d3e9fc29cd1b8b5326223cc8","modelId":"nemotron-3-ultra","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Nemotron 3 Ultra 550B A55B (Reasoning)","configuration":"Nemotron 3 Ultra 550B A55B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b","score":0.505050505050505,"warning":null},{"id":"d732d01a1a91bbf216a9b322","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":100.39,"warning":null},{"id":"4a17e10223ee1411771a3af5","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":13.3333333333333,"warning":null},{"id":"b2dc7594e6af2cc119bbf07f","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":91,"warning":null},{"id":"5a0f57a5757378689b26c0ef","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":10.6666666666667,"warning":null},{"id":"6942b61505042b6b4b415fa4","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":38,"warning":null},{"id":"740ea85e8bb22f60c115f846","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":0.9714694010433006,"warning":null},{"id":"4725e625f7ee2b6f05fc8d81","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":0,"warning":null},{"id":"04c131410c9c4622e4220c54","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":0.857142857142857,"warning":null},{"id":"105df0aa2225f0561f8563cb","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":1,"warning":null},{"id":"8821961d17d37107b9cc0f93","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":-121.8,"warning":null},{"id":"ee3b105798bbfa2db43304ce","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":438.32,"warning":null},{"id":"dc5659065cf79eedaaa45f2b","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":61.21875,"warning":null},{"id":"303aa21ce366cec63aaa88cc","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":39.8989898989899,"warning":null},{"id":"3bcc88ebddfd31d3a6afbaf9","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":75.6565656565657,"warning":null},{"id":"f396723527d1d08e73b2ade8","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":4.5875810936051895,"warning":null},{"id":"faa9167f4773b2090ba9857d","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":11.3994439295644,"warning":null},{"id":"d2d234d9d2b294ff915e8975","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":37.4829931972789,"warning":null},{"id":"920d7dc6fe4b7a6441efce8b","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":71.08843537414971,"warning":null},{"id":"ecfb7d6f27acde66bc3833ec","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":35.978835978836,"warning":null},{"id":"7cfb3235eb6f77d41014f6bc","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":74.0740740740741,"warning":null},{"id":"d5cf104e5d3166bb18ea1ac1","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":57.8956117021277,"warning":null},{"id":"b34aa90172208f886564ae04","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":79.37998670212771,"warning":null},{"id":"055179e91fb700bc3a6f59f6","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":-69.3,"warning":null},{"id":"691104d3d04d79d51b9cc955","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":-51.5666666666667,"warning":null},{"id":"3b39cae17a85fc9da8893154","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":11.366666666666667,"warning":null},{"id":"3e96872c29bb0036fc03afd9","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":17.299999999999997,"warning":null},{"id":"7592763efd7af6d017ddbac4","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":30.555555555555603,"warning":null},{"id":"6d927cefa7d4ed8898286a1c","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":25.4385964912281,"warning":null},{"id":"afc36157fe035615d4c4dcfb","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":40.935672514619895,"warning":null},{"id":"deb3f5b0ae380724472197f6","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":5.97938144329897,"warning":null},{"id":"36f02769540bd50aba5ce319","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b","score":12.1212121212121,"warning":null},{"id":"b8471a3b510bb8f93eb57bbf","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":13.6363636363636,"warning":null},{"id":"cae5947e36d58b255b600621","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":6.741573033707859,"warning":null},{"id":"72227cbdbda7131737c24853","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)","configuration":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning","score":0,"warning":null},{"id":"b7085be742c2946fbbc31711","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.6666666666667,"warning":null},{"id":"7fe21d4763c029be3e3150d3","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"1e2c2ed5165e11457bea1f14","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":159.11,"warning":null},{"id":"89190aafce97ca2ae081fd7a","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.3131313131313,"warning":null},{"id":"44a97e00847114128f35d524","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.86561631139944,"warning":null},{"id":"8faa35e0975d2edcb8c369dc","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.23129251700681,"warning":null},{"id":"a9e95986995916b5c3500760","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-70.5333333333333,"warning":null},{"id":"74a2cfad0a1a8204637fd1e1","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.566666666666666,"warning":null},{"id":"13b5a452eb77a8d72c5aee9e","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.0701754385965,"warning":null},{"id":"df2ed9679fa5e588c1a56afc","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.81818181818182,"warning":null},{"id":"fc311965ffa7d6bd33acdb98","modelId":"nvidia-nemotron-3-nano-4b-bf16","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"NVIDIA Nemotron 3 Nano 4B","configuration":"NVIDIA Nemotron 3 Nano 4B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.7453183520599302,"warning":null},{"id":"b1f86a0d6ed3aac7cfa5a9f0","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":0,"warning":null},{"id":"e0d8ceb1e0ff885eb209f347","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":1.84365781710914,"warning":null},{"id":"22dcb321de77eebd96aca5cc","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":65.6666666666667,"warning":null},{"id":"5e4aa8b40fd444337c32809b","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":3.7790306947452605,"warning":null},{"id":"73ed6ba64bf2059d55d8be7e","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":3.14285714285714,"warning":null},{"id":"fce7835c797d7abb5d285155","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":23.545210384959713,"warning":null},{"id":"1cc0d1f19c8293a989d67698","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":2.6,"warning":null},{"id":"000865eefbf0bb513f87e318","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":644.41,"warning":null},{"id":"e03108aae6e2496d2303c047","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":80,"warning":null},{"id":"f892e23b0db5ed5a425cd84f","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":20.7599629286376,"warning":null},{"id":"3227135ad004c9ae9505d2ba","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":71.4965986394558,"warning":null},{"id":"fb0bf7feab41fec0f6aa816b","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":1.12994350282486,"warning":null},{"id":"310aba84e1b25c307bc27dbc","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":3.33333333333333,"warning":null},{"id":"c608bf4dd61434f7ad16f374","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":-41.5,"warning":null},{"id":"d8569bb6a64e4b906358c8d9","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":24.316666666666666,"warning":null},{"id":"deb1da1366abb23e09076986","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":36.2268518518519,"warning":null},{"id":"bd4190abebbd6c254565fd40","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":67.83625730994149,"warning":null},{"id":"79e868c3529be4536f58ca91","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":10.3092783505155,"warning":null},{"id":"5803ab6f2e085b119e49725d","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":28.7878787878788,"warning":null},{"id":"9f43288e9868e748c6d12ce8","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":38.5767790262172,"warning":null},{"id":"c8565a66e2745e03531942d4","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Nemotron 3 Super 120B A12B (Reasoning)","configuration":"Nemotron 3 Super 120B A12B (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b","score":0,"warning":null},{"id":"1bbe5f5bd2168c15b29f2aa9","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":508.5,"warning":null},{"id":"21959688eb48ffff3fe84528","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":60.33333333333331,"warning":null},{"id":"af2766360679f1e677876ff9","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.8410069634719541,"warning":null},{"id":"8328d0c67d5667e15aea1472","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"cb59004d5b0f5c683a653e25","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.352730528200535,"warning":null},{"id":"9fa52eeea400c87c7dcac0f2","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":3,"warning":null},{"id":"83ebf96d953e9050e39fd2aa","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":766.89,"warning":null},{"id":"83dba6dbeba046f0f7d51cfa","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.3434343434343,"warning":null},{"id":"f70dadd761ac409f5b15d090","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.5653382761817,"warning":null},{"id":"4ac3635f000bb105bf308376","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.1111111111111098,"warning":null},{"id":"b1606fde6708193b5680178c","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":-17.7166666666667,"warning":null},{"id":"7132c5ebfae4d2f596ff0d23","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.433333333333334,"warning":null},{"id":"685493fcb0926afc1fc64549","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.060185185185205,"warning":null},{"id":"7edad9d658746f2d63c7df37","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.8659793814433,"warning":null},{"id":"b950df4c5b583a803b26d5bb","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.3445692883895,"warning":null},{"id":"328c4ebcaeafd433ae54b333","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Nemotron 3.5 Lightning","configuration":"Nemotron 3.5 Lightning; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/nemotron-3-5-lightning; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.505050505050505,"warning":null},{"id":"feba9b16c718555279f17565","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":26.6666666666667,"warning":null},{"id":"f85bf97903a3efa738c3c09d","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":75,"warning":null},{"id":"c0c3995b50ac95fdbbe5a33a","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":20.6666666666667,"warning":null},{"id":"fccbf930a0cd235301fd9c30","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":41,"warning":null},{"id":"a002c70aa4a84b956eb1d7a4","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":0,"warning":null},{"id":"947b304c37119f3e69f321e1","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":0,"warning":null},{"id":"91ab8f5ba0ad27187e93d250","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":43.9393939393939,"warning":null},{"id":"a3864c283775f7f8392f8896","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":57.1717171717172,"warning":null},{"id":"7c14b2fff22f134a398b1ba6","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":4.2632066728452305,"warning":null},{"id":"39f85a1aa619cb4553d41337","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":5.514365152919369,"warning":null},{"id":"959c553cf61235f930271918","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":25.8503401360544,"warning":null},{"id":"5a93007cac0b3f2e36f76b61","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":31.9047619047619,"warning":null},{"id":"2bb6cd4194cb711be51eeefe","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":34.4973544973545,"warning":null},{"id":"4a13875440065eb6af7f7070","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":69.4179894179894,"warning":null},{"id":"94684e452e66e092d884cf33","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":64.9185505319149,"warning":null},{"id":"fdf6426314faa35ff1e8e3a9","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":75.93085106382979,"warning":null},{"id":"0a091815e44913c3e3f3f3eb","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":44.508670520231206,"warning":null},{"id":"b4d8805b551c7b4e396cd13e","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":52.89017341040459,"warning":null},{"id":"794273354d8e571966e3c3cd","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":-72.2333333333333,"warning":null},{"id":"0afea5460705df6d4ceff65e","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":-64.2333333333333,"warning":null},{"id":"45875b87e9ce3fe9118e9ba9","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":11.916666666666668,"warning":null},{"id":"4aa3f76c32cc1abeba33a5cc","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":14.616666666666667,"warning":null},{"id":"a136762d0e55a8e533046dd3","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":19.2982456140351,"warning":null},{"id":"21db66dacfcddd9994ebaf85","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":21.3450292397661,"warning":null},{"id":"26ebef6866839033a02ce9af","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl","score":0,"warning":null},{"id":"d03e56381bfc8647adb6de5f","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning)","configuration":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning","score":4.545454545454549,"warning":null},{"id":"ce49848989035f224c0a9abe","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":62.33333333333329,"warning":null},{"id":"bf3009a8f08e136dd031ca3e","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":69.6666666666667,"warning":null},{"id":"2a318e72c061446677b7e820","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":24,"warning":null},{"id":"097cde742534d8b869269f2c","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":22.6666666666667,"warning":null},{"id":"33327d7ad7ed35ac4c558fd3","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":0,"warning":null},{"id":"c31a0552226bd1dfa238efb5","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":0,"warning":null},{"id":"8701a0a6fca8a6f69f770e8e","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":55.656565656565704,"warning":null},{"id":"e197387edb4f2e7ff0aa63b0","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":56.969696969697004,"warning":null},{"id":"5e44ddbffbe9cd84adbb0929","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":4.5875810936051895,"warning":null},{"id":"0ebb34a4287e8734ee82c77c","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":4.86561631139944,"warning":null},{"id":"8eda6116a8883034780a1873","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":27.142857142857103,"warning":null},{"id":"9ec18de31c80adfa15c57028","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":27.6190476190476,"warning":null},{"id":"fee2a2c4e302f056e0af9649","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":70.05291005291011,"warning":null},{"id":"14b88287eaf9ef9d92720eb8","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":72.38095238095241,"warning":null},{"id":"091ed4bb386bcf9a5a52226c","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":73.936170212766,"warning":null},{"id":"5afa45ddf4b7f15df4d108f4","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":74.2270611702128,"warning":null},{"id":"0c9b0458dabd028dcd7317d2","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":-57.25,"warning":null},{"id":"dd9503a5b07df03d5dd74bde","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":-41.55,"warning":null},{"id":"efdbda71278dabccbcce9c68","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":9.816666666666666,"warning":null},{"id":"21f2ccc498801a3c11aa79d5","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":11.799999999999999,"warning":null},{"id":"a617ac3d85cbb542b061ea8e","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":23.3918128654971,"warning":null},{"id":"f9acb65ceba2998896351b43","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":21.9298245614035,"warning":null},{"id":"2784590b707e50b89ab8f946","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2","score":0.757575757575758,"warning":null},{"id":"ebdd1011cfb7d6007184a931","modelId":"nvidia-nemotron-nano-9b-v2","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"NVIDIA Nemotron Nano 9B V2 (Reasoning)","configuration":"NVIDIA Nemotron Nano 9B V2 (Reasoning); Model source: https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning","score":1.51515151515152,"warning":null},{"id":"d43df74ab94b7ff5b19c51f5","modelId":"o1","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":65,"warning":null},{"id":"d4b61d84c417f9d0cdad5d5d","modelId":"o1","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.28571428571428603,"warning":null},{"id":"dff08073706a671e10ffd04f","modelId":"o1","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.7474747474747,"warning":null},{"id":"c51ba771a259cf9fda6b04e1","modelId":"o1","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.01,"warning":null},{"id":"a99adc9667d02b7495975f92","modelId":"o1","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.3401360544218,"warning":null},{"id":"95eccd5b098daf7dce5b90a0","modelId":"o1","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.9365079365079,"warning":null},{"id":"7edb809ee87346c119299a36","modelId":"o1","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":97,"warning":null},{"id":"d68b4dbd3f5e0035224e7c76","modelId":"o1","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.0591755319149,"warning":null},{"id":"fe3b117476be77296f685c2b","modelId":"o1","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":-11.05,"warning":null},{"id":"b253a77469ef4f301baed94b","modelId":"o1","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.53333333333333,"warning":null},{"id":"ef4ce5d877f52434b3beb1fc","modelId":"o1","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":62.5730994152047,"warning":null},{"id":"9b71a59f4c3b1e0589de4a70","modelId":"o1","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"o1","configuration":"o1; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o1; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.8787878787879,"warning":null},{"id":"370cf31a2407efae21be583a","modelId":"o3","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.3333333333333,"warning":null},{"id":"f466d671d2eef974ea005b2b","modelId":"o3","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.6666666666667,"warning":null},{"id":"75946bb5200d898db3265c34","modelId":"o3","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.1428571428571401,"warning":null},{"id":"4f70a218b1f6a8fc2114d48e","modelId":"o3","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.7272727272727,"warning":null},{"id":"b3e92ab090534be36366d3ec","modelId":"o3","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.05,"warning":null},{"id":"cd4f93e7f4f1a45735079084","modelId":"o3","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.4285714285714,"warning":null},{"id":"30ee4a241c6f54cb0ca85362","modelId":"o3","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.8465608465608,"warning":null},{"id":"019b987204bf0a37c545c13c","modelId":"o3","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":99.2,"warning":null},{"id":"99c65e088b8907331a5c2554","modelId":"o3","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":85.3474069148936,"warning":null},{"id":"e6f4e33c7c2b7b4ca2e20e28","modelId":"o3","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.0578034682081,"warning":null},{"id":"350484fd270e9192ba0525d4","modelId":"o3","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":-15.55,"warning":null},{"id":"7cf10f4304e8d80bbcf66d39","modelId":"o3","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.56666666666666,"warning":null},{"id":"9a1204eb9a9a16442ef47947","modelId":"o3","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.7017543859649,"warning":null},{"id":"001226139bfffd4e21b870af","modelId":"o3","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"o3","configuration":"o3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.121212121212096,"warning":null},{"id":"d7e49807f538aef93f8c591f","modelId":"o3","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"o3 (High)","configuration":"o3 (High); Source model ID: o3-2025-04-16-high; 120 tasks","score":6.529999999999999,"warning":null},{"id":"c4c43e9a8ca07f6c7e48de89","modelId":"o3","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"o3 (Low)","configuration":"o3 (Low); Source model ID: o3-2025-04-16-low; 120 tasks","score":1.9900000000000002,"warning":null},{"id":"44ec3c5d0da4e3f62912c05f","modelId":"o3","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"o3 (Medium)","configuration":"o3 (Medium); Source model ID: o3-2025-04-16-medium; 120 tasks","score":2.98,"warning":null},{"id":"de6fe228603e9238b659ea7d","modelId":"o3","benchmarkId":"livecode-generationpass1","level":"high","sourceLabel":"O3 (High)","configuration":"O3 (High); Exact source model: o3__high; 454 tasks","score":75.8,"warning":null},{"id":"01a156003da2d47b7c81895a","modelId":"o3-mini","benchmarkId":"aa-aa-briefcase","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":161.06,"warning":null},{"id":"0e677a3227e6bacc4a0e9a40","modelId":"o3-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":43,"warning":null},{"id":"2d80aa65c5a1e66963cd6340","modelId":"o3-mini","benchmarkId":"aa-automationbench-aa","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":0.5301828617801994,"warning":null},{"id":"c4250ae81639657e77c36aaf","modelId":"o3-mini","benchmarkId":"aa-critpt","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":0.28571428571428603,"warning":null},{"id":"e5b3e40b7466bcdf13bd150c","modelId":"o3-mini","benchmarkId":"aa-gdp-pdf","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":2,"warning":null},{"id":"2841993d80a9999de9f6ee7f","modelId":"o3-mini","benchmarkId":"aa-gdpval-aa","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":420.79,"warning":null},{"id":"42f4c2c9076d696f07dc6783","modelId":"o3-mini","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":77.27272727272731,"warning":null},{"id":"811d9c240ea23b82e185a589","modelId":"o3-mini","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"o3-mini","configuration":"o3-mini; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.8484848484848,"warning":null},{"id":"4a7f79808eefcb014ec3f0be","modelId":"o3-mini","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":12.04,"warning":null},{"id":"e161b5a9b646a096149330a7","modelId":"o3-mini","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"o3-mini","configuration":"o3-mini; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.91,"warning":null},{"id":"6a9234b7c969c2c1abb86d31","modelId":"o3-mini","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":67.14285714285711,"warning":null},{"id":"6d65babdfac67d23efa92d48","modelId":"o3-mini","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":73.4391534391534,"warning":null},{"id":"318e34735b7b00c4d11a9a09","modelId":"o3-mini","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"o3-mini","configuration":"o3-mini; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.7460317460317,"warning":null},{"id":"745e69c691f9b694b7c9353f","modelId":"o3-mini","benchmarkId":"aa-math-500","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":98.4666666666667,"warning":null},{"id":"b03c9376d3f09d3c80e63a54","modelId":"o3-mini","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"o3-mini","configuration":"o3-mini; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":97.3333333333333,"warning":null},{"id":"00d8df98308d9c695c029966","modelId":"o3-mini","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":80.1944813829787,"warning":null},{"id":"e266c73c6ec784e58caaf44a","modelId":"o3-mini","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"o3-mini","configuration":"o3-mini; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.05585106382979,"warning":null},{"id":"db1badd09c0ec2742a1bda68","modelId":"o3-mini","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":-42.5666666666667,"warning":null},{"id":"8d5a35515e13598e754d8782","modelId":"o3-mini","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":21.266666666666666,"warning":null},{"id":"fdf870defc76ce206427d252","modelId":"o3-mini","benchmarkId":"aa-scicode","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":42.8240740740741,"warning":null},{"id":"9939fced55db051e5e0be0c6","modelId":"o3-mini","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":31.2865497076023,"warning":null},{"id":"19eb94c3b4a5578e45bc7056","modelId":"o3-mini","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"o3-mini","configuration":"o3-mini; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.6549707602339,"warning":null},{"id":"f5d59a1795d09f33dd6e3fee","modelId":"o3-mini","benchmarkId":"aa-tau3-banking","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":5.1546391752577305,"warning":null},{"id":"14aa700efe22f08ce992bfb4","modelId":"o3-mini","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":6.06060606060606,"warning":null},{"id":"4da7c16ca683432d6e1cd5ba","modelId":"o3-mini","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"o3-mini","configuration":"o3-mini; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.81818181818182,"warning":null},{"id":"6c0182a63d8db78a905b0380","modelId":"o3-mini","benchmarkId":"aa-terminalbench-v2-1","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":4.49438202247191,"warning":null},{"id":"06585d01215ca9d0bce0d3f5","modelId":"o3-mini","benchmarkId":"aa-terminalbench-v4-0","level":"high","sourceLabel":"o3-mini (high)","configuration":"o3-mini (high); Model source: https://artificialanalysis.ai/models/o3-mini-high","score":0,"warning":null},{"id":"c2c3b8b661de8636e2ceca83","modelId":"o3-mini","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"o3-mini (High)","configuration":"o3-mini (High); Source model ID: o3-mini-2025-01-31-high; 120 tasks","score":2.9899999999999998,"warning":null},{"id":"78ba06f11057b6bec4542c33","modelId":"o3-mini","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"o3-mini (Low)","configuration":"o3-mini (Low); Source model ID: o3-mini-2025-01-31-low; 120 tasks","score":0,"warning":null},{"id":"e76fe3fd7aff227cd9253390","modelId":"o3-mini","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"o3-mini (Medium)","configuration":"o3-mini (Medium); Source model ID: o3-mini-2025-01-31-medium; 120 tasks","score":2.08,"warning":null},{"id":"bd98f3407d228d7b34d15a3b","modelId":"o3-pro","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"o3-pro","configuration":"o3-pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/o3-pro; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.5454545454545,"warning":null},{"id":"549730e49987d6154a62d579","modelId":"o3-pro","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"o3-Pro (High)","configuration":"o3-Pro (High); Source model ID: o3-pro-2025-06-10-high; 120 tasks","score":4.859999999999999,"warning":null},{"id":"342bab39cacc26dd8a82dd79","modelId":"o3-pro","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"o3-Pro (Low)","configuration":"o3-Pro (Low); Source model ID: o3-pro-2025-06-10-low; 120 tasks","score":2.0500000000000003,"warning":null},{"id":"f5bae5777f5b932bda30b31f","modelId":"o3-pro","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"o3-Pro (Medium)","configuration":"o3-Pro (Medium); Source model ID: o3-pro-2025-06-10-medium; 120 tasks","score":1.94,"warning":null},{"id":"db9246e68971e76beeba26d2","modelId":"o4-mini","benchmarkId":"aa-aime-2025","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":90.6666666666667,"warning":null},{"id":"dcb3ed7e008063d590801660","modelId":"o4-mini","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":61,"warning":null},{"id":"efe3ee5e510a1f9d9309239d","modelId":"o4-mini","benchmarkId":"aa-critpt","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":0.571428571428571,"warning":null},{"id":"0129f1e1a13aeb775a53a55c","modelId":"o4-mini","benchmarkId":"aa-gpqa-diamond","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":78.3838383838384,"warning":null},{"id":"77b640461cfce8756b234629","modelId":"o4-mini","benchmarkId":"aa-humanitys-last-exam","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":16.5430954587581,"warning":null},{"id":"48b638db61a973babc2ae6b7","modelId":"o4-mini","benchmarkId":"aa-ifbench","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":68.7074829931973,"warning":null},{"id":"2012c98b7c0b198f7fca6c55","modelId":"o4-mini","benchmarkId":"aa-livecodebench","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":85.9259259259259,"warning":null},{"id":"1c31fb5e1455b4c4ab80556f","modelId":"o4-mini","benchmarkId":"aa-math-500","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":98.8666666666667,"warning":null},{"id":"2116de3638350f5f74312fb0","modelId":"o4-mini","benchmarkId":"aa-mmlu-pro","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":83.1948138297872,"warning":null},{"id":"ed9b2508389eebf3c69deacf","modelId":"o4-mini","benchmarkId":"aa-mmmu-pro","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":69.2485549132948,"warning":null},{"id":"ed11d2a6911024075e30eda3","modelId":"o4-mini","benchmarkId":"aa-omniscience","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":-35.7,"warning":null},{"id":"5d14e1f9efd0488dbcec0d2f","modelId":"o4-mini","benchmarkId":"aa-omniscience-accuracy","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":24.8,"warning":null},{"id":"957e1e7000b2a0aa69fbb665","modelId":"o4-mini","benchmarkId":"aa-tau2-bench","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":55.5555555555556,"warning":null},{"id":"7e42ac7bd5a7610c724d7104","modelId":"o4-mini","benchmarkId":"aa-terminalbench-hard","level":"high","sourceLabel":"o4-mini (high)","configuration":"o4-mini (high); Model source: https://artificialanalysis.ai/models/o4-mini","score":15.151515151515198,"warning":null},{"id":"e74df9fbfd59b581eb76ffa2","modelId":"o4-mini","benchmarkId":"arc-v2semiprivate","level":"high","sourceLabel":"o4-mini (High)","configuration":"o4-mini (High); Source model ID: o4-mini-2025-04-16-high; 120 tasks","score":6.11,"warning":null},{"id":"a03ef69f5f0bf9f19a64b6c1","modelId":"o4-mini","benchmarkId":"arc-v2semiprivate","level":"low","sourceLabel":"o4-mini (Low)","configuration":"o4-mini (Low); Source model ID: o4-mini-2025-04-16-low; 120 tasks","score":1.67,"warning":null},{"id":"904517858e9c5b0473e556b3","modelId":"o4-mini","benchmarkId":"arc-v2semiprivate","level":"medium","sourceLabel":"o4-mini (Medium)","configuration":"o4-mini (Medium); Source model ID: o4-mini-2025-04-16-medium; 120 tasks","score":2.36,"warning":null},{"id":"ee9d1ca8d2407e02d504ac6b","modelId":"o4-mini","benchmarkId":"livecode-generationpass1","level":"high","sourceLabel":"O4-Mini (High)","configuration":"O4-Mini (High); Exact source model: o4-mini__high; 454 tasks","score":80.2,"warning":null},{"id":"c16742f35a5ca0f1da2cd5d9","modelId":"o4-mini","benchmarkId":"livecode-generationpass1","level":"low","sourceLabel":"O4-Mini (Low)","configuration":"O4-Mini (Low); Exact source model: o4-mini__low; 454 tasks","score":65.9,"warning":null},{"id":"dbd3c0c14e4d3b745599aed7","modelId":"o4-mini","benchmarkId":"livecode-generationpass1","level":"medium","sourceLabel":"O4-Mini (Medium)","configuration":"O4-Mini (Medium); Exact source model: o4-mini__medium; 454 tasks","score":74.2,"warning":null},{"id":"77b72d8bb8f6229c4935bd1d","modelId":"phi-4","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":18,"warning":null},{"id":"7913c6e2413a96102bbbf1fe","modelId":"phi-4","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"834342d113eaeacdec6c68c2","modelId":"phi-4","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"c45844e7e930f528caf96218","modelId":"phi-4","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":57.4747474747475,"warning":null},{"id":"92a3672a2fcdd9eae2cfe4c8","modelId":"phi-4","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.7600000000000002,"warning":null},{"id":"70dd1ef196043632b7c37a03","modelId":"phi-4","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.5374149659864,"warning":null},{"id":"f2fa14f24036f5ed63850347","modelId":"phi-4","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.068783068783098,"warning":null},{"id":"b1300da3198b950627b64868","modelId":"phi-4","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":81,"warning":null},{"id":"e87a2d3e2af83fbba103ecc7","modelId":"phi-4","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.4428191489362,"warning":null},{"id":"d4d5188cfd91b9b6ddb85ec5","modelId":"phi-4","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":-55.7,"warning":null},{"id":"aff564f7946147cb44a15141","modelId":"phi-4","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.066666666666666,"warning":null},{"id":"68eef27c9393c82acd930591","modelId":"phi-4","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"a0d8027ad98e252733a703ca","modelId":"phi-4","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Phi-4","configuration":"Phi-4; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.78787878787879,"warning":null},{"id":"516823481eb1495f3fb3c99c","modelId":"phi-4-mini-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.66666666666667,"warning":null},{"id":"601f36f2404c745b7bc714e7","modelId":"phi-4-mini-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.333333333333298,"warning":null},{"id":"ab4cc6c2aa36c216f8568f92","modelId":"phi-4-mini-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"a2627d43541d47421d317811","modelId":"phi-4-mini-instruct","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":-171.32,"warning":null},{"id":"5438058f26b61c57fa0f9afc","modelId":"phi-4-mini-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.1313131313131,"warning":null},{"id":"4d6bf305ef56bc9d7d14e527","modelId":"phi-4-mini-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.45,"warning":null},{"id":"f1959c33d56b49b87d365a30","modelId":"phi-4-mini-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.0884353741497,"warning":null},{"id":"cad43079054208b6d9bfa144","modelId":"phi-4-mini-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.592592592592599,"warning":null},{"id":"b9dfce1492ec029021a05b9e","modelId":"phi-4-mini-instruct","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.6,"warning":null},{"id":"8aa58d9564291e79f8c7d5aa","modelId":"phi-4-mini-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.484375,"warning":null},{"id":"ec4c88a12f8e0d0998cc68b9","modelId":"phi-4-mini-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":-61.0833333333333,"warning":null},{"id":"70e69f2115f632139a54d1c0","modelId":"phi-4-mini-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.5,"warning":null},{"id":"c13bc87ea7fbb9edee07b054","modelId":"phi-4-mini-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.18713450292398,"warning":null},{"id":"64dbb96bbf3ee55255c6a592","modelId":"phi-4-mini-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"53b7d3d06cae0753bfaa177b","modelId":"phi-4-mini-instruct","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Phi-4 Mini Instruct","configuration":"Phi-4 Mini Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-mini; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.374531835205993,"warning":null},{"id":"be0d629d53023aac889d0050","modelId":"phi-4-multimodal-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Phi-4 Multimodal Instruct","configuration":"Phi-4 Multimodal Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-multimodal; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.5151515151515,"warning":null},{"id":"5e56b10f487f5015dd377634","modelId":"phi-4-multimodal-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Phi-4 Multimodal Instruct","configuration":"Phi-4 Multimodal Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-multimodal; Mode from evaluator isReasoning metadata; effort budget not specified","score":5,"warning":null},{"id":"1c00cc4d194123d3e4240049","modelId":"phi-4-multimodal-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Phi-4 Multimodal Instruct","configuration":"Phi-4 Multimodal Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-multimodal; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.1216931216931,"warning":null},{"id":"9b113a9a9d3b6af3846f819a","modelId":"phi-4-multimodal-instruct","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Phi-4 Multimodal Instruct","configuration":"Phi-4 Multimodal Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-multimodal; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.2666666666667,"warning":null},{"id":"88f07e63051ff123b88335b7","modelId":"phi-4-multimodal-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Phi-4 Multimodal Instruct","configuration":"Phi-4 Multimodal Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-multimodal; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.545545212766,"warning":null},{"id":"10aaef8ddcae5e8c1c02ab70","modelId":"phi-4-multimodal-instruct","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Phi-4 Multimodal Instruct","configuration":"Phi-4 Multimodal Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/phi-4-multimodal; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.5086705202312,"warning":null},{"id":"95791dc88f64b23b16d4019b","modelId":"pixtral-large-2411","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.33333333333333,"warning":null},{"id":"528da2e0681c24dea179b207","modelId":"pixtral-large-2411","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.5050505050505,"warning":null},{"id":"0f3e5bc4908fb6b8e1788d00","modelId":"pixtral-large-2411","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.8000000000000003,"warning":null},{"id":"52b14f5c6812c2e2fb14b98f","modelId":"pixtral-large-2411","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.4897959183673,"warning":null},{"id":"cd0a839399405ae15ba9139d","modelId":"pixtral-large-2411","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.137566137566097,"warning":null},{"id":"2a7f996917775f67ba770d2f","modelId":"pixtral-large-2411","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.39999999999999,"warning":null},{"id":"d563ff92ab0b6ba9cff379b5","modelId":"pixtral-large-2411","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.1130319148936,"warning":null},{"id":"eb614b4b073a151ea844b8a5","modelId":"pixtral-large-2411","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.5780346820809,"warning":null},{"id":"f3c6fe94a03132a6f2f3db5f","modelId":"pixtral-large-2411","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Pixtral Large","configuration":"Pixtral Large; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/pixtral-large-2411; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.5497076023392,"warning":null},{"id":"79ac39c316bced8f0d7c2cb9","modelId":"qwen-3.8-max","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":1387.89,"warning":null},{"id":"57435d7deb3cdff15c2a3a8b","modelId":"qwen-3.8-max","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.3333333333333,"warning":null},{"id":"5c09e4e33bd17b0d5c324b60","modelId":"qwen-3.8-max","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":49.23210407553669,"warning":null},{"id":"79ab32eaa9b651d3342a99ff","modelId":"qwen-3.8-max","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":20,"warning":null},{"id":"c03ba8504722b0e530cc22b0","modelId":"qwen-3.8-max","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.200000000000003,"warning":null},{"id":"074c885729617e4a79bc8333","modelId":"qwen-3.8-max","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":1630.39,"warning":null},{"id":"d96d19fdb68c550c1214c0cc","modelId":"qwen-3.8-max","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":92.7272727272727,"warning":null},{"id":"e9d1d3caf6ce2b25dfbb864f","modelId":"qwen-3.8-max","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.0491195551437,"warning":null},{"id":"15fa3a1b83adaff4e8f742dc","modelId":"qwen-3.8-max","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.4444444444444,"warning":null},{"id":"d70d4d6859dba0c566beeb24","modelId":"qwen-3.8-max","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.3121387283237,"warning":null},{"id":"58633d857fd008646f1cc6eb","modelId":"qwen-3.8-max","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.4,"warning":null},{"id":"89c264b8b197f4d77c71a2c6","modelId":"qwen-3.8-max","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.85,"warning":null},{"id":"6d3819ebea45c3c63a94d80f","modelId":"qwen-3.8-max","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":53.2407407407407,"warning":null},{"id":"3ed822dd05e4a59aae023d79","modelId":"qwen-3.8-max","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.340206185567006,"warning":null},{"id":"b38697af9ba8ab047240c165","modelId":"qwen-3.8-max","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.2734082397004,"warning":null},{"id":"401aa39daad5e621da7b61ae","modelId":"qwen-3.8-max","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.8 Max","configuration":"Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.6868686868687,"warning":null},{"id":"fdf7a8eca4003c72a2a46e18","modelId":"qwen-3.8-max","benchmarkId":"deepswe-minisweagent","level":"xhigh","sourceLabel":"qwen3-8-max","configuration":"qwen3-8-max; Reported effort: xhigh; 113 unique tasks; 449 attempts; 4 runs","score":57.5,"warning":null},{"id":"e07d9dd5005dfa0df02827b8","modelId":"qwen3-0.6b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":10.3333333333333,"warning":null},{"id":"a6f7a5f79bbca4f2a67412d9","modelId":"qwen3-0.6b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":18,"warning":null},{"id":"c8d0f96fa682deeb06e51740","modelId":"qwen3-0.6b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":0,"warning":null},{"id":"ecde6783ec0d47e1bf98a46a","modelId":"qwen3-0.6b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":0,"warning":null},{"id":"b338841b63f737ffb17ed7e0","modelId":"qwen3-0.6b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":0,"warning":null},{"id":"902940590320d8648dca2883","modelId":"qwen3-0.6b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":0,"warning":null},{"id":"f04fd1b531b951f250617193","modelId":"qwen3-0.6b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":23.1313131313131,"warning":null},{"id":"3d1a9de8bbd963f3c5f6bf0d","modelId":"qwen3-0.6b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":23.9393939393939,"warning":null},{"id":"90e7d8ad72bd6576a81f42eb","modelId":"qwen3-0.6b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":4.93,"warning":null},{"id":"6518f5de94545adfe1985361","modelId":"qwen3-0.6b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":5.64,"warning":null},{"id":"230731584c91a733879819a5","modelId":"qwen3-0.6b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":21.904761904761898,"warning":null},{"id":"a6bbd08d320ee6b9dfd559fd","modelId":"qwen3-0.6b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":23.3333333333333,"warning":null},{"id":"55a17c98e627b355cd8b17da","modelId":"qwen3-0.6b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":7.3015873015873005,"warning":null},{"id":"0c6f9d11fcb4e03bd1b8a9a7","modelId":"qwen3-0.6b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":12.0634920634921,"warning":null},{"id":"20398efbf3c87c56cf33356f","modelId":"qwen3-0.6b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":52.066666666666706,"warning":null},{"id":"8e582fa9a22661b9a0279e7a","modelId":"qwen3-0.6b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":75,"warning":null},{"id":"a370fde9d0ef2c43e306e7f1","modelId":"qwen3-0.6b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":23.0718085106383,"warning":null},{"id":"9fa5e0ad520b1ed9244765c2","modelId":"qwen3-0.6b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":34.682513297872305,"warning":null},{"id":"607485fd1a1b0b822e375d3e","modelId":"qwen3-0.6b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":-84.95,"warning":null},{"id":"7427f5729e938d7772017aa2","modelId":"qwen3-0.6b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":-78.85,"warning":null},{"id":"b50bf9a788cc1febbbb1372a","modelId":"qwen3-0.6b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":4.583333333333333,"warning":null},{"id":"692d1a2005d56e466b6dc93b","modelId":"qwen3-0.6b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":6.333333333333334,"warning":null},{"id":"aaf8eb92ad1848d2c667404a","modelId":"qwen3-0.6b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":14.619883040935699,"warning":null},{"id":"62476ba134bc76ca975eaf3c","modelId":"qwen3-0.6b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":21.052631578947402,"warning":null},{"id":"5cc385d16cc1b35f2bcc4b90","modelId":"qwen3-0.6b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 0.6B (Non-reasoning)","configuration":"Qwen3 0.6B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct","score":0,"warning":null},{"id":"2d2875437a15ced44a23ebcc","modelId":"qwen3-0.6b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 0.6B (Reasoning)","configuration":"Qwen3 0.6B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-0.6b-instruct-reasoning","score":0,"warning":null},{"id":"f0903b0785448402e3ee7b14","modelId":"qwen3-1.7b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":7.33333333333333,"warning":null},{"id":"1708d3fe7d21b8dc9194f8c4","modelId":"qwen3-1.7b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":38.6666666666667,"warning":null},{"id":"8b2f14005445f5c569f1b1ce","modelId":"qwen3-1.7b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":0,"warning":null},{"id":"6081c63272fd15a08492c8db","modelId":"qwen3-1.7b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":0,"warning":null},{"id":"fd4f239d936984cd38e77d8c","modelId":"qwen3-1.7b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":0,"warning":null},{"id":"ee141c0067f8a08b74460ce2","modelId":"qwen3-1.7b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":0,"warning":null},{"id":"0d1130f0b8f0226c88c62a1e","modelId":"qwen3-1.7b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":48.839285714285715,"warning":null},{"id":"5f5f56834853b82731dea301","modelId":"qwen3-1.7b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":28.282828282828298,"warning":null},{"id":"5605706863518eb467d8a1b5","modelId":"qwen3-1.7b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":35.5555555555556,"warning":null},{"id":"8661b817f3af2404661a7e11","modelId":"qwen3-1.7b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":5.319999999999999,"warning":null},{"id":"5392dc4a9cc4b181f5b920c6","modelId":"qwen3-1.7b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":4.64,"warning":null},{"id":"a1f40f1a67da3871ed644d2c","modelId":"qwen3-1.7b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":21.0884353741497,"warning":null},{"id":"88058002752a6680711097c0","modelId":"qwen3-1.7b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":26.8707482993197,"warning":null},{"id":"a6d45937d0d15bb4efa4365c","modelId":"qwen3-1.7b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":12.592592592592599,"warning":null},{"id":"a87339e0e9504b36ddb6bded","modelId":"qwen3-1.7b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":30.7936507936508,"warning":null},{"id":"50e7de8cdf0b7ec58dc21ada","modelId":"qwen3-1.7b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":71.7333333333333,"warning":null},{"id":"f2145165c64ee568b19fe04a","modelId":"qwen3-1.7b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":89.4,"warning":null},{"id":"30e97a4e868b3d4ca68973be","modelId":"qwen3-1.7b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":41.057180851063805,"warning":null},{"id":"c412281a2b4367841d9fc1eb","modelId":"qwen3-1.7b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":56.9730718085106,"warning":null},{"id":"460ee126fa722ac88fa60ce9","modelId":"qwen3-1.7b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":-84.0833333333333,"warning":null},{"id":"33f988c4c7a2096720a36eb5","modelId":"qwen3-1.7b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":-77.5333333333333,"warning":null},{"id":"82004cae536a8489b3f16bc2","modelId":"qwen3-1.7b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":6.916666666666667,"warning":null},{"id":"b545a2bd1e66b5dcad42acc3","modelId":"qwen3-1.7b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":8.866666666666667,"warning":null},{"id":"5782bd6d71560bdef6e6bbf0","modelId":"qwen3-1.7b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":21.6374269005848,"warning":null},{"id":"f7bac8d61f92b0d58d694350","modelId":"qwen3-1.7b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":26.023391812865498,"warning":null},{"id":"7a6bdbbd5bb164a640d8cff1","modelId":"qwen3-1.7b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 1.7B (Non-reasoning)","configuration":"Qwen3 1.7B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct","score":0,"warning":null},{"id":"8631ae15df88ea157c982d73","modelId":"qwen3-1.7b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 1.7B (Reasoning)","configuration":"Qwen3 1.7B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-1.7b-instruct-reasoning","score":0,"warning":null},{"id":"c200f8f5974cced91b94c3a7","modelId":"qwen3-14b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":0,"warning":null},{"id":"7823070fce74572c14440227","modelId":"qwen3-14b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":57.99999999999999,"warning":null},{"id":"3309e13df52fd1fabb19ab86","modelId":"qwen3-14b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":55.6666666666667,"warning":null},{"id":"360c4369d2880bd3f33bf48d","modelId":"qwen3-14b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":0,"warning":null},{"id":"93da3ff3c5d7b1bff4c94ecb","modelId":"qwen3-14b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":0,"warning":null},{"id":"3b2a114e7d0f60358dc89582","modelId":"qwen3-14b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":0.19111706206154658,"warning":null},{"id":"5bafcc8253fd4f179cd575bd","modelId":"qwen3-14b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":0,"warning":null},{"id":"22963f5bec954903994c9380","modelId":"qwen3-14b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":0,"warning":null},{"id":"28e79ab1e630d682cf1391f6","modelId":"qwen3-14b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":1.2,"warning":null},{"id":"19b97b3a583459ff567123aa","modelId":"qwen3-14b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":187.72,"warning":null},{"id":"76b7eda2e03b9fb81d741935","modelId":"qwen3-14b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":46.969696969697,"warning":null},{"id":"e62d0d2d9690c57703bf9f13","modelId":"qwen3-14b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":60.4040404040404,"warning":null},{"id":"fff6cdef363e6e229f008d13","modelId":"qwen3-14b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":4.09,"warning":null},{"id":"29501eeeebecd801dc346bab","modelId":"qwen3-14b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":4.53,"warning":null},{"id":"c6cac11306b7bc7f25813687","modelId":"qwen3-14b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":23.9455782312925,"warning":null},{"id":"c9662b1cbc42cb80f1003cb1","modelId":"qwen3-14b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":40.5442176870748,"warning":null},{"id":"4a6b0f3481ccc7e6d3e485b4","modelId":"qwen3-14b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":28.042328042328002,"warning":null},{"id":"d182d825eeccc745161b2067","modelId":"qwen3-14b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":52.27513227513229,"warning":null},{"id":"f92bf192d6248fe1b4e85427","modelId":"qwen3-14b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":87.1333333333333,"warning":null},{"id":"41d90092001ad63411e08f39","modelId":"qwen3-14b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":96.1333333333333,"warning":null},{"id":"30b278ac1c8c5464b1a1def2","modelId":"qwen3-14b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":67.4617686170213,"warning":null},{"id":"f1ac22cc2380f41a90cbfc68","modelId":"qwen3-14b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":77.3769946808511,"warning":null},{"id":"f9876ccbd46960970f8661c0","modelId":"qwen3-14b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":-66.6666666666667,"warning":null},{"id":"fffa4d922bb3d13549db3532","modelId":"qwen3-14b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":-48.95,"warning":null},{"id":"6c21071980d804a1d67a0c8c","modelId":"qwen3-14b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":13.333333333333334,"warning":null},{"id":"ea5ca53936049bd3f26c2477","modelId":"qwen3-14b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":15.283333333333331,"warning":null},{"id":"a32d713ac22ff457128d16eb","modelId":"qwen3-14b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":30.6712962962963,"warning":null},{"id":"05dcd8e868462f666322c651","modelId":"qwen3-14b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":32.1637426900585,"warning":null},{"id":"9cf6758bbc1a1642912303d1","modelId":"qwen3-14b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":34.5029239766082,"warning":null},{"id":"7f1d3dd2bf9d082e2778499a","modelId":"qwen3-14b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":5.56701030927835,"warning":null},{"id":"57f6dbe626d153af997eff0b","modelId":"qwen3-14b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 14B (Non-reasoning)","configuration":"Qwen3 14B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct","score":5.3030303030303,"warning":null},{"id":"2ce50946464c3e30979c50bf","modelId":"qwen3-14b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":3.78787878787879,"warning":null},{"id":"7eee7a8e12e744a002d4d6b4","modelId":"qwen3-14b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":4.8689138576779,"warning":null},{"id":"1b5bf342de1a14490bce8c1a","modelId":"qwen3-14b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3 14B (Reasoning)","configuration":"Qwen3 14B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-14b-instruct-reasoning","score":0,"warning":null},{"id":"38375a3f39d92c5ad2706da2","modelId":"qwen3-235b-a22b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":23.6666666666667,"warning":null},{"id":"89305b27a86a0ce63a7e4eb8","modelId":"qwen3-235b-a22b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":82,"warning":null},{"id":"56d76f45737dce7a63a667ff","modelId":"qwen3-235b-a22b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":0,"warning":null},{"id":"14f9f716a2a328d472ca21e0","modelId":"qwen3-235b-a22b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":0,"warning":null},{"id":"ca93a3563807fd6a9ff50462","modelId":"qwen3-235b-a22b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":0,"warning":null},{"id":"e658e6c4bd06b5c59d0cdf8b","modelId":"qwen3-235b-a22b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":0,"warning":null},{"id":"ca162e62aabc277e7d0ea215","modelId":"qwen3-235b-a22b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":61.313131313131294,"warning":null},{"id":"c361e8d72495bb5786b6cf90","modelId":"qwen3-235b-a22b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":70,"warning":null},{"id":"8fb4c5a3c327a127ebc0ebc9","modelId":"qwen3-235b-a22b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":4.19,"warning":null},{"id":"cf462f7e796944884abc14f1","modelId":"qwen3-235b-a22b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":10.979999999999999,"warning":null},{"id":"839df9c48331bc134df3997d","modelId":"qwen3-235b-a22b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":36.5986394557823,"warning":null},{"id":"b0696a5cc76427177558d015","modelId":"qwen3-235b-a22b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":38.7074829931973,"warning":null},{"id":"ab7dc27978537cbe461952da","modelId":"qwen3-235b-a22b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":34.285714285714306,"warning":null},{"id":"87125f56c97261ce790af1db","modelId":"qwen3-235b-a22b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":62.2222222222222,"warning":null},{"id":"a5ec4ea7bfb7ef8568384a61","modelId":"qwen3-235b-a22b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":90.2,"warning":null},{"id":"43cf687682a8eb0a638a3c45","modelId":"qwen3-235b-a22b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":93,"warning":null},{"id":"fe9af6c837da0b3d9cf4a593","modelId":"qwen3-235b-a22b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":76.2134308510638,"warning":null},{"id":"227ee0acf1c6c720d1350ecf","modelId":"qwen3-235b-a22b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":82.7958776595745,"warning":null},{"id":"c8b44554d63181fae5555e52","modelId":"qwen3-235b-a22b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":-52.3833333333333,"warning":null},{"id":"c34a248fd9868cde08c5ce20","modelId":"qwen3-235b-a22b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":-44.7,"warning":null},{"id":"69f9f3d7ea24015d72835b85","modelId":"qwen3-235b-a22b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":18.566666666666666,"warning":null},{"id":"860f80781817eb047ddb5ff5","modelId":"qwen3-235b-a22b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":18.53333333333333,"warning":null},{"id":"0326ce95ca6eb85d64c1291b","modelId":"qwen3-235b-a22b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":27.192982456140403,"warning":null},{"id":"5ce73290decba9279d8cafa3","modelId":"qwen3-235b-a22b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":23.9766081871345,"warning":null},{"id":"b923b18effc8abc789063841","modelId":"qwen3-235b-a22b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B (Non-reasoning)","configuration":"Qwen3 235B A22B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct","score":6.06060606060606,"warning":null},{"id":"1a1ddf3972ddca61d88d99d3","modelId":"qwen3-235b-a22b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 235B A22B (Reasoning)","configuration":"Qwen3 235B A22B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-reasoning","score":6.06060606060606,"warning":null},{"id":"d77b602a8a35d0a4a648dd95","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.6666666666667,"warning":null},{"id":"67ad2e1e4f3abbfc96fd72d0","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.900000000000006,"warning":null},{"id":"1d7d03c896b07879689bc033","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"1622a07edd5343e87803e57a","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.2525252525253,"warning":null},{"id":"d64fc0c5fd25c6f3f2839386","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.1214087117702,"warning":null},{"id":"02dd73192a322d1d0f8c6c1d","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.0544217687075,"warning":null},{"id":"f1461f99f24065e4929bc6f5","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.380952380952394,"warning":null},{"id":"d34742eb5d738ba73157d238","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":98,"warning":null},{"id":"e8399cdab1190c86e4e1550d","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.7875664893617,"warning":null},{"id":"5f17f8f143ab442b52c0ca93","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":-43.9833333333333,"warning":null},{"id":"c7456329253fb027797f510f","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.73333333333333,"warning":null},{"id":"70d0cd044393c24c57a06146","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.3333333333333,"warning":null},{"id":"9b42443b66c734d0f2d7c944","modelId":"qwen3-235b-a22b-instruct-2507","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 235B A22B 2507 Instruct","configuration":"Qwen3 235B A22B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.151515151515198,"warning":null},{"id":"6d1a4f33583a5e4cf8e7a06b","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":189.93,"warning":null},{"id":"5ecc084f491a729e9b7a74c9","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":91,"warning":null},{"id":"3a5ed8eea3db9089c7dbc5ff","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":72,"warning":null},{"id":"bb8fa7dd28b53b28a7ead28e","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":2.1540366122608225,"warning":null},{"id":"c1990682da03247d86412c31","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":0,"warning":null},{"id":"1a399e93d52acd969298026c","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":4.8,"warning":null},{"id":"16c9acfa6c591aba2ddf7c2f","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":495.33,"warning":null},{"id":"0558174eaf2fcd898108553e","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":85.29166666666667,"warning":null},{"id":"72ec400df622abf0993c0b92","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":78.989898989899,"warning":null},{"id":"07bdaa927df321564f2c1d84","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":15.8943466172382,"warning":null},{"id":"44d7a6991cc91d58c55ff9a6","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":51.2244897959184,"warning":null},{"id":"cabc23b6d1570087cdf40e87","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":78.8359788359788,"warning":null},{"id":"67ad8c31109848b751082bc1","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":98.4,"warning":null},{"id":"1f706dbdb38fdc0c25ef1282","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":84.2586436170213,"warning":null},{"id":"963e940e7972f41eb041f884","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":-46.5166666666667,"warning":null},{"id":"e126146d0f6fd5e675ea5077","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":22.816666666666666,"warning":null},{"id":"257a65544bb4192d4e6972b6","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":41.435185185185205,"warning":null},{"id":"e51a19f3141204938b7e3a3c","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":53.2163742690059,"warning":null},{"id":"2acb2f76d344a5a0435308de","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":7.83505154639175,"warning":null},{"id":"0c1071699ff2079d8fdebc1b","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":13.6363636363636,"warning":null},{"id":"2f2ba29d0427aaad4c86e0c6","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":11.9850187265918,"warning":null},{"id":"2209fa80f3ef69cff5c6933e","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3 235B A22B 2507 (Reasoning)","configuration":"Qwen3 235B A22B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-235b-a22b-instruct-2507-reasoning","score":0,"warning":null},{"id":"5e6dd137fbbb57f48edbb48f","modelId":"qwen3-30b-a3b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":21.6666666666667,"warning":null},{"id":"192afae643d6adf6c2b4c358","modelId":"qwen3-30b-a3b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":72.3333333333333,"warning":null},{"id":"70efb52fb8f76af5b6b52a6e","modelId":"qwen3-30b-a3b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":0,"warning":null},{"id":"fdf5b9f8d714afb06ad143b4","modelId":"qwen3-30b-a3b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":0,"warning":null},{"id":"ae488d8b4035636896c7c04b","modelId":"qwen3-30b-a3b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":0,"warning":null},{"id":"4381440088e84230d7416ca0","modelId":"qwen3-30b-a3b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":0,"warning":null},{"id":"9eba4f44d37ec442eae1c0b6","modelId":"qwen3-30b-a3b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":51.5151515151515,"warning":null},{"id":"3fef3ec80ad899c411e920db","modelId":"qwen3-30b-a3b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":61.616161616161605,"warning":null},{"id":"eeeec44dbdcbcd1fec5088ff","modelId":"qwen3-30b-a3b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":4.6,"warning":null},{"id":"0d7d919efd90d5c6c7d2d155","modelId":"qwen3-30b-a3b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":6.16,"warning":null},{"id":"ebd843a2940c41c39943f6fc","modelId":"qwen3-30b-a3b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":31.9047619047619,"warning":null},{"id":"dca37a8019d4b22d0d4f863a","modelId":"qwen3-30b-a3b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":41.4965986394558,"warning":null},{"id":"660d0d9d49749f2371fee225","modelId":"qwen3-30b-a3b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":32.1693121693122,"warning":null},{"id":"2c9b11fa4972aba196c050ec","modelId":"qwen3-30b-a3b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":50.5820105820106,"warning":null},{"id":"85fa93b4a127efea07f4ee97","modelId":"qwen3-30b-a3b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":86.26666666666671,"warning":null},{"id":"faac05e386302fdce6abc902","modelId":"qwen3-30b-a3b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":95.93333333333331,"warning":null},{"id":"a744d10897af345ffbf1637e","modelId":"qwen3-30b-a3b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":71.0438829787234,"warning":null},{"id":"bafe260a148c38a7ada467f2","modelId":"qwen3-30b-a3b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":77.6761968085106,"warning":null},{"id":"be9c4f9166e8a88c6c27dc71","modelId":"qwen3-30b-a3b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":-65.9833333333333,"warning":null},{"id":"48c5c21ee84158570d29b986","modelId":"qwen3-30b-a3b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":-51.4833333333333,"warning":null},{"id":"811a45a5a0d28bd953acd4a1","modelId":"qwen3-30b-a3b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":11.966666666666667,"warning":null},{"id":"f5dec5d5bb04db837fefe24f","modelId":"qwen3-30b-a3b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":16.183333333333334,"warning":null},{"id":"a9de0ffeb600f9f6945e64b7","modelId":"qwen3-30b-a3b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":22.2222222222222,"warning":null},{"id":"ad5665745ea3639e88c0f813","modelId":"qwen3-30b-a3b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":26.023391812865498,"warning":null},{"id":"af5c211c7fbd820d3a9078a1","modelId":"qwen3-30b-a3b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B (Non-reasoning)","configuration":"Qwen3 30B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct","score":6.81818181818182,"warning":null},{"id":"8a719f06b81ca947a876e5a9","modelId":"qwen3-30b-a3b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 30B A3B (Reasoning)","configuration":"Qwen3 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-instruct-reasoning","score":2.27272727272727,"warning":null},{"id":"e6194a0353b1168809b0b254","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.3333333333333,"warning":null},{"id":"77ce916db696117abf426908","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.333333333333297,"warning":null},{"id":"727953477da1c7bfd3dddf55","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"bbff8e891ca3ce9fb273e4e0","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.01041666666667,"warning":null},{"id":"2d5e8811e66cf17e31e93e44","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":65.85858585858591,"warning":null},{"id":"fdacb847dded341069a86e17","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.90454124189064,"warning":null},{"id":"9119e88a171b62aff4d1d30f","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.0612244897959,"warning":null},{"id":"04f2969c4b63ad25ed889181","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.5343915343915,"warning":null},{"id":"d2d8294eaf80d456436b1a75","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":97.5333333333333,"warning":null},{"id":"4251c0820afca56a08be5811","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.7177526595745,"warning":null},{"id":"62854b9cc7a0052762824704","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":-66.15,"warning":null},{"id":"de8c589cdba00a5c5afca9c9","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.966666666666667,"warning":null},{"id":"587a06eec8c56d9a9b6aedb0","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.233918128654999,"warning":null},{"id":"b8383df5670c6809c2eef77c","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 30B A3B 2507 Instruct","configuration":"Qwen3 30B A3B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.06060606060606,"warning":null},{"id":"3550590d824ebcef07ed8d6e","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":31.59,"warning":null},{"id":"d6db70276e35943ca61c814e","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":56.3333333333333,"warning":null},{"id":"2321ae88075ead248809d8e1","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":61.33333333333329,"warning":null},{"id":"1f1f0c80edae6f3a634beda2","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":0.795143729768833,"warning":null},{"id":"370b5b9bebce490bc7802be4","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":0.28571428571428603,"warning":null},{"id":"b4d7a3feb92d122e78ebcd62","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":0.4,"warning":null},{"id":"d2591a46db7e7e1ce9c5d203","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":273.6,"warning":null},{"id":"82ee76c486480d1331cac8a7","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":70.7070707070707,"warning":null},{"id":"694a6ae93a990d591913241b","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":10.2873030583874,"warning":null},{"id":"7ece9316f357641df5610882","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":50.6802721088435,"warning":null},{"id":"f4e0fece0be006e5564b5eea","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":70.6878306878307,"warning":null},{"id":"48efe4f78a59711b33996eb4","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":97.6,"warning":null},{"id":"1bfc9cea4d180f9ec285a7ad","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":80.5019946808511,"warning":null},{"id":"d309ffb9a64b671bdd150c8c","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":-56.1333333333333,"warning":null},{"id":"a0c4514c75c30f131fadd06c","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":16.3,"warning":null},{"id":"97fe37c7f9321a9afbce9419","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":32.9861111111111,"warning":null},{"id":"2143491abf4fa705ee0ff478","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":28.0701754385965,"warning":null},{"id":"eb94bdb3a73cbd6888dd9b81","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":5.36082474226804,"warning":null},{"id":"7da6e30fc453a9160b7fc090","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":5.3030303030303,"warning":null},{"id":"da91fae6c59400b775705b5c","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":1.4981273408239701,"warning":null},{"id":"52eff8771abcc56b8e2ca851","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3 30B A3B 2507 (Reasoning)","configuration":"Qwen3 30B A3B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-30b-a3b-2507-reasoning","score":0,"warning":null},{"id":"40395342c9fca4b8ab6ec126","modelId":"qwen3-32b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":9.49,"warning":null},{"id":"50bc16029e3f89646a8db5d5","modelId":"qwen3-32b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 32B (Non-reasoning)","configuration":"Qwen3 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct","score":19.6666666666667,"warning":null},{"id":"236503dc2ece70ff04cb2662","modelId":"qwen3-32b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":73,"warning":null},{"id":"467c0d1a8d9fbd1da7d58c18","modelId":"qwen3-32b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 32B (Non-reasoning)","configuration":"Qwen3 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct","score":0,"warning":null},{"id":"dc2bbac9236f9e228cd498ce","modelId":"qwen3-32b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":0,"warning":null},{"id":"f14f0ee78f85450317855ae0","modelId":"qwen3-32b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":0.9711289785341921,"warning":null},{"id":"32e698f91999aa66dbf0d33b","modelId":"qwen3-32b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":0.28571428571428603,"warning":null},{"id":"2881dc70ef3c09ffe8b7aaf6","modelId":"qwen3-32b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":1.6,"warning":null},{"id":"8d8b0c8bfd82a870c0e8e9fe","modelId":"qwen3-32b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":239.65,"warning":null},{"id":"ef0a55af7e9bca42a6969898","modelId":"qwen3-32b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 32B (Non-reasoning)","configuration":"Qwen3 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct","score":53.5353535353535,"warning":null},{"id":"09c94da7f63cc4f35fcaa8ef","modelId":"qwen3-32b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":66.7676767676768,"warning":null},{"id":"48c85cef75aca509424f96d8","modelId":"qwen3-32b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 32B (Non-reasoning)","configuration":"Qwen3 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct","score":4.130000000000001,"warning":null},{"id":"532667768a038808e1c06a66","modelId":"qwen3-32b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":7.41,"warning":null},{"id":"cc30d25c84e9b4477b649acc","modelId":"qwen3-32b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 32B (Non-reasoning)","configuration":"Qwen3 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct","score":31.496598639455797,"warning":null},{"id":"fe95c5c72ff58ffbfe5f6823","modelId":"qwen3-32b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":36.3265306122449,"warning":null},{"id":"c013a49962eaeffd601049e4","modelId":"qwen3-32b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 32B (Non-reasoning)","configuration":"Qwen3 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct","score":28.7830687830688,"warning":null},{"id":"366e308a05ab543e85742e62","modelId":"qwen3-32b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":54.6031746031746,"warning":null},{"id":"ba8a236b0d865aa499356fe1","modelId":"qwen3-32b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 32B (Non-reasoning)","configuration":"Qwen3 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct","score":86.8666666666667,"warning":null},{"id":"0b986f53a1a49d882b80d396","modelId":"qwen3-32b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":96.0666666666667,"warning":null},{"id":"29346831ae44b3d310de7180","modelId":"qwen3-32b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 32B (Non-reasoning)","configuration":"Qwen3 32B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct","score":72.7476728723404,"warning":null},{"id":"239624201d84931ac65ea002","modelId":"qwen3-32b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":79.8454122340426,"warning":null},{"id":"864945a3e7a9e02b314d1f06","modelId":"qwen3-32b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":-50.3666666666667,"warning":null},{"id":"7986bc6ac6e65fd08a7872d5","modelId":"qwen3-32b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":17.433333333333334,"warning":null},{"id":"4f069f41ce299bb5371886aa","modelId":"qwen3-32b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":35.9953703703704,"warning":null},{"id":"49a11e10c53668cb78a23aff","modelId":"qwen3-32b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":29.8245614035088,"warning":null},{"id":"66b3f17222441498b28217a6","modelId":"qwen3-32b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":5.36082474226804,"warning":null},{"id":"0473d12b293f64f0a0d6891e","modelId":"qwen3-32b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":3.03030303030303,"warning":null},{"id":"600f05c1a0f31fa75134db9e","modelId":"qwen3-32b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":5.2434456928839,"warning":null},{"id":"051c088ca8dff8e607638eba","modelId":"qwen3-32b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3 32B (Reasoning)","configuration":"Qwen3 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-32b-instruct-reasoning","score":0,"warning":null},{"id":"3fb8f25022ef3577afaf7e10","modelId":"qwen3-4b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":22.3333333333333,"warning":null},{"id":"37ddd191ba8a7706c22ede89","modelId":"qwen3-4b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":0,"warning":null},{"id":"65f0ddfbfd712968af3079af","modelId":"qwen3-4b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 4B (Non-reasoning)","configuration":"Qwen3 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct","score":39.7979797979798,"warning":null},{"id":"91155b95de942a7455e43323","modelId":"qwen3-4b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":52.2222222222222,"warning":null},{"id":"6a3477ae7039d94212e11fec","modelId":"qwen3-4b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 4B (Non-reasoning)","configuration":"Qwen3 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct","score":3.32,"warning":null},{"id":"603076858d0e2948a85c123d","modelId":"qwen3-4b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":4.42,"warning":null},{"id":"87904f931dc2ffb73802afcf","modelId":"qwen3-4b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":32.5170068027211,"warning":null},{"id":"7eda1f86bc4fd88090113e80","modelId":"qwen3-4b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 4B (Non-reasoning)","configuration":"Qwen3 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct","score":23.2804232804233,"warning":null},{"id":"e0bb53c1cf9d782756209f3d","modelId":"qwen3-4b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":46.4550264550264,"warning":null},{"id":"f7989a07f2d2c06d46c14671","modelId":"qwen3-4b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 4B (Non-reasoning)","configuration":"Qwen3 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct","score":84.2666666666667,"warning":null},{"id":"b4374f7d2c16022ba21b76a9","modelId":"qwen3-4b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":93.3333333333333,"warning":null},{"id":"629a36632de288da7f71fb5d","modelId":"qwen3-4b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 4B (Non-reasoning)","configuration":"Qwen3 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct","score":58.59375,"warning":null},{"id":"f46c6d830769a6c4e5c99df7","modelId":"qwen3-4b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":69.5644946808511,"warning":null},{"id":"32c6def6785bf325dc4f87ed","modelId":"qwen3-4b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 4B (Reasoning)","configuration":"Qwen3 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-instruct-reasoning","score":19.0058479532164,"warning":null},{"id":"b8304749e7352f154e474794","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.3333333333333,"warning":null},{"id":"15a1c599f7692208475bf7ec","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.3333333333333,"warning":null},{"id":"56d2377da4fb0704eb1ac2d3","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"fa65e4aae5f09070d5102301","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.71153846153847,"warning":null},{"id":"9eb087a7abc8d597044257ee","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.717171717171695,"warning":null},{"id":"4d43e7f62daa161d728080e2","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.49490268767377,"warning":null},{"id":"c10be8c55f9429f748beb6b9","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.5374149659864,"warning":null},{"id":"9b204881e5210ee72604f1d6","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.6719576719577,"warning":null},{"id":"78d1af6fd684f7bf363b664e","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.2373670212766,"warning":null},{"id":"49c265837d27d2d2bf8e4efd","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-61.9333333333333,"warning":null},{"id":"cd9a6a9b734e8a05a1d62106","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.9,"warning":null},{"id":"be24a4e27b32bad48a266dab","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.6081871345029,"warning":null},{"id":"37afc57a11a68563f8f2ef72","modelId":"qwen3-4b-instruct-2507","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 4B 2507 Instruct","configuration":"Qwen3 4B 2507 Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.545454545454549,"warning":null},{"id":"96ebe1b6fbf2e0d343e3a601","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":82.6666666666667,"warning":null},{"id":"e5545ac10fac2b93cda828d1","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":37.3333333333333,"warning":null},{"id":"73326f7b5805389fbe29ad4d","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":0,"warning":null},{"id":"e11def07dfa9e995c73e1bac","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":66.6666666666667,"warning":null},{"id":"15a62e80d61f958a5049ebf7","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":6.1631139944393,"warning":null},{"id":"8942418d355ebf98c867b34b","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":49.7959183673469,"warning":null},{"id":"db6ac46ae5700dbe44444c52","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":64.1269841269841,"warning":null},{"id":"7b9744f8d20c3175afe7b407","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":74.3101728723404,"warning":null},{"id":"b3a3f857a9b6c30c32f5e781","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":-60.2666666666667,"warning":null},{"id":"fa0a36c238b7bcee88d55771","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":12.533333333333333,"warning":null},{"id":"9cd71124c6978766c9d6d511","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":25.4385964912281,"warning":null},{"id":"a6478507eb9c1b358f3b4a3c","modelId":"qwen3-4b-thinking-2507","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 4B 2507 (Reasoning)","configuration":"Qwen3 4B 2507 (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-4b-2507-instruct-reasoning","score":1.51515151515152,"warning":null},{"id":"6aec1ffa155c03633da8ddbc","modelId":"qwen3-8b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":0,"warning":null},{"id":"77e57e37efff0800a4ac52e2","modelId":"qwen3-8b","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":24.3333333333333,"warning":null},{"id":"0ee738972827562727062ab4","modelId":"qwen3-8b","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":19,"warning":null},{"id":"810d82044b4b72e1d77b2229","modelId":"qwen3-8b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":0,"warning":null},{"id":"fff734316823fab5da7d9839","modelId":"qwen3-8b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":0,"warning":null},{"id":"470d367830b121eff8410527","modelId":"qwen3-8b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":0.3326067293298021,"warning":null},{"id":"553d1656777ad9dd0b5fbd2e","modelId":"qwen3-8b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":0,"warning":null},{"id":"a71931fca8ea24e37311ccff","modelId":"qwen3-8b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":0,"warning":null},{"id":"ebca0d32e1876250f09920a9","modelId":"qwen3-8b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":1.4000000000000001,"warning":null},{"id":"1d0248ab020e41ba3ca08e1c","modelId":"qwen3-8b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":165.39,"warning":null},{"id":"9607a0d57cad509ef28ad301","modelId":"qwen3-8b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":45.1515151515152,"warning":null},{"id":"3f121713f6dd60580e421928","modelId":"qwen3-8b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":58.8888888888889,"warning":null},{"id":"f444a8a8c61adea63cb4e058","modelId":"qwen3-8b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":1.95,"warning":null},{"id":"07a8885a5754031517a535e8","modelId":"qwen3-8b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":3.8899999999999997,"warning":null},{"id":"bf779bb3e13563b175f0959e","modelId":"qwen3-8b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":28.571428571428598,"warning":null},{"id":"c0a1791dc8cd498b60abbce8","modelId":"qwen3-8b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":33.469387755102,"warning":null},{"id":"a1b9be1ec2a8c4aba2017b1b","modelId":"qwen3-8b","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":20.2116402116402,"warning":null},{"id":"1c4376001c7ea7ed1c0c72d6","modelId":"qwen3-8b","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":40.634920634920604,"warning":null},{"id":"3598c03b7e5214c93e9c72ca","modelId":"qwen3-8b","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":82.8,"warning":null},{"id":"c030d0371f9e059436a36972","modelId":"qwen3-8b","benchmarkId":"aa-math-500","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":90.4,"warning":null},{"id":"bbb6369c5b97ed3eb6f04b90","modelId":"qwen3-8b","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":64.2785904255319,"warning":null},{"id":"3085e36820ee68bd4a102b22","modelId":"qwen3-8b","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":74.30186170212771,"warning":null},{"id":"7d82a974e643a8d0e079950e","modelId":"qwen3-8b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":-73.95,"warning":null},{"id":"ab22b03c0bef227a91b34986","modelId":"qwen3-8b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":-64.7333333333333,"warning":null},{"id":"f261ae29c7c086c8c29aff0b","modelId":"qwen3-8b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":11.083333333333334,"warning":null},{"id":"5702032aa67edf32f4667d95","modelId":"qwen3-8b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":13.633333333333333,"warning":null},{"id":"f14ac71d6c0d2283748b9d25","modelId":"qwen3-8b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":27.8935185185185,"warning":null},{"id":"c2a1189537534941d9d8a6cf","modelId":"qwen3-8b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":24.8538011695906,"warning":null},{"id":"a2753d2f3b8d5e1cdf181a56","modelId":"qwen3-8b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":27.7777777777778,"warning":null},{"id":"733f2508843a636f98ba5701","modelId":"qwen3-8b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":4.74226804123711,"warning":null},{"id":"e64c7478502eac8baee26e39","modelId":"qwen3-8b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 8B (Non-reasoning)","configuration":"Qwen3 8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct","score":2.27272727272727,"warning":null},{"id":"25b23d6d1d47b76b25448251","modelId":"qwen3-8b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":2.27272727272727,"warning":null},{"id":"90aa8fa4b05c718ddfd307c8","modelId":"qwen3-8b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":2.2471910112359503,"warning":null},{"id":"5c8bf720b7385ebdeb270f69","modelId":"qwen3-8b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3 8B (Reasoning)","configuration":"Qwen3 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8b-instruct-reasoning","score":0,"warning":null},{"id":"a5e53cf2346ee45d0c582775","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.999999999999996,"warning":null},{"id":"8639ec30f3a041013cccdecc","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.6666666666667,"warning":null},{"id":"fdd2d19f3143bc2b076e5415","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"2ae61a29f11e72de77a36c9d","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.616161616161605,"warning":null},{"id":"eec049bcf666ad4a78e12134","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.84615384615385,"warning":null},{"id":"2c80de3cac3aa9982c6fbe1a","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.6530612244898,"warning":null},{"id":"fe3e00ef3fb3a6b9d569105e","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.3174603174603,"warning":null},{"id":"2fb790d8ab3d3930b2000933","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":89.3333333333333,"warning":null},{"id":"1b62d586150de22843349748","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.63663563829789,"warning":null},{"id":"26f52aa824dc36a26b030308","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-50.7333333333333,"warning":null},{"id":"9b267017f4daf531a326f8af","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.400000000000002,"warning":null},{"id":"76caa5bcdaa62e0399c1cbd7","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":34.5029239766082,"warning":null},{"id":"282d2dd5d0f2b0feec3a9bbb","modelId":"qwen3-coder-30b-a3b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 Coder 30B A3B Instruct","configuration":"Qwen3 Coder 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.151515151515198,"warning":null},{"id":"8ece51f27224d12114df7c4a","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.3333333333333,"warning":null},{"id":"0de3521cedd608973feca387","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":45.6666666666667,"warning":null},{"id":"b7bb1715f0274733e3390c12","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"cfa076638384c0501b932837","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":61.818181818181806,"warning":null},{"id":"1ce4d095b186c8dbb2109774","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.54124189063948,"warning":null},{"id":"e9ccf3989be626311c527af4","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.476190476190496,"warning":null},{"id":"c826b7e819def2b96de0b1c1","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":58.518518518518505,"warning":null},{"id":"69c8dc453e9cd5a94a8bdbac","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-math-500","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":94.19999999999999,"warning":null},{"id":"c490527d77a38dba93e58b40","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.7898936170213,"warning":null},{"id":"0b2034bca18006f3172a087a","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-22.2,"warning":null},{"id":"13d73650a0ce5aadc74813ae","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.683333333333332,"warning":null},{"id":"7c7d9e8d1215597f71eb1e20","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.5672514619883,"warning":null},{"id":"cef9782dc0d168133b8a20ff","modelId":"qwen3-coder-480b-a35b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 Coder 480B A35B Instruct","configuration":"Qwen3 Coder 480B A35B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-480b-a35b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.939393939393902,"warning":null},{"id":"d469c05a1795dc81f7c98893","modelId":"qwen3-coder-next","benchmarkId":"aa-aa-briefcase","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":413.75,"warning":null},{"id":"4023e37a7772337e40c94a66","modelId":"qwen3-coder-next","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":47,"warning":null},{"id":"c0813bddfc181d56d1e8b8a5","modelId":"qwen3-coder-next","benchmarkId":"aa-automationbench-aa","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.0593550691766298,"warning":null},{"id":"b74549c8fd9f209dea3e7bc5","modelId":"qwen3-coder-next","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"f590ce5d0d46d0cce0006d8e","modelId":"qwen3-coder-next","benchmarkId":"aa-gdp-pdf","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.6,"warning":null},{"id":"106d757c07493e32172fb22f","modelId":"qwen3-coder-next","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":664.31,"warning":null},{"id":"b7b3a1fbc5ff2942f395c61f","modelId":"qwen3-coder-next","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.39583333333333,"warning":null},{"id":"f5eee82bc106b4fb51416f3e","modelId":"qwen3-coder-next","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.7373737373737,"warning":null},{"id":"1806e532fa8659866761b296","modelId":"qwen3-coder-next","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.1482854494903,"warning":null},{"id":"4fdb286556f7a859f007abc5","modelId":"qwen3-coder-next","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.2380952380952,"warning":null},{"id":"6fb3b7bf91c4f655e0f9e5f6","modelId":"qwen3-coder-next","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":-62.4,"warning":null},{"id":"9dd3ea750813737b771bb546","modelId":"qwen3-coder-next","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.150000000000002,"warning":null},{"id":"e73b78f68f384f26a35c1f23","modelId":"qwen3-coder-next","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":36.2268518518519,"warning":null},{"id":"70885ee7997cb7f5413f9175","modelId":"qwen3-coder-next","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.5321637426901,"warning":null},{"id":"bb4142bd1725e8cb824ec398","modelId":"qwen3-coder-next","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.36082474226804,"warning":null},{"id":"1c252534d9d58d5a8dc603c1","modelId":"qwen3-coder-next","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.181818181818198,"warning":null},{"id":"0851b3e49721b62cf6fdcad2","modelId":"qwen3-coder-next","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.2022471910112,"warning":null},{"id":"48676396dd68515d0e746b37","modelId":"qwen3-coder-next","benchmarkId":"aa-terminalbench-v4-0","level":"non-reasoning","sourceLabel":"Qwen3 Coder Next","configuration":"Qwen3 Coder Next; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-coder-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"379f3e03c5a75e45500083ec","modelId":"qwen3-max","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.6666666666667,"warning":null},{"id":"d0ee451e3d70f7acbd7160ad","modelId":"qwen3-max","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":75,"warning":null},{"id":"41701e2d8384671332f59b80","modelId":"qwen3-max","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":50,"warning":null},{"id":"873b3fc87079fb7d99451bb6","modelId":"qwen3-max","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":43,"warning":null},{"id":"315935ae2fb0b8d9506630ce","modelId":"qwen3-max","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.857142857142857,"warning":null},{"id":"618ec7df142e33dee8639477","modelId":"qwen3-max","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"4d4b86792ad7edf434ee2ac5","modelId":"qwen3-max","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":83.28645833333333,"warning":null},{"id":"1ab71f78c9db94e51405eddb","modelId":"qwen3-max","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.3636363636364,"warning":null},{"id":"c2fdb1293b42e7e45cbd183b","modelId":"qwen3-max","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.3636363636364,"warning":null},{"id":"18a603f0cb554eff82286b14","modelId":"qwen3-max","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.1482854494903,"warning":null},{"id":"380908933be5913820054566","modelId":"qwen3-max","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.9091751621872,"warning":null},{"id":"879326ff889e832b42641611","modelId":"qwen3-max","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.0272108843537,"warning":null},{"id":"c69c24d53e30040f4c162f6f","modelId":"qwen3-max","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.1496598639456,"warning":null},{"id":"3659c33ae93ad5a386c4057d","modelId":"qwen3-max","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.7195767195767,"warning":null},{"id":"eb581aed1e808fa587fdb05b","modelId":"qwen3-max","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":65.0793650793651,"warning":null},{"id":"08a91161451f412505e30032","modelId":"qwen3-max","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":83.83477393617021,"warning":null},{"id":"2b16892f62e2b462f8dead01","modelId":"qwen3-max","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.11735372340429,"warning":null},{"id":"520b99ee426c18dd7f263df5","modelId":"qwen3-max","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":-42.7833333333333,"warning":null},{"id":"c010e27462d3d72e8f96c438","modelId":"qwen3-max","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":-43.55,"warning":null},{"id":"4bbb94159adbed7fb9c2fd95","modelId":"qwen3-max","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.2,"warning":null},{"id":"e392854706b6be7d554ebf84","modelId":"qwen3-max","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.416666666666668,"warning":null},{"id":"12c287fe88bcaa562fa38631","modelId":"qwen3-max","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.7485380116959,"warning":null},{"id":"8e7b03c9d5c0d8dea1a9ebd9","modelId":"qwen3-max","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.2690058479532,"warning":null},{"id":"2bdf79ef92caebbcd2a7db59","modelId":"qwen3-max","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 Max","configuration":"Qwen3 Max; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.4545454545455,"warning":null},{"id":"c942c318ad1475140efa1310","modelId":"qwen3-max","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 Max (Preview)","configuration":"Qwen3 Max (Preview); Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-max-preview; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.6969696969697,"warning":null},{"id":"bb0a0f706bcfacfc8bfbcb0b","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":66.3333333333333,"warning":null},{"id":"39324bf234452599e097140c","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.66666666666669,"warning":null},{"id":"0bebebb1c0d3d8c78f37ab1f","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"b6d6b7200e8855577137d44b","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.8383838383838,"warning":null},{"id":"e3f87d78cfb9be15308174cc","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.645968489341979,"warning":null},{"id":"2dec37e2c4f881a390992157","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.6598639455782,"warning":null},{"id":"7902cc4d3470d6a216813a4e","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.3597883597884,"warning":null},{"id":"02254150ed5397242e653e1c","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.88164893617021,"warning":null},{"id":"2263e85fdc24b011ab25738f","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-59.5,"warning":null},{"id":"c5b9a37885e2ba0e8b3361a4","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.25,"warning":null},{"id":"7ba187ae862e408223ddd229","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.6374269005848,"warning":null},{"id":"32276506d0d1e55800cb28e1","modelId":"qwen3-next-80b-a3b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 Next 80B A3B Instruct","configuration":"Qwen3 Next 80B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.57575757575758,"warning":null},{"id":"8d89e459916593927b09df0d","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":84.3333333333333,"warning":null},{"id":"6f45310222eab628315727a3","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":63.66666666666671,"warning":null},{"id":"7cd92797a65aa1b3546d034a","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":0,"warning":null},{"id":"8df0294fd65c5979676259e0","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":324.88,"warning":null},{"id":"b85018d49d57cf2e8050c2ad","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":81.94270833333333,"warning":null},{"id":"9c43e3dd521102061d12b83c","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":75.8585858585858,"warning":null},{"id":"a632fb2495b87e7d0e9989e0","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":12.5579240037071,"warning":null},{"id":"0fd93cc59b58680c7cd8160d","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":60.6802721088435,"warning":null},{"id":"8725748b17d9c049319bc806","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":78.4126984126984,"warning":null},{"id":"739cc3ae08400828dd7e34ad","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":82.3803191489362,"warning":null},{"id":"9e71a0ae62a979c3a73340e0","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":-51.4166666666667,"warning":null},{"id":"52855ab9f5e4787364e91f02","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":19.03333333333333,"warning":null},{"id":"8d68334084e3a4fcd1a96926","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":41.5204678362573,"warning":null},{"id":"cde368032b5e946e8016b135","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":6.18556701030928,"warning":null},{"id":"8bdb9faad99b2ad6caa3e59e","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":9.84848484848485,"warning":null},{"id":"53f02abbe152e698259000de","modelId":"qwen3-next-80b-a3b-thinking","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3 Next 80B A3B (Reasoning)","configuration":"Qwen3 Next 80B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning","score":6.741573033707859,"warning":null},{"id":"66e1a70cfbb06ba377a24906","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":52.3333333333333,"warning":null},{"id":"6e1994fe220192d4f648bc00","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"cb01da84527cd626a88d69a5","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"207e511763a5de76dd47573d","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":62.020202020202,"warning":null},{"id":"a52027c783bbeb79f5ee0053","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.6339202965709,"warning":null},{"id":"d2f6bbcba92a230b64695fba","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.156462585034,"warning":null},{"id":"a95606570c645f6594bdd527","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.2222222222222,"warning":null},{"id":"edacfa4d7f499e0fbdf77f56","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.4817154255319,"warning":null},{"id":"23cb074182ab575c2d998986","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":55.4913294797688,"warning":null},{"id":"96e0b755ad70d1c1e0ae9354","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-69.2666666666667,"warning":null},{"id":"c67b438ddcafcd62ab222e69","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.333333333333334,"warning":null},{"id":"44fe6f288cb432b5362daa11","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.374269005848,"warning":null},{"id":"da85a712a2a928f8a0093ebe","modelId":"qwen3-omni-30b-a3b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 Omni 30B A3B Instruct","configuration":"Qwen3 Omni 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.51515151515152,"warning":null},{"id":"f78f496de1e6c875cbbb78f7","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.6666666666667,"warning":null},{"id":"ffe8f1f73796df547f259cd9","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.6666666666667,"warning":null},{"id":"debf36b3ff3a8afa229b244f","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"25e5c20c242f402a50e10b5c","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.2121212121212,"warning":null},{"id":"d83fa0fcf5570fd9e34ce182","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.62650602409639,"warning":null},{"id":"8768eb7e5b3055cae4949a8c","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.653061224489804,"warning":null},{"id":"2b8146bfa8634abeab45959f","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":59.365079365079396,"warning":null},{"id":"94e4190c5036843765fa2396","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.313829787234,"warning":null},{"id":"5e3a87793c1033e86adf1f22","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.5722543352601,"warning":null},{"id":"1648013dead8d8b7e3ccc5b7","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-52.6666666666667,"warning":null},{"id":"d60c61b3b2041a2b188d80da","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.3,"warning":null},{"id":"f872fe1f414e47d1ea0273fc","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.0877192982456,"warning":null},{"id":"a131db2197b9e48ad031e4c0","modelId":"qwen3-vl-235b-a22b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 VL 235B A22B Instruct","configuration":"Qwen3 VL 235B A22B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.81818181818182,"warning":null},{"id":"1c9c62a5f652b687c1908560","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.3333333333333,"warning":null},{"id":"ce2d0da396f1bad697146064","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"6bec8c4c730c568a6b901187","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":69.4949494949495,"warning":null},{"id":"5b21bb8a42d86dea2ee62b68","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.302131603336419,"warning":null},{"id":"c8b57cbe46a5a65b9861cf57","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.1292517006803,"warning":null},{"id":"8edf38eeca7d9796ddf0e53e","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.6190476190476,"warning":null},{"id":"7e5b735a0b87bf634aa6456a","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.4461436170213,"warning":null},{"id":"f977ec4daaaca0a87c90c23a","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":62.1387283236994,"warning":null},{"id":"3d168904477178b1120a9f97","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-63.4166666666667,"warning":null},{"id":"d248649872ed9e5e376ce5b7","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.616666666666667,"warning":null},{"id":"4f52b0d13a697ef0d9e0d6b8","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":19.0058479532164,"warning":null},{"id":"a6bf0592349468ca8091cc9a","modelId":"qwen3-vl-30b-a3b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 VL 30B A3B Instruct","configuration":"Qwen3 VL 30B A3B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.06060606060606,"warning":null},{"id":"a4c021f4566a015478f0f03d","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":82.3333333333333,"warning":null},{"id":"d52a0dfa14f73e70c99eece0","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":0,"warning":null},{"id":"2cde6a74401fadb647be7203","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":72.02020202020199,"warning":null},{"id":"c5ba2f971eba83fe4e4cd779","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":8.943466172381841,"warning":null},{"id":"652d921806364ca7568196c2","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":45.1020408163265,"warning":null},{"id":"f954718896851a2f87b497bd","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":69.73544973544969,"warning":null},{"id":"e26f300586ddb51b29981834","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":80.6682180851064,"warning":null},{"id":"4a35028ffd4c5b0bd78f6503","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":61.849710982659,"warning":null},{"id":"bc8e92ab40faf29f9b4d4907","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":-57.6333333333333,"warning":null},{"id":"d6a9a7a1d698ec0f45749b16","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":16.933333333333334,"warning":null},{"id":"bbcfcfc5a57e209927c93a91","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":19.8830409356725,"warning":null},{"id":"76bffec8df092259b0e2775e","modelId":"qwen3-vl-30b-a3b-thinking","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 VL 30B A3B (Reasoning)","configuration":"Qwen3 VL 30B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-30b-a3b-reasoning","score":5.3030303030303,"warning":null},{"id":"db2809519c432f97129f7f51","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.3333333333333,"warning":null},{"id":"a0b8bc5d77324f5d4a6184e7","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"f932e350d02270272a4699b5","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.0707070707071,"warning":null},{"id":"7346e21ff6039e7851f3cf0c","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.811862835959221,"warning":null},{"id":"5cdf63b8df011f0ff87fb63b","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.1836734693878,"warning":null},{"id":"6fe04ab988c966bcc2cc8917","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.4285714285714,"warning":null},{"id":"d82e08723042532db00fbf64","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.05585106382979,"warning":null},{"id":"8435069f6714805a5bdcb8b3","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":64.27745664739881,"warning":null},{"id":"47a57d2d2d5bebced36433b6","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-63.3666666666667,"warning":null},{"id":"4eeb25e06a76789d08deef48","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.833333333333334,"warning":null},{"id":"937f3deb6ec8769352a2f898","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.2397660818713,"warning":null},{"id":"788b5a4a18e66ca329d23ccd","modelId":"qwen3-vl-32b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 VL 32B Instruct","configuration":"Qwen3 VL 32B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.33333333333333,"warning":null},{"id":"2e55ba0226be74935acdc897","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":84.6666666666667,"warning":null},{"id":"a4094dd3667ddcfa668fe7e5","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":55.3333333333333,"warning":null},{"id":"d582a1e6ea952bdaa149da51","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":0,"warning":null},{"id":"73203773c02c1803cc040e47","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":73.3333333333333,"warning":null},{"id":"90a23b0985eb873d6da4fbac","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":10.1482854494903,"warning":null},{"id":"a535d8fa36ad7b6f19efccfb","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":59.3877551020408,"warning":null},{"id":"8f152c8b037230620cdf6612","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":73.7566137566138,"warning":null},{"id":"0833bcf585498456cc9d0564","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":81.781914893617,"warning":null},{"id":"72340574c11bdf92b50a5b2f","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":63.410404624277504,"warning":null},{"id":"79f1b817a8bf3ed314092aa1","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":-52.5166666666667,"warning":null},{"id":"6175e18fd0e66b677d391766","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":16.966666666666665,"warning":null},{"id":"91c0534b0a62fc3b88904ed9","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":45.6140350877193,"warning":null},{"id":"96aa9eb5f454deea7dce2ec5","modelId":"qwen3-vl-32b-thinking","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 VL 32B (Reasoning)","configuration":"Qwen3 VL 32B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-32b-reasoning","score":7.57575757575758,"warning":null},{"id":"fdb356426f563f83f2ea4a01","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":37,"warning":null},{"id":"ecb1b4b1085894574d2ede22","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.000000000000002,"warning":null},{"id":"3965d02265b8cd2f3fb53b31","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"048a32652d70416c7f411620","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.0707070707071,"warning":null},{"id":"3411bba2fa134fafbba0bb3a","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":3.6144578313252995,"warning":null},{"id":"0cf5d2bad9846828c180e48e","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.8367346938775,"warning":null},{"id":"18d7349015832a249624fd5c","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.994708994709,"warning":null},{"id":"656a47fb67b2a19fef4e31ec","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.3976063829787,"warning":null},{"id":"5d8e3953b819ae9ecb77cb33","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.8728323699422,"warning":null},{"id":"edb4937174129ff14d58735a","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-75.9666666666667,"warning":null},{"id":"1d167a258f9e93c210f259ed","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.866666666666665,"warning":null},{"id":"1724ab099aea8608156fc956","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.3918128654971,"warning":null},{"id":"ee07bf88a91e4495261d3439","modelId":"qwen3-vl-4b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 VL 4B Instruct","configuration":"Qwen3 VL 4B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"a2016ac901838a157d54e1eb","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":25.6666666666667,"warning":null},{"id":"ecb9cf10e11fd05f5d7d8502","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":21.3333333333333,"warning":null},{"id":"5819e3fd8452136833f35718","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":0,"warning":null},{"id":"57b61b1da9a2c9e3a3acb85f","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":49.3939393939394,"warning":null},{"id":"e959c69c4467ef5bf9ef4072","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":4.5875810936051895,"warning":null},{"id":"45e7c304d53e99009f735f7b","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":36.5986394557823,"warning":null},{"id":"500c1e917c2929e5059ee4d0","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":31.957671957672,"warning":null},{"id":"574bba91af7fe1baced3aeb5","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":69.9800531914894,"warning":null},{"id":"5937d980c6d4c9fbd919d5c9","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":52.0231213872832,"warning":null},{"id":"362b4a14df3cdc84afbc71f4","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":-68.3833333333333,"warning":null},{"id":"be0266afffdd5c4ea60000a9","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":12.216666666666667,"warning":null},{"id":"ca54d8ad8a33c18db1d947ab","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":15.4970760233918,"warning":null},{"id":"bd7f1bd0f1e410e21b9c5b0a","modelId":"qwen3-vl-4b-thinking","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 VL 4B (Reasoning)","configuration":"Qwen3 VL 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-4b-reasoning","score":1.51515151515152,"warning":null},{"id":"a73112ccabc790faf47fc2ac","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-aime-2025","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.3333333333333,"warning":null},{"id":"5bc12952f1891bb0379aa9c7","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.6666666666667,"warning":null},{"id":"1a3f4483f198c01a748200ab","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"6b9f2418d52839baa7a340b2","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.727272727272705,"warning":null},{"id":"2616cf11c1caf39e02f50c19","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.68767377201112,"warning":null},{"id":"fa9589c76a8ee5e83bd7774c","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.312925170068,"warning":null},{"id":"f7d1263f0ece557ae1ad4f4d","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-livecodebench","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":33.2275132275132,"warning":null},{"id":"68113c3030360a2eb3a4d15a","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-mmlu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.58377659574471,"warning":null},{"id":"adbe6ad89c794eda3ff9c001","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.3410404624277,"warning":null},{"id":"36cb2e462ea1e247f9f8aa78","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-51.8833333333333,"warning":null},{"id":"1cd485ab01810c1389e0f4d6","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.483333333333334,"warning":null},{"id":"5cc01773941f38b549389bb9","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.2397660818713,"warning":null},{"id":"79091a97cdd8c46eb8496f8f","modelId":"qwen3-vl-8b-instruct","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3 VL 8B Instruct","configuration":"Qwen3 VL 8B Instruct; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.27272727272727,"warning":null},{"id":"cc7b91f0e6eb4ba4a8af2d29","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":30.666666666666696,"warning":null},{"id":"6070f6657824dddd8b696352","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":33.3333333333333,"warning":null},{"id":"70e25eae318c15611c90329a","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":0.28571428571428603,"warning":null},{"id":"96396a220f050f9c610a29b7","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":57.8787878787879,"warning":null},{"id":"405328f5d7cbbe8ce56d7b17","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":3.84615384615385,"warning":null},{"id":"8ab8eba51f6cc002414295be","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":39.8639455782313,"warning":null},{"id":"4ecac423e4e3317e14f55ad5","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":35.3439153439153,"warning":null},{"id":"f865331efe53ccc13479e7f9","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":74.85039893617021,"warning":null},{"id":"cffa767ba0a1e16e2db0137e","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":56.647398843930596,"warning":null},{"id":"bc245f925590016dc55fa53a","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":-52.3,"warning":null},{"id":"bce789fbb94ae0834475783e","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":20.433333333333334,"warning":null},{"id":"a0a268dca21cea302e2bdc4b","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":22.5146198830409,"warning":null},{"id":"a6c738ba4e4e4ebda37da9cf","modelId":"qwen3-vl-8b-thinking","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3 VL 8B (Reasoning)","configuration":"Qwen3 VL 8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-vl-8b-reasoning","score":3.78787878787879,"warning":null},{"id":"c79f005bd2c96b3dfac33ffa","modelId":"qwen3.5-0.8b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":8,"warning":null},{"id":"6526c4eb6102f766c4c1062f","modelId":"qwen3.5-0.8b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":9,"warning":null},{"id":"d0bdc890c6710da451dc8600","modelId":"qwen3.5-0.8b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":0,"warning":null},{"id":"60b7d90d07f72044a849d7a4","modelId":"qwen3.5-0.8b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":0,"warning":null},{"id":"07ef03c305071784ff828680","modelId":"qwen3.5-0.8b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":-133.2,"warning":null},{"id":"694b1c4ba5beca31bc0eb98e","modelId":"qwen3.5-0.8b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":-152.17,"warning":null},{"id":"3f1ad55633cc7a58851cd2c9","modelId":"qwen3.5-0.8b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":23.6363636363636,"warning":null},{"id":"3cf0f7313bdb3bb306cf325b","modelId":"qwen3.5-0.8b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":11.1111111111111,"warning":null},{"id":"00910596b4c53cfe534ac0eb","modelId":"qwen3.5-0.8b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":5.09731232622799,"warning":null},{"id":"1c91f30bb30bc36833d46e2a","modelId":"qwen3.5-0.8b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":1.06580166821131,"warning":null},{"id":"dedc8bed9daad7fda2892e8f","modelId":"qwen3.5-0.8b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":21.5646258503401,"warning":null},{"id":"b20cc339a7f979c41b1c036d","modelId":"qwen3.5-0.8b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":21.4965986394558,"warning":null},{"id":"b6fa5f20a494fa9ecedcc7ee","modelId":"qwen3.5-0.8b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":25.6647398843931,"warning":null},{"id":"8aad14fd7116de2c2cfdeeef","modelId":"qwen3.5-0.8b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":25.838150289017296,"warning":null},{"id":"f04c11d1b1e78ba49a626d3e","modelId":"qwen3.5-0.8b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":-88.5833333333333,"warning":null},{"id":"937ba73b35a8ad5eb48af2c0","modelId":"qwen3.5-0.8b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":-54.5166666666667,"warning":null},{"id":"aff956fbf6dee32a521c6a67","modelId":"qwen3.5-0.8b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":4.983333333333333,"warning":null},{"id":"9eb4731b4ea4ea831d5585e4","modelId":"qwen3.5-0.8b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":4.233333333333333,"warning":null},{"id":"c43d78ed5ec033460060cf6c","modelId":"qwen3.5-0.8b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":65.2046783625731,"warning":null},{"id":"ced6927af98788f28fec7064","modelId":"qwen3.5-0.8b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":47.6608187134503,"warning":null},{"id":"fe58f57624f6bfd77e4a529b","modelId":"qwen3.5-0.8b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":0,"warning":null},{"id":"f848e97ce77653c8903415bd","modelId":"qwen3.5-0.8b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":0,"warning":null},{"id":"0557d91e1328599eddeedaa0","modelId":"qwen3.5-0.8b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.5 0.8B (Non-reasoning)","configuration":"Qwen3.5 0.8B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning","score":0.374531835205993,"warning":null},{"id":"6c477d7a9ed5f790dea8bffe","modelId":"qwen3.5-0.8b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.5 0.8B (Reasoning)","configuration":"Qwen3.5 0.8B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-0-8b","score":0,"warning":null},{"id":"c98dbe8888cd28347bc8f571","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":498.94,"warning":null},{"id":"7570031879abad667cd8e969","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":61.33333333333329,"warning":null},{"id":"fd77aa95b9c29c06a6b169cc","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":76.3333333333333,"warning":null},{"id":"f1e2c1476fab5dba5c841fa6","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":5.481116230292565,"warning":null},{"id":"1434c5402cedf4ac2b4da110","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":0.857142857142857,"warning":null},{"id":"4e4780dee2a81d7e9171107a","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":0.571428571428571,"warning":null},{"id":"dc76f6471810c741012070f3","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":3.4000000000000004,"warning":null},{"id":"5f77b4f7b54fff6de405295d","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":833.05,"warning":null},{"id":"128847b55a3390d3459c48df","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":925.2,"warning":null},{"id":"4f7ad991264657d538d51832","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":85.88020833333334,"warning":null},{"id":"89cbf8eb01c2697fd35c27a3","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":89.13020833333334,"warning":null},{"id":"712427354a54a3d7928dc9a0","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":82.7272727272727,"warning":null},{"id":"9b2b75d84b4f7c03bc1bc751","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":85.6565656565657,"warning":null},{"id":"cd859ec8921f41c450fecef8","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":15.940685820203901,"warning":null},{"id":"91a6a7e402d1e1cd935677c2","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":25.2085264133457,"warning":null},{"id":"9e4d9fd1a2574d6a5ae7703f","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":50.8163265306122,"warning":null},{"id":"ad4b717ca4a435c0c7b6bf1a","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":75.7142857142857,"warning":null},{"id":"b5b2eded240cc84231225e2e","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":70.2890173410405,"warning":null},{"id":"633304c9460583efb1a9d123","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":74.971098265896,"warning":null},{"id":"13945cfbd8edd56e3c0efd6b","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":-54.9666666666667,"warning":null},{"id":"c7e647c2a4d2f6427799cdf3","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":-41.5,"warning":null},{"id":"2680ab741c6710c6308ef76b","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":19.116666666666667,"warning":null},{"id":"dca6e42139718103b2bc6718","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":24.366666666666667,"warning":null},{"id":"515eeda369aef75d1b3b90a2","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":39.6990740740741,"warning":null},{"id":"c3bfff836c0b94cd19e1ab01","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":84.5029239766082,"warning":null},{"id":"a3b2b0715095d52d58ac063b","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":93.56725146198829,"warning":null},{"id":"3dd3e9d4d8dcd772354db4ac","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":10.3092783505155,"warning":null},{"id":"591bd1ccff3f9c16ac8904ce","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":15.2577319587629,"warning":null},{"id":"c6b2a6fcceb391533b9ccb6d","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":29.545454545454504,"warning":null},{"id":"dbcbfe85658c4ab468fa9ca3","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":31.060606060606098,"warning":null},{"id":"a29311df8979dbac227d11e3","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.5 122B A10B (Non-reasoning)","configuration":"Qwen3.5 122B A10B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning","score":47.1910112359551,"warning":null},{"id":"928dfca300ef1cd20891bdf3","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":47.565543071160995,"warning":null},{"id":"393b7eb4b3c229026330a49e","modelId":"qwen3.5-122b-a10b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.5 122B A10B (Reasoning)","configuration":"Qwen3.5 122B A10B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-122b-a10b","score":0,"warning":null},{"id":"70ec9dd22c9c9b201c491822","modelId":"qwen3.5-27b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":64,"warning":null},{"id":"b3259eb613b9008d13bfb2fd","modelId":"qwen3.5-27b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":77.6666666666667,"warning":null},{"id":"52b6b150197775cfe5c91b8e","modelId":"qwen3.5-27b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":0.28571428571428603,"warning":null},{"id":"3e51ac2e0bcfc616f60fdbcb","modelId":"qwen3.5-27b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":0.8530612244897959,"warning":null},{"id":"c1822f4f16b355f03b6b133e","modelId":"qwen3.5-27b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":83.82291666666666,"warning":null},{"id":"3a55ccda11cad6f5dc83eb08","modelId":"qwen3.5-27b","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":86.76041666666667,"warning":null},{"id":"4a6498ef78e583463717f583","modelId":"qwen3.5-27b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":84.24242424242419,"warning":null},{"id":"c89518098dd5dccb090f454a","modelId":"qwen3.5-27b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":85.7575757575758,"warning":null},{"id":"78ef779c3fcd29db093d3844","modelId":"qwen3.5-27b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":13.9481000926784,"warning":null},{"id":"4f49cf2685886f6ec4a83da8","modelId":"qwen3.5-27b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":23.9110287303058,"warning":null},{"id":"b21250eb9c4c108f04af43f0","modelId":"qwen3.5-27b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":46.9387755102041,"warning":null},{"id":"9dc289d96ddc9b2f19861742","modelId":"qwen3.5-27b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":75.57823129251699,"warning":null},{"id":"6386fdf31a291d72b80c8bda","modelId":"qwen3.5-27b","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":35.4990583804143,"warning":null},{"id":"8e7a86835734ba4cfd98b502","modelId":"qwen3.5-27b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":70,"warning":null},{"id":"4ae5bffa4ac662eed074e463","modelId":"qwen3.5-27b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":75.028901734104,"warning":null},{"id":"40ff7c5a40a01e803bb1cd8c","modelId":"qwen3.5-27b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":-47.6666666666667,"warning":null},{"id":"55cdfeeabac6031082ecb7d4","modelId":"qwen3.5-27b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":-43.9833333333333,"warning":null},{"id":"6fe875ee0279a564bcd15685","modelId":"qwen3.5-27b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":15.683333333333332,"warning":null},{"id":"8e5f70a0d9b318aca939682c","modelId":"qwen3.5-27b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":20.666666666666668,"warning":null},{"id":"dd74023e1d36e1931e867b89","modelId":"qwen3.5-27b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":87.1345029239766,"warning":null},{"id":"d04bd91f3abbf17a30df7293","modelId":"qwen3.5-27b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":93.859649122807,"warning":null},{"id":"3535372b77b4f10a2aae2f53","modelId":"qwen3.5-27b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 27B (Non-reasoning)","configuration":"Qwen3.5 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b-non-reasoning","score":31.818181818181802,"warning":null},{"id":"87314125e9b141d0f793b80a","modelId":"qwen3.5-27b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.5 27B (Reasoning)","configuration":"Qwen3.5 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-27b","score":32.5757575757576,"warning":null},{"id":"a7c022f322decc2d18aacdf5","modelId":"qwen3.5-2b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":14.000000000000002,"warning":null},{"id":"340251b326024b7a69c3bf39","modelId":"qwen3.5-2b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":21,"warning":null},{"id":"d6189f1ea70832a412f06340","modelId":"qwen3.5-2b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":0,"warning":null},{"id":"98ea8b4e38a123443727892b","modelId":"qwen3.5-2b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":0,"warning":null},{"id":"d62f734d7f7d727dff607f0b","modelId":"qwen3.5-2b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":-130.44,"warning":null},{"id":"4d4a80b838db126050c276e6","modelId":"qwen3.5-2b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":165.7,"warning":null},{"id":"1dc539f5096fa85e6092c50a","modelId":"qwen3.5-2b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":43.8383838383838,"warning":null},{"id":"1efb5443137143050e7ed17e","modelId":"qwen3.5-2b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":45.5555555555556,"warning":null},{"id":"248d8fef7e7a90ae0e4e2295","modelId":"qwen3.5-2b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":4.95829471733086,"warning":null},{"id":"7bd48532b9a85b06d476758b","modelId":"qwen3.5-2b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":2.5949953660797,"warning":null},{"id":"67088604dbeb65c302440afb","modelId":"qwen3.5-2b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":29.115646258503403,"warning":null},{"id":"a54f47fe6f74069debb77e36","modelId":"qwen3.5-2b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":31.496598639455797,"warning":null},{"id":"4dfcabb11e935b9d77c34307","modelId":"qwen3.5-2b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":42.6589595375723,"warning":null},{"id":"f426f85b359f8e2fe9579751","modelId":"qwen3.5-2b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":43.0057803468208,"warning":null},{"id":"0aba9d436f02774f10805fd1","modelId":"qwen3.5-2b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":-83.1333333333333,"warning":null},{"id":"4ebd8fc4a160d868162f9b65","modelId":"qwen3.5-2b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":-60.1833333333333,"warning":null},{"id":"05ae862b6429e595ff8d2b84","modelId":"qwen3.5-2b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":7.383333333333334,"warning":null},{"id":"30a8a589ff73daf9b30088ef","modelId":"qwen3.5-2b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":8.066666666666666,"warning":null},{"id":"60624d170a81e918f4879de3","modelId":"qwen3.5-2b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":81.5789473684211,"warning":null},{"id":"3f24913e7ca1a2f286dbdce8","modelId":"qwen3.5-2b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":69.0058479532164,"warning":null},{"id":"20c954bf67b034614b5f10b0","modelId":"qwen3.5-2b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":3.78787878787879,"warning":null},{"id":"050daa4bef2d46ebbccd176d","modelId":"qwen3.5-2b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":3.78787878787879,"warning":null},{"id":"84335a8349dd1b9d4fa8d0d2","modelId":"qwen3.5-2b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.5 2B (Non-reasoning)","configuration":"Qwen3.5 2B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning","score":0,"warning":null},{"id":"31afa3a5ee4f8ddeb7c59185","modelId":"qwen3.5-2b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.5 2B (Reasoning)","configuration":"Qwen3.5 2B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-2b","score":2.9962546816479403,"warning":null},{"id":"518b3def44f7c280d9c2b344","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":63,"warning":null},{"id":"a6bb3e77e8089018687551e0","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":72,"warning":null},{"id":"0c4fc56597384246a3c510ea","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":0.571428571428571,"warning":null},{"id":"bca3df4c2afb6534b7ab2365","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":0.857142857142857,"warning":null},{"id":"fab70734378c4523a279cdfa","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":740.47,"warning":null},{"id":"52dac326b14ad8274e860038","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":82.421875,"warning":null},{"id":"5b6def33141d74b866cef6e3","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":86.44270833333333,"warning":null},{"id":"ffa5a2f4c3d54a3e22f9ef1e","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":81.9191919191919,"warning":null},{"id":"1a4eac252ecd64ac0ec9fac3","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":84.5454545454545,"warning":null},{"id":"f4bcadbf6a497277a67985f9","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":13.438368860055599,"warning":null},{"id":"e47d94c493c3d8efa18fed87","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":21.0379981464319,"warning":null},{"id":"4b2a00224e4e77c869bb3525","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":44.4897959183673,"warning":null},{"id":"6429639babbd562974064492","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":72.5170068027211,"warning":null},{"id":"7eb289685e2f9e25fba62890","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":21.5160075329567,"warning":null},{"id":"3db7471df67389c685b88dbc","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":69.19075144508669,"warning":null},{"id":"71b06d1e69d3282835e9802d","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":72.6589595375723,"warning":null},{"id":"f638bda28b9ca9b449743a3e","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":-63.0166666666667,"warning":null},{"id":"eebdfc2b391ba014eacbdef5","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":-48.1,"warning":null},{"id":"cce73caaf54d5224ad13f618","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":15.716666666666669,"warning":null},{"id":"1ef6e17ab8bf9c8ccebbad85","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":20.133333333333333,"warning":null},{"id":"956b26763c1cc19ed48e62ee","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":86.2573099415205,"warning":null},{"id":"ef170a6bbbf2157e05ffd6b9","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":89.1812865497076,"warning":null},{"id":"0fe2b426e7191799fd5ad7b0","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":4.948453608247419,"warning":null},{"id":"23b432199e2d041e6d0644b0","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":10.6060606060606,"warning":null},{"id":"f796f8cd0abdbccf18ef98f6","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.5 35B A3B (Reasoning)","configuration":"Qwen3.5 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b","score":26.5151515151515,"warning":null},{"id":"ab038381c16df8d1e510bd8a","modelId":"qwen3.5-35b-a3b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.5 35B A3B (Non-reasoning)","configuration":"Qwen3.5 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning","score":40.8239700374532,"warning":null},{"id":"76d6f70fae4e310ca7590def","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":562.65,"warning":null},{"id":"acf644377690a4fb775a2880","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":15.339233038348098,"warning":null},{"id":"cd62f190593255d149665e0c","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":64.3333333333333,"warning":null},{"id":"dfb69334a23f689f666068a2","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":77.3333333333333,"warning":null},{"id":"135958e9d5c43321eb1d8dbb","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":6.886670023070867,"warning":null},{"id":"75a41b8db9b3590c183008fc","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":0.857142857142857,"warning":null},{"id":"c99d476c058b4a89123fa646","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":1.70612244897959,"warning":null},{"id":"83ea18f7ab43ad1f8b8722de","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":30.88630259623993,"warning":null},{"id":"521a42cd831cbbe5b0e2060b","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":12.2,"warning":null},{"id":"27488df1427b0253553c87df","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":905.4,"warning":null},{"id":"082b89a396ab2c1e7104c310","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":86.515625,"warning":null},{"id":"7e0dbe0e88c6108996e40748","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":90.03645833333334,"warning":null},{"id":"911a594d4aab2c408e3fd321","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":86.0606060606061,"warning":null},{"id":"bc7c4c940825fac880dcc166","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":89.2929292929293,"warning":null},{"id":"98e5e9d937b9d54203e61f95","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":72.3838471558836,"warning":null},{"id":"79dce625ee6f0c2ed9c8245b","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":19.8331788693234,"warning":null},{"id":"ba25e9f3d4d437738db9b852","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":28.962001853568097,"warning":null},{"id":"dfd2256c044cc016cd99b343","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":51.632653061224495,"warning":null},{"id":"a3d4369851bced4c6f9e534d","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":78.7755102040816,"warning":null},{"id":"b395c95b8a65bb01a89133e0","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":34.0866290018832,"warning":null},{"id":"86340fbe3bc82bdd6b9d0f7d","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":52.6589595375723,"warning":null},{"id":"721334010c9ce0613c28fb6c","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":77.28323699421969,"warning":null},{"id":"263ebc7960a8a4cb108bd07c","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":-37.9,"warning":null},{"id":"6a3a254fa11a7c706555dff3","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":-30.75,"warning":null},{"id":"8ff8cfd69dedb3a094f26ced","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":24.516666666666666,"warning":null},{"id":"028e196a79298f6522c3e81f","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":30.8,"warning":null},{"id":"b223f7629fdf1388f9bed2a9","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":44.7916666666667,"warning":null},{"id":"3d1b866c502ba3c2b8352a96","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":83.9181286549708,"warning":null},{"id":"a0cc3fbb604ccc3d914119e9","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":95.6140350877193,"warning":null},{"id":"6f9e10389b596e289112755a","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":13.4020618556701,"warning":null},{"id":"1164bcd5a5aa3712ceea50a7","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 397B A17B (Non-reasoning)","configuration":"Qwen3.5 397B A17B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning","score":35.6060606060606,"warning":null},{"id":"4ce0b8becc8fdf948549228c","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":40.9090909090909,"warning":null},{"id":"642a262fba6eeac8cd6c33a1","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":51.310861423221,"warning":null},{"id":"ee547f794b6f2b28ae9a8028","modelId":"qwen3.5-397b-a17b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.5 397B A17B (Reasoning)","configuration":"Qwen3.5 397B A17B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-397b-a17b","score":0,"warning":null},{"id":"0ea8b264473dc425326ac154","modelId":"qwen3.5-4b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":34.6666666666667,"warning":null},{"id":"897ab118ac1342a924d6112e","modelId":"qwen3.5-4b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":63,"warning":null},{"id":"053597e91079b350b9341d09","modelId":"qwen3.5-4b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":0,"warning":null},{"id":"92b1bbe4bab1236ee4b0635f","modelId":"qwen3.5-4b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":0,"warning":null},{"id":"e91f85c76ca2395e8d16bcd7","modelId":"qwen3.5-4b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":71.2121212121212,"warning":null},{"id":"af08f36e4be4659803ff0480","modelId":"qwen3.5-4b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":77.0707070707071,"warning":null},{"id":"47153236c0ed4b07d1500751","modelId":"qwen3.5-4b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":7.970342910101951,"warning":null},{"id":"642772c958d7cd65f97835cb","modelId":"qwen3.5-4b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":9.91658943466172,"warning":null},{"id":"dce15135abcbf97e2e75e164","modelId":"qwen3.5-4b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":33.265306122449005,"warning":null},{"id":"9f54a0ec86853c159d448797","modelId":"qwen3.5-4b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":51.9727891156463,"warning":null},{"id":"a9e1f9b1809bcd29819a8408","modelId":"qwen3.5-4b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":62.080924855491304,"warning":null},{"id":"a1af20461c5aa98121c402cd","modelId":"qwen3.5-4b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":65.3757225433526,"warning":null},{"id":"e7f8e4594adf9ffcf3ed6e8a","modelId":"qwen3.5-4b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":-74.7333333333333,"warning":null},{"id":"ebe98a5e899b1dcb02f76998","modelId":"qwen3.5-4b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":-58.35,"warning":null},{"id":"ed5f4a1b29b3009ad0ceeed1","modelId":"qwen3.5-4b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":11.216666666666667,"warning":null},{"id":"247c36abe2eb6e790cc417b2","modelId":"qwen3.5-4b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":15.116666666666667,"warning":null},{"id":"d28e385d70e803a765f7fc5c","modelId":"qwen3.5-4b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":87.719298245614,"warning":null},{"id":"50e3c30102eb314283834c71","modelId":"qwen3.5-4b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":92.1052631578947,"warning":null},{"id":"f08a6b8acbba22210e4198c1","modelId":"qwen3.5-4b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":4.32989690721649,"warning":null},{"id":"b2ed8afbd8136fb37d1c54bd","modelId":"qwen3.5-4b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":6.8041237113402095,"warning":null},{"id":"d6fe8b1efef057e8b67e8412","modelId":"qwen3.5-4b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":11.363636363636399,"warning":null},{"id":"3f84ada02ed713f5b4df5e8b","modelId":"qwen3.5-4b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":18.181818181818198,"warning":null},{"id":"5776b4e242b36d7888d749b7","modelId":"qwen3.5-4b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.5 4B (Non-reasoning)","configuration":"Qwen3.5 4B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning","score":21.3483146067416,"warning":null},{"id":"6b92b80ee9f40384f85cdd13","modelId":"qwen3.5-4b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.5 4B (Reasoning)","configuration":"Qwen3.5 4B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-4b","score":25.842696629213503,"warning":null},{"id":"987f147949570e5f033630d1","modelId":"qwen3.5-9b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":46,"warning":null},{"id":"35ab75c2d9610fd9d6afd707","modelId":"qwen3.5-9b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":70,"warning":null},{"id":"51cceb0f761a19498f07f43b","modelId":"qwen3.5-9b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":0.571428571428571,"warning":null},{"id":"93e0ee1fea4ee49c409f7f30","modelId":"qwen3.5-9b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":0.28571428571428603,"warning":null},{"id":"d2c14147928ad0cbac8fa156","modelId":"qwen3.5-9b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":588.42,"warning":null},{"id":"c2a233e0c283bc6f848ab7f8","modelId":"qwen3.5-9b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":78.5858585858586,"warning":null},{"id":"9f70624165f1bfb5534f12d8","modelId":"qwen3.5-9b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":80.60606060606061,"warning":null},{"id":"4d9e271b62a791eb7aa355fb","modelId":"qwen3.5-9b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":9.36051899907322,"warning":null},{"id":"91f1614a6570830ed8587c39","modelId":"qwen3.5-9b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":14.921223354958299,"warning":null},{"id":"405394a5fe3ae5cd4ffb5987","modelId":"qwen3.5-9b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":37.8231292517007,"warning":null},{"id":"b268faf0293cf763ce33c6d5","modelId":"qwen3.5-9b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":66.734693877551,"warning":null},{"id":"bee5fa058648448b9abb72f4","modelId":"qwen3.5-9b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":66.7630057803468,"warning":null},{"id":"3271ebc988e5db1d40b6ee92","modelId":"qwen3.5-9b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":69.2485549132948,"warning":null},{"id":"70c7c662608af8f632662f38","modelId":"qwen3.5-9b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":-70.7,"warning":null},{"id":"5686f65f304b0ae905401fe5","modelId":"qwen3.5-9b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":-53.4666666666667,"warning":null},{"id":"37143e5c779711b1534cd2c0","modelId":"qwen3.5-9b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":13.983333333333334,"warning":null},{"id":"bbb1c791dbb001405e0b3785","modelId":"qwen3.5-9b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":16.416666666666664,"warning":null},{"id":"35b08aa160794079a7760a9a","modelId":"qwen3.5-9b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":85.0877192982456,"warning":null},{"id":"b6ad97d2e6b84fb5bfff38af","modelId":"qwen3.5-9b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":86.8421052631579,"warning":null},{"id":"1ea96f71f7b8acf0e5c92135","modelId":"qwen3.5-9b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":7.01030927835052,"warning":null},{"id":"5a9c2b5e5ea876f9675bbd0c","modelId":"qwen3.5-9b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":18.181818181818198,"warning":null},{"id":"0eb44799cf54377c7b779992","modelId":"qwen3.5-9b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":24.2424242424242,"warning":null},{"id":"9beec241281354166f7f4cdf","modelId":"qwen3.5-9b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.5 9B (Non-reasoning)","configuration":"Qwen3.5 9B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning","score":21.3483146067416,"warning":null},{"id":"71565ab7921a7bff37fd8271","modelId":"qwen3.5-9b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.5 9B (Reasoning)","configuration":"Qwen3.5 9B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-5-9b","score":29.213483146067396,"warning":null},{"id":"c717dab863d029554a546f07","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":52,"warning":null},{"id":"b94f1d2228e900a6c2df44ae","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"4828255fcd543335b20e8178","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.24242424242419,"warning":null},{"id":"5584d2dd8f205f5dfc703398","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.5996292863762696,"warning":null},{"id":"7ed7cbd32da3164f960078dd","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":37.9591836734694,"warning":null},{"id":"f03d2e976501ce3b51c34286","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":64.73988439306359,"warning":null},{"id":"ce044099dd1a13b985395372","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":-65.0666666666667,"warning":null},{"id":"de3e87fa1b992b3a661f0744","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.649999999999999,"warning":null},{"id":"4305e3ee57626ca07733f9a1","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.5029239766082,"warning":null},{"id":"0e201fd8e88804cf432985b7","modelId":"qwen3.5-omni-flash","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Flash","configuration":"Qwen3.5 Omni Flash; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.33333333333333,"warning":null},{"id":"c82039a80845dab3eadfacd8","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.66666666666671,"warning":null},{"id":"2e75afb685d3a3295079aa9b","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.5632653061224491,"warning":null},{"id":"0f1a5a784a71c9e6676ed3fd","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.6262626262626,"warning":null},{"id":"4d99610acf5319007bb0aeea","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.874884151992601,"warning":null},{"id":"ef689030a893d35e97f6f3d2","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":51.156462585034,"warning":null},{"id":"4db50a094c083851e4fab68c","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":70.52023121387279,"warning":null},{"id":"62d333463f4ce6b2f02693ee","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":-13.1166666666667,"warning":null},{"id":"047dd20376f5c65c5e1a899a","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.433333333333334,"warning":null},{"id":"75ce6997f9a7d90791f02ea5","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.3040935672515,"warning":null},{"id":"08f342f50a739b3ac9528085","modelId":"qwen3.5-omni-plus","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.5 Omni Plus","configuration":"Qwen3.5 Omni Plus; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/qwen3-5-omni-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.2121212121212,"warning":null},{"id":"90ba7abd10ab7bfb8b7e1265","modelId":"qwen3.6-27b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":812.14,"warning":null},{"id":"9407d449239c38058843fede","modelId":"qwen3.6-27b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":66.6666666666667,"warning":null},{"id":"e7a488abcf660ae289f3a24f","modelId":"qwen3.6-27b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":77.3333333333333,"warning":null},{"id":"69a809df0aeb1b2ecf654222","modelId":"qwen3.6-27b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":11.045223588713588,"warning":null},{"id":"f8f423f444a94a81a9c1a0a8","modelId":"qwen3.6-27b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":0.857142857142857,"warning":null},{"id":"536bcb7f59ec5628dcee1463","modelId":"qwen3.6-27b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":1.1428571428571401,"warning":null},{"id":"448b575dcd1acd2a60fbb4cd","modelId":"qwen3.6-27b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":11,"warning":null},{"id":"6121ad64b0d2129d07648388","modelId":"qwen3.6-27b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":1042.8,"warning":null},{"id":"0b4a0dd24a68180a17e59c72","modelId":"qwen3.6-27b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":1068.87,"warning":null},{"id":"9f3b5a5650f0028b75e6627a","modelId":"qwen3.6-27b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":82.9292929292929,"warning":null},{"id":"ab44e7ebb36589f6af440d58","modelId":"qwen3.6-27b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":84.24242424242419,"warning":null},{"id":"055fd1f94ed84235b0dd236b","modelId":"qwen3.6-27b","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":82.2984512954118,"warning":null},{"id":"511a91b9c33047739bda7f2e","modelId":"qwen3.6-27b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":15.060240963855401,"warning":null},{"id":"f8e8bc36191c7551f6b5cc4d","modelId":"qwen3.6-27b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":23.0769230769231,"warning":null},{"id":"5a0cb4fe77de2668f3a7851d","modelId":"qwen3.6-27b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":45.7142857142857,"warning":null},{"id":"147cff2e7b77dbe7a3ab9a02","modelId":"qwen3.6-27b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":67.5510204081633,"warning":null},{"id":"01d2afdc9f3d7512a2797f1c","modelId":"qwen3.6-27b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":71.73410404624279,"warning":null},{"id":"1f330c240a2e147daf36750e","modelId":"qwen3.6-27b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":74.6242774566474,"warning":null},{"id":"3388bc6451fc50d48d32f80f","modelId":"qwen3.6-27b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":-53.2,"warning":null},{"id":"a670029bf642d55d2f29a869","modelId":"qwen3.6-27b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":-20.0166666666667,"warning":null},{"id":"8c5b10be361e3b52f4be8621","modelId":"qwen3.6-27b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":16.716666666666665,"warning":null},{"id":"3ccb2b0ee8fb9a12d8d0b958","modelId":"qwen3.6-27b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":19.6,"warning":null},{"id":"db7758f0177deb0686de0fde","modelId":"qwen3.6-27b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":42.8240740740741,"warning":null},{"id":"ef1ca5e4c1d0640e21632a3b","modelId":"qwen3.6-27b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":93.56725146198829,"warning":null},{"id":"e8af44f1827fd2b34c9c1f57","modelId":"qwen3.6-27b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":94.15204678362569,"warning":null},{"id":"3bdf7a8c944fd163c8dd47a8","modelId":"qwen3.6-27b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":9.27835051546392,"warning":null},{"id":"b302521289de79298a4c4a11","modelId":"qwen3.6-27b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":16.7010309278351,"warning":null},{"id":"319dd147ad8ab4256d9e920a","modelId":"qwen3.6-27b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":21.2121212121212,"warning":null},{"id":"3e197f94e3c030d6c4c768f4","modelId":"qwen3.6-27b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":34.8484848484849,"warning":null},{"id":"c4e9d38c2e0b145c31db613b","modelId":"qwen3.6-27b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.6 27B (Non-reasoning)","configuration":"Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning","score":51.310861423221,"warning":null},{"id":"c666c345c763a37020abfa2b","modelId":"qwen3.6-27b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":60.674157303370805,"warning":null},{"id":"44ce799a8b6dfb3736957ecf","modelId":"qwen3.6-27b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.6 27B (Reasoning)","configuration":"Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b","score":0,"warning":null},{"id":"abc2c041b38dbf315527e97e","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":711.46,"warning":null},{"id":"fa3d8f5b093a68f35e1410fa","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":64.3333333333333,"warning":null},{"id":"fc1010f44b620abdf26e9a2e","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":71.6666666666667,"warning":null},{"id":"2e3c0a8de99217d5789e6006","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":5.2085656145058845,"warning":null},{"id":"5e00d1d331c11537440b8cc4","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":0,"warning":null},{"id":"7ade4f0426c6245254429d02","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":0.28571428571428603,"warning":null},{"id":"6744996241ae0d03122039af","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":6.6000000000000005,"warning":null},{"id":"ba9f4904226ab6c8af5d97a7","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":953.19,"warning":null},{"id":"010d7241edecdc97c2517e80","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":990.51,"warning":null},{"id":"94ac74e00d580eaeef1daa5e","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":81.7171717171717,"warning":null},{"id":"22f962a63a0b5ff81b811a76","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":84.14141414141419,"warning":null},{"id":"2140cb653135c824c77c5a52","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":13.9017608897127,"warning":null},{"id":"65e97e60b864e0aeedbb1d77","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":22.242817423540302,"warning":null},{"id":"39d90e1de15d33cb62e706b4","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":36.190476190476204,"warning":null},{"id":"4082640dc825a629a68d77ca","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":64.3537414965986,"warning":null},{"id":"e3238199ea24918db578f48a","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":71.0404624277457,"warning":null},{"id":"f021164defbe4c063630dc02","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":75.028901734104,"warning":null},{"id":"eacdde9b4ef2d608c6c5db66","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":-60.0166666666667,"warning":null},{"id":"bd2c4bd715ab130b5a7baa31","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":-22.1833333333333,"warning":null},{"id":"60d26e69fe34430556065e73","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":16.716666666666665,"warning":null},{"id":"794bebda292e3704b05c0a0d","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":18.816666666666666,"warning":null},{"id":"ed5c9e27d2893228f1baa185","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":36.5740740740741,"warning":null},{"id":"309240dbc037d56fbcb6b7b9","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":85.0877192982456,"warning":null},{"id":"5fd472847cba72707397312a","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":95.3216374269006,"warning":null},{"id":"ec8ec75f74ad4b9274f062ed","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":5.36082474226804,"warning":null},{"id":"2c7fa9fd818e2d0e84c1b39f","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":9.27835051546392,"warning":null},{"id":"948bee28800b4658a01a25ed","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":25.7575757575758,"warning":null},{"id":"034278450a24f60e27015b1a","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":34.8484848484849,"warning":null},{"id":"e2153c542957bfe883a91411","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.6 35B A3B (Non-reasoning)","configuration":"Qwen3.6 35B A3B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning","score":41.5730337078652,"warning":null},{"id":"34bbe6472870bee2df06ea3d","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":44.9438202247191,"warning":null},{"id":"50d69af85898178490384a19","modelId":"qwen3.6-35b-a3b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.6 35B A3B (Reasoning)","configuration":"Qwen3.6 35B A3B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-35b-a3b","score":0,"warning":null},{"id":"93638a70fa1bd2eb2973ebf3","modelId":"qwen3.6-plus","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":78.3333333333333,"warning":null},{"id":"d22f57bac206134b0895962b","modelId":"qwen3.6-plus","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.85714285714286,"warning":null},{"id":"b350b5042596f5ed2bb3dff4","modelId":"qwen3.6-plus","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":1065.83,"warning":null},{"id":"0ea5751656e8fdb09476cde1","modelId":"qwen3.6-plus","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":88.1818181818182,"warning":null},{"id":"b17e297aaf4c740f79979be4","modelId":"qwen3.6-plus","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":27.8498609823911,"warning":null},{"id":"e50ff97c4425d2ebbf1223b7","modelId":"qwen3.6-plus","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.1700680272109,"warning":null},{"id":"3eb7381b382205fba1f0fe65","modelId":"qwen3.6-plus","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.9768786127168,"warning":null},{"id":"a62bce89fdb4d3abd526eb43","modelId":"qwen3.6-plus","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.883333333333333,"warning":null},{"id":"45436b8af16d8065711b3a43","modelId":"qwen3.6-plus","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":26.38333333333333,"warning":null},{"id":"21437c6d099de4a38389b43d","modelId":"qwen3.6-plus","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":97.6608187134503,"warning":null},{"id":"489ee597fc16833ca2058214","modelId":"qwen3.6-plus","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.8247422680412,"warning":null},{"id":"59391278a6dd9fcc53640072","modelId":"qwen3.6-plus","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.9393939393939,"warning":null},{"id":"08465a135acc9707f92293e4","modelId":"qwen3.6-plus","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.6 Plus","configuration":"Qwen3.6 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-6-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":61.4232209737828,"warning":null},{"id":"9ad3e1f3423393d133f7b393","modelId":"qwen3.7-max","benchmarkId":"aa-aa-analyst-agent","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.75,"warning":null},{"id":"3965321e80f30621ed470e8f","modelId":"qwen3.7-max","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":917.94,"warning":null},{"id":"6f305c1c4e37d27e61f689a4","modelId":"qwen3.7-max","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":79,"warning":null},{"id":"2a657017fa2edaf82956db37","modelId":"qwen3.7-max","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.976890336173604,"warning":null},{"id":"870c96fc00ec0feb2f32dfb8","modelId":"qwen3.7-max","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.4285714285714,"warning":null},{"id":"297e5cb842ccbb88ca618949","modelId":"qwen3.7-max","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":45.00149209191286,"warning":null},{"id":"6e30bc47e35c2d4bf9e1eb0a","modelId":"qwen3.7-max","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.6,"warning":null},{"id":"4be42440d0557b1c75f0a0e8","modelId":"qwen3.7-max","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":1189.86,"warning":null},{"id":"2307b5abe75cf7cfc52c4986","modelId":"qwen3.7-max","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":92.32323232323229,"warning":null},{"id":"0dabc74907ca4392d902bfc6","modelId":"qwen3.7-max","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":83.4274135185989,"warning":null},{"id":"4c0e30a179da19a4e7f3bfa4","modelId":"qwen3.7-max","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.5004633920297,"warning":null},{"id":"1b9110161c8cc2b19d6f2080","modelId":"qwen3.7-max","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.5442176870748,"warning":null},{"id":"3a4875b885ec50b15c8693a6","modelId":"qwen3.7-max","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.4670433145009,"warning":null},{"id":"4355bc5b1225c68cd10d5191","modelId":"qwen3.7-max","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.4833333333333,"warning":null},{"id":"7baa3c2e804282809b3e549f","modelId":"qwen3.7-max","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.133333333333336,"warning":null},{"id":"9ca0c4c478ac4a52d15f4f0c","modelId":"qwen3.7-max","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":49.537037037037,"warning":null},{"id":"41227f76cdd36be7d5ea2c15","modelId":"qwen3.7-max","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":94.7368421052632,"warning":null},{"id":"d5af817cd3c32f49b5984987","modelId":"qwen3.7-max","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.7525773195876,"warning":null},{"id":"f157407c28400fa2fac4f930","modelId":"qwen3.7-max","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.7575757575758,"warning":null},{"id":"f2e2da41746ec055e02aecf7","modelId":"qwen3.7-max","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":74.53183520599251,"warning":null},{"id":"3196d9aa5b9ad70ac47a6b65","modelId":"qwen3.7-max","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.7 Max","configuration":"Qwen3.7 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-max; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.51515151515152,"warning":null},{"id":"c7aa87b0fb7770deb506f5b6","modelId":"qwen3.7-plus","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":912.73,"warning":null},{"id":"9cedf613da4351040d1e92db","modelId":"qwen3.7-plus","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.4188790560472,"warning":null},{"id":"963077a2374e6ded6adff9ed","modelId":"qwen3.7-plus","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":73,"warning":null},{"id":"0fbe559fc5ce72b2613c6245","modelId":"qwen3.7-plus","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.391220980015497,"warning":null},{"id":"a2ed5103fa0df8f7cfd0375e","modelId":"qwen3.7-plus","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.14285714285714,"warning":null},{"id":"5a1345f8a31fdf95832c6a86","modelId":"qwen3.7-plus","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":40.55505819158461,"warning":null},{"id":"defc9a7127c75101a72a75b1","modelId":"qwen3.7-plus","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":12.2,"warning":null},{"id":"f961b4367e7279d1907c103f","modelId":"qwen3.7-plus","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":885.83,"warning":null},{"id":"ccb7687f63b0c6d5ac1eecd7","modelId":"qwen3.7-plus","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":90,"warning":null},{"id":"35f5a4346e3ce8ee05a96b41","modelId":"qwen3.7-plus","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.7918656824432,"warning":null},{"id":"79ac3364e000c6cd672fbd91","modelId":"qwen3.7-plus","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.6348470806302,"warning":null},{"id":"4945d0ef68fe56561ca877da","modelId":"qwen3.7-plus","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.9591836734694,"warning":null},{"id":"5d2243ff9337e95a2dd7edc4","modelId":"qwen3.7-plus","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.44444444444444,"warning":null},{"id":"b7a0d9322ace326caf2db310","modelId":"qwen3.7-plus","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.4624277456647,"warning":null},{"id":"1d6fc7a9f857efb4ea8a4d09","modelId":"qwen3.7-plus","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.08333333333333,"warning":null},{"id":"987027dbf8f699071447f03f","modelId":"qwen3.7-plus","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":22.516666666666666,"warning":null},{"id":"3ea57b2c6129ce72f6450114","modelId":"qwen3.7-plus","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.064814814814795,"warning":null},{"id":"85e6bb415f16c9b56e03fef9","modelId":"qwen3.7-plus","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":92.9824561403509,"warning":null},{"id":"97acc2df5e24a7cda1402355","modelId":"qwen3.7-plus","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":17.5257731958763,"warning":null},{"id":"3f7cbb594499981fc7681ee1","modelId":"qwen3.7-plus","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":46.969696969697,"warning":null},{"id":"85fb53fb3b36f8e29d58711e","modelId":"qwen3.7-plus","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":61.0486891385768,"warning":null},{"id":"eb42639192e6f3b2becf6ef8","modelId":"qwen3.7-plus","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.7 Plus","configuration":"Qwen3.7 Plus; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-7-plus; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.01010101010101,"warning":null},{"id":"9444d9b9256a7cd2e2918fda","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1438.5,"warning":null},{"id":"27df0e5138bd5f8d7c930041","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.3333333333333,"warning":null},{"id":"ff0811d93cce836318787010","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":57.247376545822206,"warning":null},{"id":"190e54337ed7afe809ef9033","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":20,"warning":null},{"id":"8bba6cdadf34a978f2014270","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":47.35899731423456,"warning":null},{"id":"1c96bec87c5b1f7f05ecaba5","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.6,"warning":null},{"id":"56238879c4a50c74046c5756","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1627.82,"warning":null},{"id":"a99e4925b9bb3d9b381f52ca","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":93.53535353535351,"warning":null},{"id":"1305aa179987856b5864ef92","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":42.4467099165894,"warning":null},{"id":"6ea79d9a87da1399709e4fe4","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"215c0a040e1f469b97f5f0d1","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":4.31666666666667,"warning":null},{"id":"3cb914a9e40ec3c843a24080","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":31.25,"warning":null},{"id":"845e3104f356e8046a04495f","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":54.050925925925895,"warning":null},{"id":"72e55893e37d975afe2e59af","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":49.0721649484536,"warning":null},{"id":"cc3f9005dc869c1b5547b4f0","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":82.0224719101124,"warning":null},{"id":"db82321f46121c82cac0b9d8","modelId":"qwen3.8-2.4t-a95b","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.8 2.4T A95B","configuration":"Qwen3.8 2.4T A95B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.1111111111111,"warning":null},{"id":"b719f9e8b09e209b85b1a1f1","modelId":"qwen3.8-27b","benchmarkId":"aa-aa-briefcase","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":1277.44,"warning":null},{"id":"86bee422ce1951283a6eee66","modelId":"qwen3.8-27b","benchmarkId":"aa-aa-briefcase","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":1375.7,"warning":null},{"id":"fd81cc23b91a66f00c3f8c04","modelId":"qwen3.8-27b","benchmarkId":"aa-aa-briefcase","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":1397.82,"warning":null},{"id":"19b0485cf1bfd20332a6d197","modelId":"qwen3.8-27b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":77.3333333333333,"warning":null},{"id":"6f61543be64902b815e4737c","modelId":"qwen3.8-27b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":79.6666666666667,"warning":null},{"id":"1ec9d3b365ddb11b5239f4ac","modelId":"qwen3.8-27b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":69.3333333333333,"warning":null},{"id":"945088724c81324ac8f23ad1","modelId":"qwen3.8-27b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":82,"warning":null},{"id":"b7c106e9436bf259deec9c01","modelId":"qwen3.8-27b","benchmarkId":"aa-automationbench-aa","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":30.103295303433768,"warning":null},{"id":"a11d07d00f37c70adccad7cc","modelId":"qwen3.8-27b","benchmarkId":"aa-automationbench-aa","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":40.252101015938635,"warning":null},{"id":"03c3f0f74b136d54e7ef30d7","modelId":"qwen3.8-27b","benchmarkId":"aa-automationbench-aa","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":48.24244368224193,"warning":null},{"id":"ee9a12dcf44b9eb2c8f122e9","modelId":"qwen3.8-27b","benchmarkId":"aa-critpt","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":0,"warning":null},{"id":"74444598a5429e7c932561c6","modelId":"qwen3.8-27b","benchmarkId":"aa-critpt","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":0,"warning":null},{"id":"db23778fb38a738162c3739d","modelId":"qwen3.8-27b","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":0.28571428571428603,"warning":null},{"id":"e5d09b30a62641fd043c20be","modelId":"qwen3.8-27b","benchmarkId":"aa-critpt","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":5.42857142857143,"warning":null},{"id":"1493b163b0b799c95096ee25","modelId":"qwen3.8-27b","benchmarkId":"aa-enterprise-ops-gym-aa","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":44.225604297224706,"warning":null},{"id":"62b4a85d1ee9d190988264d3","modelId":"qwen3.8-27b","benchmarkId":"aa-gdp-pdf","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":10.4,"warning":null},{"id":"f34a69bcff3a02bebb787c16","modelId":"qwen3.8-27b","benchmarkId":"aa-gdp-pdf","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":12.8,"warning":null},{"id":"ee9581a4eac628d2891dc86e","modelId":"qwen3.8-27b","benchmarkId":"aa-gdp-pdf","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":16.400000000000002,"warning":null},{"id":"5a3eb5d8a89b57365845de17","modelId":"qwen3.8-27b","benchmarkId":"aa-gdpval-aa","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":1402.54,"warning":null},{"id":"65e57ec334f4df9a4b3617de","modelId":"qwen3.8-27b","benchmarkId":"aa-gdpval-aa","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":1430.39,"warning":null},{"id":"5277a02a57030f1526653932","modelId":"qwen3.8-27b","benchmarkId":"aa-gdpval-aa","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":1136.81,"warning":null},{"id":"5c4410504b14db530e88e38c","modelId":"qwen3.8-27b","benchmarkId":"aa-gdpval-aa","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":1463.25,"warning":null},{"id":"a3d2839bcc71d9bb7edd251b","modelId":"qwen3.8-27b","benchmarkId":"aa-gpqa-diamond","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":84.5454545454545,"warning":null},{"id":"46f816a1e1c7631080155c28","modelId":"qwen3.8-27b","benchmarkId":"aa-gpqa-diamond","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":84.5454545454545,"warning":null},{"id":"149b9aed78a8b393be1ac340","modelId":"qwen3.8-27b","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":81.8181818181818,"warning":null},{"id":"aaf557a7b57bbf68838151e6","modelId":"qwen3.8-27b","benchmarkId":"aa-gpqa-diamond","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":90.5050505050505,"warning":null},{"id":"c14c8032c2a9477a91be02e2","modelId":"qwen3.8-27b","benchmarkId":"aa-humanitys-last-exam","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":14.040778498609798,"warning":null},{"id":"45789802fc3895cbe31eb8ed","modelId":"qwen3.8-27b","benchmarkId":"aa-humanitys-last-exam","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":14.0871177015755,"warning":null},{"id":"2b5e2ca909dc461cdc38a556","modelId":"qwen3.8-27b","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":12.1408711770158,"warning":null},{"id":"30ac372f7fb03d555903153b","modelId":"qwen3.8-27b","benchmarkId":"aa-humanitys-last-exam","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":33.920296570899,"warning":null},{"id":"395a465b3f1f60977613b6a5","modelId":"qwen3.8-27b","benchmarkId":"aa-mlcr-aa","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":21.6666666666667,"warning":null},{"id":"0a5895e3fbece4eaf4323c47","modelId":"qwen3.8-27b","benchmarkId":"aa-mmmu-pro","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":73.757225433526,"warning":null},{"id":"7ff9c733e52387a7a5d3d1a1","modelId":"qwen3.8-27b","benchmarkId":"aa-mmmu-pro","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":74.1618497109827,"warning":null},{"id":"135f2e02482f3c68bbcd884a","modelId":"qwen3.8-27b","benchmarkId":"aa-mmmu-pro","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":69.9421965317919,"warning":null},{"id":"8dcde2b92c7f4ab70a64854d","modelId":"qwen3.8-27b","benchmarkId":"aa-mmmu-pro","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":76.3005780346821,"warning":null},{"id":"a03d4ad0bd3a804b66a9b24a","modelId":"qwen3.8-27b","benchmarkId":"aa-omniscience","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":-26.6666666666667,"warning":null},{"id":"5d47e816e792f15b47d77830","modelId":"qwen3.8-27b","benchmarkId":"aa-omniscience","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":-36.15,"warning":null},{"id":"369ef6b3e1de52e3da9e761d","modelId":"qwen3.8-27b","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":-7.95,"warning":null},{"id":"035420d05ec2253ac495caa6","modelId":"qwen3.8-27b","benchmarkId":"aa-omniscience","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":-9.98333333333333,"warning":null},{"id":"133afe96fba2e67c6aaa2ac0","modelId":"qwen3.8-27b","benchmarkId":"aa-omniscience-accuracy","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":17.133333333333333,"warning":null},{"id":"3ffc6bf6a010111fb752652b","modelId":"qwen3.8-27b","benchmarkId":"aa-omniscience-accuracy","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":18.35,"warning":null},{"id":"59fcf8705623283774907cd0","modelId":"qwen3.8-27b","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":8.583333333333334,"warning":null},{"id":"63e26c5f81acf9016f061b8c","modelId":"qwen3.8-27b","benchmarkId":"aa-omniscience-accuracy","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":15.583333333333332,"warning":null},{"id":"811f19db6bfb655cc3a26d44","modelId":"qwen3.8-27b","benchmarkId":"aa-scicode","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":40.046296296296305,"warning":null},{"id":"0573143394705aeca6cd7ca5","modelId":"qwen3.8-27b","benchmarkId":"aa-scicode","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":39.0046296296296,"warning":null},{"id":"f0b6f28261f842ffd221371f","modelId":"qwen3.8-27b","benchmarkId":"aa-scicode","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":36.2268518518519,"warning":null},{"id":"4fc56c008f264520aa21e8a3","modelId":"qwen3.8-27b","benchmarkId":"aa-scicode","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":46.6435185185185,"warning":null},{"id":"4dc87aed8e48c77a76e5b0ae","modelId":"qwen3.8-27b","benchmarkId":"aa-tau3-banking","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":32.1649484536082,"warning":null},{"id":"a678d60ab97b56c3739d98dd","modelId":"qwen3.8-27b","benchmarkId":"aa-tau3-banking","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":47.4226804123711,"warning":null},{"id":"ebdcbf46dd03ef58d97834a3","modelId":"qwen3.8-27b","benchmarkId":"aa-tau3-banking","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":20,"warning":null},{"id":"d38663513b05928bf62032bf","modelId":"qwen3.8-27b","benchmarkId":"aa-tau3-banking","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":48.041237113402104,"warning":null},{"id":"6ded7cba3e8c6acf2681b027","modelId":"qwen3.8-27b","benchmarkId":"aa-terminalbench-v2-1","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":67.4157303370786,"warning":null},{"id":"16a685d097b9257bece582b3","modelId":"qwen3.8-27b","benchmarkId":"aa-terminalbench-v2-1","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":65.1685393258427,"warning":null},{"id":"06d60c6c4c5a2369cf9b0093","modelId":"qwen3.8-27b","benchmarkId":"aa-terminalbench-v2-1","level":"non-reasoning","sourceLabel":"Qwen3.8 27B (Non-reasoning)","configuration":"Qwen3.8 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-non-reasoning","score":49.063670411985,"warning":null},{"id":"fd22f232820d993578b5699c","modelId":"qwen3.8-27b","benchmarkId":"aa-terminalbench-v2-1","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":79.7752808988764,"warning":null},{"id":"125ea9db3e69a8e08b2b0147","modelId":"qwen3.8-27b","benchmarkId":"aa-terminalbench-v4-0","level":"low","sourceLabel":"Qwen3.8 27B (low)","configuration":"Qwen3.8 27B (low); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-low","score":2.52525252525253,"warning":null},{"id":"72b5f2cbe66abb63e4d32772","modelId":"qwen3.8-27b","benchmarkId":"aa-terminalbench-v4-0","level":"medium","sourceLabel":"Qwen3.8 27B (medium)","configuration":"Qwen3.8 27B (medium); Model source: https://artificialanalysis.ai/models/qwen3-8-27b-medium","score":5.05050505050505,"warning":null},{"id":"d6892a199b887a3e762e71aa","modelId":"qwen3.8-27b","benchmarkId":"aa-terminalbench-v4-0","level":"xhigh","sourceLabel":"Qwen3.8 27B (xhigh)","configuration":"Qwen3.8 27B (xhigh); Model source: https://artificialanalysis.ai/models/qwen3-8-27b","score":5.55555555555556,"warning":null},{"id":"e1b2c60fd4d4f016e95db681","modelId":"qwen3.8-flash-next","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":1586.58,"warning":null},{"id":"1af1c14074eae9ab67bac2a5","modelId":"qwen3.8-flash-next","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.6666666666667,"warning":null},{"id":"100eb437023dad366f563363","modelId":"qwen3.8-flash-next","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":55.9083218951688,"warning":null},{"id":"d7c9d2a0fd1760ad961f399e","modelId":"qwen3.8-flash-next","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.1428571428571,"warning":null},{"id":"e21724aca11f3198eedbc6e7","modelId":"qwen3.8-flash-next","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":15.6,"warning":null},{"id":"6deae3600f54d6cccf5a0be9","modelId":"qwen3.8-flash-next","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":1647.02,"warning":null},{"id":"e02c83aacb3a00e840a9af72","modelId":"qwen3.8-flash-next","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":92.32323232323229,"warning":null},{"id":"16d3fe3f51d36c136b12f8b5","modelId":"qwen3.8-flash-next","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":38.044485634847106,"warning":null},{"id":"653bd0d5164de68aa04fc91e","modelId":"qwen3.8-flash-next","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":79.7687861271676,"warning":null},{"id":"19beb3218856ab5fe419a3c9","modelId":"qwen3.8-flash-next","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":-9.71666666666667,"warning":null},{"id":"6cd571f906fa29b42e3b182b","modelId":"qwen3.8-flash-next","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":24.5,"warning":null},{"id":"107f8908a0e4a7c541544f2f","modelId":"qwen3.8-flash-next","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.578703703703695,"warning":null},{"id":"e600574b71b21a5cafdd9d49","modelId":"qwen3.8-flash-next","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":45.360824742268,"warning":null},{"id":"58c528b02767f71c2ef600cc","modelId":"qwen3.8-flash-next","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":86.1423220973783,"warning":null},{"id":"50e7110e3b20dacde3b37e1e","modelId":"qwen3.8-flash-next","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Qwen3.8-Flash-Next","configuration":"Qwen3.8-Flash-Next; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-flash-next; Mode from evaluator isReasoning metadata; effort budget not specified","score":25.2525252525253,"warning":null},{"id":"ac0ddd5b5ae8b79a4ddc80c8","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-aime-2025","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":84.6666666666667,"warning":null},{"id":"fd77bc1467dfe4486490d845","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":61.33333333333329,"warning":null},{"id":"9e8614db68b3d211029ec88c","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"841cd6af604c06ea92463ab9","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":77.90104166666667,"warning":null},{"id":"58e1dd8e3731504b07c5dfad","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.6262626262626,"warning":null},{"id":"17b50474af561818c94ee00f","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.870250231696021,"warning":null},{"id":"8b0760998291d4c24b0a22a4","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":41.9047619047619,"warning":null},{"id":"ed488162479393e23b14bace","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-livecodebench","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":76.5079365079365,"warning":null},{"id":"b64d48fbd23f04ac8eebe4df","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-mmlu-pro","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":81.5408909574468,"warning":null},{"id":"12f82b95be07624d144534f1","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":-52.4666666666667,"warning":null},{"id":"044431bb8ae976aa42349a89","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.2,"warning":null},{"id":"1de2302eae9a29fe88d82846","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":49.4152046783626,"warning":null},{"id":"bff8dce7b47e199123fa7411","modelId":"seed-oss-36b-instruct","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Seed-OSS-36B-Instruct","configuration":"Seed-OSS-36B-Instruct; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/seed-oss-36b-instruct; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.81818181818182,"warning":null},{"id":"6ed7251fc836a13b8bda6c2c","modelId":"solar-open-100b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":41,"warning":null},{"id":"75cb2fffbf1adac440b9c082","modelId":"solar-open-100b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":0,"warning":null},{"id":"1d3eac54d4adb7c21226a10d","modelId":"solar-open-100b","benchmarkId":"aa-global-mmlu-lite","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":81.58333333333334,"warning":null},{"id":"6cc904fe0b8921985e0fbd2c","modelId":"solar-open-100b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":65.6565656565657,"warning":null},{"id":"b239e9e2e4dc4d96acb069c2","modelId":"solar-open-100b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":10.4263206672845,"warning":null},{"id":"7c6f3969a3bfb58f59e504a9","modelId":"solar-open-100b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":57.687074829931994,"warning":null},{"id":"786415bc21ec9ec2f6bbed5e","modelId":"solar-open-100b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":-54.5,"warning":null},{"id":"c2348de9a5afccbf97deb29c","modelId":"solar-open-100b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":18.53333333333333,"warning":null},{"id":"65366e28efa37bd0fc9304a3","modelId":"solar-open-100b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":48.245614035087705,"warning":null},{"id":"f28b14f230ca174c3535e105","modelId":"solar-open-100b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Solar Open 100B (Reasoning)","configuration":"Solar Open 100B (Reasoning); Model source: https://artificialanalysis.ai/models/solar-open-100b-reasoning","score":2.27272727272727,"warning":null},{"id":"541af6b48e4dd025e681a015","modelId":"solar-open2-250b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.6666666666667,"warning":null},{"id":"e9ccf812e35cb29f130dc31f","modelId":"solar-open2-250b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.71428571428571,"warning":null},{"id":"7460383ca07504611e1fa311","modelId":"solar-open2-250b","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":1052.82,"warning":null},{"id":"b4701fb10f02abf0859e9d2b","modelId":"solar-open2-250b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":85.6565656565657,"warning":null},{"id":"f5a8e2ba8b2c9185ba6e9900","modelId":"solar-open2-250b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":28.544949026876697,"warning":null},{"id":"f706a5ffc62ecf11d8aa11fc","modelId":"solar-open2-250b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-1.76666666666667,"warning":null},{"id":"e1c44575202fa0dd5bbff5db","modelId":"solar-open2-250b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.833333333333332,"warning":null},{"id":"793184ef1385ac9eccdc0fef","modelId":"solar-open2-250b","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":48.032407407407405,"warning":null},{"id":"b72d75ebece38f24171ed19a","modelId":"solar-open2-250b","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.6494845360825,"warning":null},{"id":"b2c76ce1b70fddc006955b7a","modelId":"solar-open2-250b","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Solar Open2 250B","configuration":"Solar Open2 250B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-open2-250b; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.194756554307105,"warning":null},{"id":"12d55ff49d0941524b330102","modelId":"solar-pro3-260323","benchmarkId":"aa-aa-briefcase","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":121.9,"warning":null},{"id":"90113e320325aad453d0207c","modelId":"solar-pro3-260323","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":32.3333333333333,"warning":null},{"id":"e1354b01691573102e86fac0","modelId":"solar-pro3-260323","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.49734242022629577,"warning":null},{"id":"2e642eb8e589b310afece9d1","modelId":"solar-pro3-260323","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"4762ee05df5eb38cf2f0a883","modelId":"solar-pro3-260323","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":1.6,"warning":null},{"id":"b062943b8fc21bef0f9e486a","modelId":"solar-pro3-260323","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":446.94,"warning":null},{"id":"087acac2342dac2567f325c0","modelId":"solar-pro3-260323","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.42424242424241,"warning":null},{"id":"f6cc07e7f169228137b2d3cf","modelId":"solar-pro3-260323","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.2873030583874,"warning":null},{"id":"6f529a5f931819bad160b6db","modelId":"solar-pro3-260323","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":71.2018140589569,"warning":null},{"id":"cef5e234850298a63380a52c","modelId":"solar-pro3-260323","benchmarkId":"aa-mlcr-aa","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.555555555555556,"warning":null},{"id":"4c646f44d8a2f54dd28f759a","modelId":"solar-pro3-260323","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":-53.4,"warning":null},{"id":"5a972a37cc173c738ac9b70a","modelId":"solar-pro3-260323","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.5,"warning":null},{"id":"c09d36e66a2605d0626b8874","modelId":"solar-pro3-260323","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":25.462962962962997,"warning":null},{"id":"5326f847758818bf93448cfe","modelId":"solar-pro3-260323","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":86.2573099415205,"warning":null},{"id":"b761794691d5cb615a77b75a","modelId":"solar-pro3-260323","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":8.65979381443299,"warning":null},{"id":"8b80c8dacf1f2ac3db0ea6ed","modelId":"solar-pro3-260323","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":7.57575757575758,"warning":null},{"id":"2163d48791cfaa3ebdc1dcd6","modelId":"solar-pro3-260323","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.9850187265918,"warning":null},{"id":"124d3b5b3e2079c76cde89fb","modelId":"solar-pro3-260323","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Solar Pro 3","configuration":"Solar Pro 3; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro-3; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"b110864377b43b4a8709ce6f","modelId":"solar-pro4-260806","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":74,"warning":null},{"id":"1ebfe07bf9a4ff4606aeb50e","modelId":"solar-pro4-260806","benchmarkId":"aa-automationbench-aa","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":9.082506839361528,"warning":null},{"id":"9dbd38e7eea0e005c8b08526","modelId":"solar-pro4-260806","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.42857142857143,"warning":null},{"id":"d9cf03ad155e2414076ae99c","modelId":"solar-pro4-260806","benchmarkId":"aa-gdp-pdf","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.6000000000000005,"warning":null},{"id":"daca0757544e83cd0db2dbf6","modelId":"solar-pro4-260806","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":1194.75,"warning":null},{"id":"524276087f80ab9a7ec587fe","modelId":"solar-pro4-260806","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":89.0909090909091,"warning":null},{"id":"b2f666197f0a616a41da848c","modelId":"solar-pro4-260806","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.2400370713624,"warning":null},{"id":"00db4ada432af3c8ba91468f","modelId":"solar-pro4-260806","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":-0.85,"warning":null},{"id":"534053ff38c39bcf0e64b018","modelId":"solar-pro4-260806","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":18.933333333333334,"warning":null},{"id":"f295d5a65cc60768acb6b130","modelId":"solar-pro4-260806","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":44.560185185185205,"warning":null},{"id":"67316d10f432f15fe7c97a55","modelId":"solar-pro4-260806","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":23.298969072164898,"warning":null},{"id":"f4dea894fcffe88ddf4ea8e7","modelId":"solar-pro4-260806","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":57.30337078651681,"warning":null},{"id":"8c993fa6a419d236d83ac4af","modelId":"solar-pro4-260806","benchmarkId":"aa-terminalbench-v4-0","level":"reasoning","sourceLabel":"Solar Pro 4","configuration":"Solar Pro 4; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/solar-pro4; Mode from evaluator isReasoning metadata; effort budget not specified","score":0.505050505050505,"warning":null},{"id":"4e4f7f66e12fa41c88b4ae62","modelId":"step-3.7-flash","benchmarkId":"aa-apex-agents-aa","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":14.823008849557501,"warning":null},{"id":"d03747357d4b99762e3c2c12","modelId":"step-3.7-flash","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":73.6666666666667,"warning":null},{"id":"05f9d1f4588607425107e0cd","modelId":"step-3.7-flash","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":2.28571428571429,"warning":null},{"id":"f3f1d0a35cc4c49e68376e7f","modelId":"step-3.7-flash","benchmarkId":"aa-enterprise-ops-gym-aa","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":29.065950462548496,"warning":null},{"id":"3bb0f7ade7fc2865154e49c7","modelId":"step-3.7-flash","benchmarkId":"aa-gdpval-aa","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":954.2,"warning":null},{"id":"aea0451a4896d102b0043d1d","modelId":"step-3.7-flash","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":80.90909090909089,"warning":null},{"id":"7871ad7a9b4fdaee2e2800fd","modelId":"step-3.7-flash","benchmarkId":"aa-harvey-lab-aa","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":72.73122014763351,"warning":null},{"id":"9eaec21698f9c763849fc748","modelId":"step-3.7-flash","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":21.408711770157602,"warning":null},{"id":"a23d7538799febe12d9a6925","modelId":"step-3.7-flash","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":67.2789115646258,"warning":null},{"id":"9006b356b7c4957dcf096d9e","modelId":"step-3.7-flash","benchmarkId":"aa-itbench-aa","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.2730696798493,"warning":null},{"id":"c87c7ea70afb04af4f026773","modelId":"step-3.7-flash","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":75.3179190751445,"warning":null},{"id":"f10ed77c5f2a457b4875815a","modelId":"step-3.7-flash","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":-37.2833333333333,"warning":null},{"id":"4cb090aa5d8a78b6a18f80f0","modelId":"step-3.7-flash","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":25.783333333333335,"warning":null},{"id":"31c949451c135ca26418dd9e","modelId":"step-3.7-flash","benchmarkId":"aa-scicode","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":43.8657407407407,"warning":null},{"id":"f6ad7a16a5446adada0a8818","modelId":"step-3.7-flash","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":98.5380116959064,"warning":null},{"id":"8b38eb1018caf6cb002d9ea9","modelId":"step-3.7-flash","benchmarkId":"aa-tau3-banking","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":11.9587628865979,"warning":null},{"id":"d29adfa107dd249d7fdf48ea","modelId":"step-3.7-flash","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":35.6060606060606,"warning":null},{"id":"ee468fde2438f81f9d3a5096","modelId":"step-3.7-flash","benchmarkId":"aa-terminalbench-v2-1","level":"reasoning","sourceLabel":"Step 3.7 Flash","configuration":"Step 3.7 Flash; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-7-flash; Mode from evaluator isReasoning metadata; effort budget not specified","score":39.325842696629195,"warning":null},{"id":"43b322ea28a4a6f277552a05","modelId":"step3-vl-10b","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"9132d81889bdde96600d5cfd","modelId":"step3-vl-10b","benchmarkId":"aa-critpt","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"a97b8f1ba39ced23967d346c","modelId":"step3-vl-10b","benchmarkId":"aa-gpqa-diamond","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":68.989898989899,"warning":null},{"id":"faa28dbbc9f9add21df2dc61","modelId":"step3-vl-10b","benchmarkId":"aa-humanitys-last-exam","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":10.8433734939759,"warning":null},{"id":"5cd738dc348ca79f2c279d55","modelId":"step3-vl-10b","benchmarkId":"aa-ifbench","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":50.2040816326531,"warning":null},{"id":"c0c789fed617bbde5f34bffc","modelId":"step3-vl-10b","benchmarkId":"aa-mmmu-pro","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":63.9884393063584,"warning":null},{"id":"0fcf0db8250ffa3a4b7f5ba1","modelId":"step3-vl-10b","benchmarkId":"aa-omniscience","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":-59,"warning":null},{"id":"b442f2f7fef04eefeaf6dde1","modelId":"step3-vl-10b","benchmarkId":"aa-omniscience-accuracy","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":13.266666666666666,"warning":null},{"id":"1d4647242d6328c3454120c9","modelId":"step3-vl-10b","benchmarkId":"aa-tau2-bench","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":16.0818713450292,"warning":null},{"id":"33581c6317d1eb43fcadfe15","modelId":"step3-vl-10b","benchmarkId":"aa-terminalbench-hard","level":"reasoning","sourceLabel":"Step3 VL 10B","configuration":"Step3 VL 10B; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/step-3-vl-10b; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.3030303030303,"warning":null},{"id":"701a12cb5a469a4de2b81dcc","modelId":"tiny-aya-global","benchmarkId":"aa-artificial-analysis-long-context-reasoning","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"803351c15f6911e960f59a82","modelId":"tiny-aya-global","benchmarkId":"aa-critpt","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"ae198468c720d10bafa7d1ed","modelId":"tiny-aya-global","benchmarkId":"aa-global-mmlu-lite","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":55.13020833333333,"warning":null},{"id":"02b8e27c2385d10ab79bd4fb","modelId":"tiny-aya-global","benchmarkId":"aa-gpqa-diamond","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":30.5050505050505,"warning":null},{"id":"1e3007800bf6ad6160a38a16","modelId":"tiny-aya-global","benchmarkId":"aa-humanitys-last-exam","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":5.23632993512512,"warning":null},{"id":"1438c051d28cc24285d0b24f","modelId":"tiny-aya-global","benchmarkId":"aa-ifbench","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":20.1360544217687,"warning":null},{"id":"41c731de4263a48b615b716d","modelId":"tiny-aya-global","benchmarkId":"aa-omniscience","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":-84.3,"warning":null},{"id":"9fbe07135ac2965896c34113","modelId":"tiny-aya-global","benchmarkId":"aa-omniscience-accuracy","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":6.066666666666666,"warning":null},{"id":"35cc8b451f8300f16237328f","modelId":"tiny-aya-global","benchmarkId":"aa-tau2-bench","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"e244a76401048b5127d71e98","modelId":"tiny-aya-global","benchmarkId":"aa-terminalbench-hard","level":"non-reasoning","sourceLabel":"Tiny Aya Global","configuration":"Tiny Aya Global; Reported effort: non-reasoning; Model source: https://artificialanalysis.ai/models/tiny-aya-global; Mode from evaluator isReasoning metadata; effort budget not specified","score":0,"warning":null},{"id":"0e654cd1466ae894d75cb1e8","modelId":"grok-4.5","benchmarkId":"vulcanbench-v3-07-grok-fable-sol","level":"medium","sourceLabel":"Grok 4.5 (medium)","configuration":"Grok 4.5; source label: Grok 4.5 (medium); medium effort; 23 tasks; evaluation 2026-07-12. See source for repeat counts and wall-clock budget.","score":91.3,"warning":null},{"id":"ffbbc7256f47ee72d321f094","modelId":"grok-4.5","benchmarkId":"vulcanbench-v3-07-grok-fable-sol","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Grok 4.5; source label: Grok 4.5 (high); high effort; 23 tasks; evaluation 2026-07-12. See source for repeat counts and wall-clock budget.","score":91.3,"warning":null},{"id":"6568b269cb7681ea39a1097c","modelId":"gpt-5.6-sol","benchmarkId":"vulcanbench-v3-07-grok-fable-sol","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"GPT-5.6 Sol; source label: GPT-5.6 Sol (high); high effort; 23 tasks; evaluation 2026-07-12. See source for repeat counts and wall-clock budget.","score":87,"warning":null},{"id":"55c55b9ae75c2c789bb81880","modelId":"grok-4.5","benchmarkId":"vulcanbench-v3-07-grok-fable-sol","level":"low","sourceLabel":"Grok 4.5 (low)","configuration":"Grok 4.5; source label: Grok 4.5 (low); low effort; 23 tasks; evaluation 2026-07-12. See source for repeat counts and wall-clock budget.","score":82.6,"warning":null},{"id":"82ad7650319190ab8ebf8f1a","modelId":"gpt-5.6-sol","benchmarkId":"vulcanbench-v3-07-grok-fable-sol","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"GPT-5.6 Sol; source label: GPT-5.6 Sol (medium); medium effort; 23 tasks; evaluation 2026-07-12. See source for repeat counts and wall-clock budget.","score":82.6,"warning":null},{"id":"07c58037116b0b06179f7fbf","modelId":"gpt-5.6-sol","benchmarkId":"vulcanbench-v3-07-grok-fable-sol","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"GPT-5.6 Sol; source label: GPT-5.6 Sol (low); low effort; 23 tasks; evaluation 2026-07-12. See source for repeat counts and wall-clock budget.","score":78.3,"warning":null},{"id":"758fa2580c85027d05e4247c","modelId":"kimi-k3","benchmarkId":"vulcanbench-v3-08-kimi-k3","level":"max","sourceLabel":"Kimi K3 (max, 30-min budget)","configuration":"Kimi K3; source label: Kimi K3 (max, 30-min budget); max effort; 23 tasks; evaluation 2026-07-19. See source for repeat counts and wall-clock budget.","score":73.9,"warning":null},{"id":"a5c39da8a1cf93a9c675f0ee","modelId":"claude-opus-5","benchmarkId":"vulcanbench-v3-10-opus5-effort","level":"low","sourceLabel":"low","configuration":"Claude Opus 5; source label: low; low effort; 23 tasks; evaluation 2026-07-26. See source for repeat counts and wall-clock budget.","score":87,"warning":null},{"id":"7177575f578b9a510d14e532","modelId":"claude-opus-5","benchmarkId":"vulcanbench-v3-10-opus5-effort","level":"medium","sourceLabel":"medium","configuration":"Claude Opus 5; source label: medium; medium effort; 23 tasks; evaluation 2026-07-26. See source for repeat counts and wall-clock budget.","score":82.6,"warning":null},{"id":"f20cb695188c6fb09c7bfde6","modelId":"claude-opus-5","benchmarkId":"vulcanbench-v3-10-opus5-effort","level":"high","sourceLabel":"high","configuration":"Claude Opus 5; source label: high; high effort; 23 tasks; evaluation 2026-07-26. See source for repeat counts and wall-clock budget.","score":78.3,"warning":null},{"id":"724e797747b99ab179cc86f3","modelId":"qwen-3.8-max","benchmarkId":"vulcanbench-v3-12-qwen38-max","level":"low","sourceLabel":"low","configuration":"Qwen3.8-Max; source label: low; low effort; 23 tasks; evaluation 2026-08-04. See source for repeat counts and wall-clock budget.","score":81.2,"warning":null},{"id":"fc3245dd2348d67c6fe183bd","modelId":"qwen-3.8-max","benchmarkId":"vulcanbench-v3-12-qwen38-max","level":"medium","sourceLabel":"medium","configuration":"Qwen3.8-Max; source label: medium; medium effort; 23 tasks; evaluation 2026-08-04. See source for repeat counts and wall-clock budget.","score":71,"warning":null},{"id":"42a596f42d31c722ee3e28df","modelId":"qwen-3.8-max","benchmarkId":"vulcanbench-v3-12-qwen38-max","level":"xhigh","sourceLabel":"xhigh (default)","configuration":"Qwen3.8-Max; source label: xhigh (default); xhigh effort; 23 tasks; evaluation 2026-08-04. Source reports 55.1% and 38/64 completed runs; incomplete trials. Published percentage retained.","score":55.1,"warning":"Source reports 55.1% and 38/64 completed runs; incomplete trials. Published percentage retained."},{"id":"1bef904009c6a794c1dd2f03","modelId":"grok-4.6","benchmarkId":"vulcanbench-v3-14-grok-46-effort","level":"low","sourceLabel":"low","configuration":"Grok 4.6; source label: low; low effort; 23 tasks; evaluation 2026-08-12. See source for repeat counts and wall-clock budget.","score":82.6,"warning":null},{"id":"5f32740262d72bbbdbf60a38","modelId":"grok-4.6","benchmarkId":"vulcanbench-v3-14-grok-46-effort","level":"medium","sourceLabel":"medium","configuration":"Grok 4.6; source label: medium; medium effort; 23 tasks; evaluation 2026-08-12. See source for repeat counts and wall-clock budget.","score":87,"warning":null},{"id":"d99fc9802ae6b1d7987cad39","modelId":"grok-4.6","benchmarkId":"vulcanbench-v3-14-grok-46-effort","level":"high","sourceLabel":"high (default)","configuration":"Grok 4.6; source label: high (default); high effort; 23 tasks; evaluation 2026-08-12. See source for repeat counts and wall-clock budget.","score":73.9,"warning":null},{"id":"47ae4c48e3377c9ee20c9652","modelId":"grok-4.6","benchmarkId":"vulcanbench-v3-14-grok-46-effort","level":"xhigh","sourceLabel":"xhigh","configuration":"Grok 4.6; source label: xhigh; xhigh effort; 23 tasks; evaluation 2026-08-12. See source for repeat counts and wall-clock budget.","score":78.3,"warning":null},{"id":"69dd3899f972d5a522219937","modelId":"qwen3.8-27b","benchmarkId":"vulcanbench-v3-17-qwen38-27b-effort","level":"low","sourceLabel":"low","configuration":"Qwen3.8-27B; source label: low; low effort; 23 tasks; evaluation 2026-08-21. See source for repeat counts and wall-clock budget.","score":82.6,"warning":null},{"id":"d6e683f349eb46ae01149f20","modelId":"qwen3.8-27b","benchmarkId":"vulcanbench-v3-17-qwen38-27b-effort","level":"medium","sourceLabel":"medium","configuration":"Qwen3.8-27B; source label: medium; medium effort; 23 tasks; evaluation 2026-08-21. See source for repeat counts and wall-clock budget.","score":82.6,"warning":null},{"id":"5a6667c8022196c74f1a2ccf","modelId":"qwen3.8-27b","benchmarkId":"vulcanbench-v3-17-qwen38-27b-effort","level":"xhigh","sourceLabel":"xhigh","configuration":"Qwen3.8-27B; source label: xhigh; xhigh effort; 23 tasks; evaluation 2026-08-21. See source for repeat counts and wall-clock budget.","score":73.9,"warning":null},{"id":"f796e96bd180b4dd9bd12eff","modelId":"glm-5.3","benchmarkId":"vulcanbench-v3-18-glm53-zcode-harness","level":"low","sourceLabel":"low","configuration":"GLM 5.3; source label: low; low effort; 23 tasks; evaluation 2026-08-24. Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode.","score":78.3,"warning":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"d783859010d571f133e77356","modelId":"glm-5.3","benchmarkId":"vulcanbench-v3-18-glm53-zcode-harness","level":"high","sourceLabel":"high","configuration":"GLM 5.3; source label: high; high effort; 23 tasks; evaluation 2026-08-24. Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode.","score":73.9,"warning":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"3bde5c20893b402a0e56ffb5","modelId":"glm-5.3","benchmarkId":"vulcanbench-v3-18-glm53-zcode-harness","level":"max","sourceLabel":"max","configuration":"GLM 5.3; source label: max; max effort; 23 tasks; evaluation 2026-08-24. Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode.","score":65.2,"warning":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"1b7ece23e8756e740abb6e39","modelId":"muse-spark-1.2","benchmarkId":"vulcanbench-v3-19-musespark-effort","level":"low","sourceLabel":"low","configuration":"Muse Spark 1.2; source label: low; low effort; 23 tasks; evaluation 2026-08-25. See source for repeat counts and wall-clock budget.","score":87,"warning":null},{"id":"970bc242697fc80101d9ac17","modelId":"muse-spark-1.2","benchmarkId":"vulcanbench-v3-19-musespark-effort","level":"high","sourceLabel":"high","configuration":"Muse Spark 1.2; source label: high; high effort; 23 tasks; evaluation 2026-08-25. See source for repeat counts and wall-clock budget.","score":73.9,"warning":null},{"id":"c5e80648923e0576c68a9c39","modelId":"muse-spark-1.2","benchmarkId":"vulcanbench-v3-19-musespark-effort","level":"xhigh","sourceLabel":"xhigh","configuration":"Muse Spark 1.2; source label: xhigh; xhigh effort; 23 tasks; evaluation 2026-08-25. See source for repeat counts and wall-clock budget.","score":52.2,"warning":null},{"id":"00cd14ef96cfd2e8dfd5e845","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"xhigh","sourceLabel":"Claude Fable 5 (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.003","score":53.480000000000004,"warning":null},{"id":"01c83861b72d5096082de252","modelId":"claude-opus-4-6","benchmarkId":"frontiercode-1.1-main-claude-code","level":"low","sourceLabel":"Claude Opus 4.6 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.003","score":18.310000000000002,"warning":null},{"id":"0acab77924c8fa3e469de011","modelId":"gemini-3.6-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"low","sourceLabel":"Gemini 3.6 Flash (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":32.769999999999996,"warning":null},{"id":"0d5e49902497ab349126387e","modelId":"claude-opus-4-6","benchmarkId":"frontiercode-1.1-main-claude-code","level":"high","sourceLabel":"Claude Opus 4.6 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":26.640000000000004,"warning":null},{"id":"0d89a61a72b86a5fc22b7ebc","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"low","sourceLabel":"Claude Fable 5.1 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":61.62,"warning":null},{"id":"0ed985881b62cd0bc3af4eb4","modelId":"gpt-6-astra","benchmarkId":"arc3-standard","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-astra; variant max; public-demo task scores are excluded","score":62.71280210060628,"warning":null},{"id":"118142e09fa2bec781ac751e","modelId":"glm-5.3","benchmarkId":"frontiercode-1.1-extended-chisel","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":52.629999999999995,"warning":null},{"id":"126b238f0fce5e381a15f5c2","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-main-claude-code","level":"medium","sourceLabel":"Claude Opus 4.7 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":28.910000000000004,"warning":null},{"id":"150f043c8b72655148c79768","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-main-claude-code","level":"low","sourceLabel":"Claude Fable 5.1 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":49.82,"warning":null},{"id":"17937afc9a71c653c9d4f6f2","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":63.629999999999995,"warning":null},{"id":"18ca9b5ee43fc4850d343f7b","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-main-claude-code","level":"low","sourceLabel":"Claude Opus 4.7 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":27.61,"warning":null},{"id":"190a41f349d6ec138ffcdc33","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"max","sourceLabel":"Claude Opus 5 (max)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0101","score":48.04,"warning":null},{"id":"1927548b0a16cd1479986cbd","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-main-claude-code","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":50.28,"warning":null},{"id":"1ca215d9d01741432bae9472","modelId":"gpt-5.6-terra","benchmarkId":"terminal4-codex","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Codex; effort max; reported margin ±3.3 percentage points, confidence level unspecified; release date 2026-06-26; board checked 2026-09-07","score":21.5,"warning":null},{"id":"1cf1455535fc32710e1965cf","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"high","sourceLabel":"Claude Opus 4.8 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0073","score":55.63,"warning":null},{"id":"1ed4c92e4aa05c76200a18bc","modelId":"claude-sonnet-4-6","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"low","sourceLabel":"Claude Sonnet 4.6 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":30.44,"warning":null},{"id":"1f3aa6afe3bf07a0c02a7308","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-extended-codex","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":41.17,"warning":null},{"id":"1f438db0c3a8d74e269dc9c6","modelId":"gpt-5.4-mini","benchmarkId":"frontiercode-1.1-extended-codex","level":"low","sourceLabel":"GPT-5.4-mini (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":20.580000000000002,"warning":null},{"id":"1fb4cc080f6a704550c60899","modelId":"grok-4.6","benchmarkId":"frontiercode-1.1-extended-grok-build","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; grok-build; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004","score":59.62,"warning":null},{"id":"2105c7646f3a139187821073","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-extended-codex","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":52.629999999999995,"warning":null},{"id":"212dafc406aab75cb58766c0","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"medium","sourceLabel":"Claude Opus 4.7 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":44.75,"warning":null},{"id":"21ee231589903749e98387ba","modelId":"gpt-6-astra","benchmarkId":"arc3-provider-adapter","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-astra; variant provider-adapter-xhigh; public-demo task scores are excluded","score":98.44155844155843,"warning":null},{"id":"25234df123a00777fcf34bce","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-extended-codex","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":60.25,"warning":null},{"id":"255229c9fb97665746c2f311","modelId":"nemotron-3-ultra","benchmarkId":"frontiercode-1.1-main-chisel","level":"unspecified","sourceLabel":"Nemotron 3 Ultra (none)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":13.61,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"276a6edb836c21a802685b40","modelId":"gpt-6-astra","benchmarkId":"arc3-provider-adapter","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-astra; variant provider-adapter-high; public-demo task scores are excluded","score":99.94571232125699,"warning":null},{"id":"28a8f1e475f0000b4b484058","modelId":"deepseek-v4-pro","benchmarkId":"frontiercode-1.1-extended-mini-swe-agent","level":"unspecified","sourceLabel":"DeepSeek V4 Pro (none)","configuration":"FrontierCode 1.1; extended; 150 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0067","score":31.009999999999998,"warning":"DeepSeek V4 Pro checkpoint is unspecified; April and August must remain separate."},{"id":"2ab8119e321a20d7de8cf1c0","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-extended-codex","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":37.79,"warning":null},{"id":"2b41628e867fcb824b023ab3","modelId":"grok-4.6","benchmarkId":"terminal4-grokbuild","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Grok Build; effort high; reported margin ±3.1 percentage points, confidence level unspecified; release date 2026-08-12; board checked 2026-09-07","score":20.3,"warning":null},{"id":"2bd0af0abcc178550c64a1ac","modelId":"grok-4.5","benchmarkId":"frontiercode-1.1-extended-grok-build","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; grok-build; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":56.55,"warning":null},{"id":"2c3bec9e4e0eff839c3ff4df","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"medium","sourceLabel":"Claude Fable 5 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":62.79,"warning":null},{"id":"2d0594eef125dd86ef42cfcb","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-extended-codex","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":54.50000000000001,"warning":null},{"id":"2d2cb54f2cced8ad23e6d7f8","modelId":"gpt-6-astra","benchmarkId":"arc3-provider-adapter","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-astra; variant provider-adapter-medium; public-demo task scores are excluded","score":98.43861309255745,"warning":null},{"id":"303f27de5519d24ea6491389","modelId":"nemotron-3-ultra","benchmarkId":"frontiercode-1.1-extended-chisel","level":"unspecified","sourceLabel":"Nemotron 3 Ultra (none)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":27.21,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"304e04af8619e1665e7baa68","modelId":"grok-4.6","benchmarkId":"frontiercode-1.1-main-grok-build","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; grok-build; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.007","score":48.010000000000005,"warning":null},{"id":"336011e6d0e94555b099f00f","modelId":"gpt-6-astra","benchmarkId":"arc3-standard","level":"none","sourceLabel":"GPT-6 Astra (none)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-astra; variant none; public-demo task scores are excluded","score":35.177880317424,"warning":"Source-reported None does not establish a supported Astra API setting."},{"id":"34af973aab00ee6e3f8d8bf8","modelId":"mistral-medium-3.5","benchmarkId":"frontiercode-1.1-extended-chisel","level":"unspecified","sourceLabel":"Mistral 3.5 Medium (none)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004","score":18.66,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"35e4eb7c3f88bd81a2774079","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"medium","sourceLabel":"Claude Sonnet 5 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":49.28,"warning":null},{"id":"35e9f237985104a6fd022a74","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-main-codex","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":38.75,"warning":null},{"id":"364834ea4ff4cde79854901b","modelId":"kimi-k3","benchmarkId":"frontiercode-1.1-main-mini-swe-agent","level":"unspecified","sourceLabel":"Kimi K3 (none)","configuration":"FrontierCode 1.1; main; 100 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0021","score":44.17,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"37e808d11c66296c681ea587","modelId":"gemini-3.7-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":51.849999999999994,"warning":null},{"id":"391c90fa4b674dc1c3932918","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"max","sourceLabel":"Claude Opus 5 (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0067","score":58.940000000000005,"warning":null},{"id":"395047417b94ee3b51adaa55","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"medium","sourceLabel":"Claude Fable 5 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.003","score":49.82,"warning":null},{"id":"3b38242e2298df478a3621e4","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-extended-codex","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":50.86000000000001,"warning":null},{"id":"3c433cf7df074c5af7c027bd","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-extended-codex","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":49.99,"warning":null},{"id":"3ca697c43da26b4e6144885f","modelId":"gpt-5.6-terra","benchmarkId":"arc3-standard","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-terra; variant medium; public-demo task scores are excluded","score":0.08,"warning":null},{"id":"3cfdd48cd8b66a487f18b2e9","modelId":"gpt-5.6-luna","benchmarkId":"arc3-standard","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-luna; variant high; public-demo task scores are excluded","score":0.1,"warning":null},{"id":"3d5e60cff8818bd0c8d67cc0","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-main-codex","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":35.89,"warning":null},{"id":"3f43c11c9388f23914100624","modelId":"gemini-3.8-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":51.239999999999995,"warning":null},{"id":"4089087bc0de296803ff3a88","modelId":"gpt-5.6-sol","benchmarkId":"arc3-standard","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-sol; variant max; public-demo task scores are excluded","score":7.779999999999999,"warning":null},{"id":"4348fbb897a2a59eae46e3f4","modelId":"claude-opus-4-6","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"high","sourceLabel":"Claude Opus 4.6 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":43.669999999999995,"warning":null},{"id":"462443c5210915015b4c7bf9","modelId":"gpt-5.4-mini","benchmarkId":"frontiercode-1.1-extended-codex","level":"xhigh","sourceLabel":"GPT-5.4-mini (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":43.01,"warning":null},{"id":"46f65324a766a154476a00ad","modelId":"claude-sonnet-4-6","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":40,"warning":null},{"id":"47d55be1dd81aa1bf4bf5a74","modelId":"claude-opus-4-8","benchmarkId":"terminal4-claudecode","level":"max","sourceLabel":"Opus 4.8 (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.6 percentage points, confidence level unspecified; release date 2026-05-28; board checked 2026-09-07","score":23.6,"warning":null},{"id":"49fac0a9cdee783034468784","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-extended-codex","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":64.48,"warning":null},{"id":"4b326191d83fb7c7b1f5d5b3","modelId":"gpt-5.5","benchmarkId":"frontiercode-1.1-main-codex","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":36.6,"warning":null},{"id":"4bacad2a4162155bcf382a46","modelId":"gemini-3.7-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":42.230000000000004,"warning":null},{"id":"4c92e3a3655317402e6e0fc6","modelId":"deepseek-v4-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.1911","score":31.7,"warning":null},{"id":"4eb55593e72129b9cfc2a23b","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-main-codex","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":50.94,"warning":null},{"id":"4f12de502332d1a93cca6d84","modelId":"gemini-3.6-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"medium","sourceLabel":"Gemini 3.6 Flash (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":48.02,"warning":null},{"id":"4f8d2f40bdc3160cdf5b7a04","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-main-codex","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":24.11,"warning":null},{"id":"50b7158c541e4c1686f7c817","modelId":"claude-sonnet-4-6","benchmarkId":"frontiercode-1.1-main-claude-code","level":"medium","sourceLabel":"Claude Sonnet 4.6 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":21.099999999999998,"warning":null},{"id":"52da31a04b7d561b7573dc1f","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"medium","sourceLabel":"Claude Opus 5 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004","score":63.629999999999995,"warning":null},{"id":"5402da52d181b12603f15f33","modelId":"glm-5.3-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":46.21,"warning":null},{"id":"541e90621a96734aecdd8834","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-main-claude-code","level":"high","sourceLabel":"Claude Opus 4.8 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.008","score":41.02,"warning":null},{"id":"55349c832862fc4d4b933188","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-main-claude-code","level":"medium","sourceLabel":"Claude Fable 5.1 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":50.91,"warning":null},{"id":"56b0314f31e75a7aa19bd3b1","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"xhigh","sourceLabel":"Claude Opus 5 (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0144","score":43.65,"warning":null},{"id":"5957688c8334d48ade93b3d5","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-main-codex","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":46.839999999999996,"warning":null},{"id":"5b4b76daf2a598a3aa8925a7","modelId":"gemini-3.6-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"low","sourceLabel":"Gemini 3.6 Flash (low)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":22.82,"warning":null},{"id":"5c999b15cf49cd9ccd8eb829","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-main-codex","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":39.81,"warning":null},{"id":"5ce108c441495c34dbedea2f","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-main-claude-code","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.006","score":46.5,"warning":null},{"id":"6080df646918e38cb77096c2","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-main-codex","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":50.62,"warning":null},{"id":"618440f872edf631f4f0df6a","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-main-codex","level":"xhigh","sourceLabel":"GPT-5.6 Luna (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":38.91,"warning":null},{"id":"61fd47e8efd909e62876c9b4","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"xhigh","sourceLabel":"Claude Sonnet 5 (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.006","score":56.18,"warning":null},{"id":"62ebd59a104b5a031160d534","modelId":"gpt-5.6-sol","benchmarkId":"arc3-standard","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-sol; variant low; public-demo task scores are excluded","score":0.33,"warning":null},{"id":"62f127539d56d2de5540a715","modelId":"kimi-k3","benchmarkId":"frontiercode-1.1-extended-mini-swe-agent","level":"unspecified","sourceLabel":"Kimi K3 (none)","configuration":"FrontierCode 1.1; extended; 150 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0014","score":58.19,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"636572fdb50187d8620318cf","modelId":"claude-sonnet-5","benchmarkId":"terminal4-claudecode","level":"max","sourceLabel":"Sonnet 5 (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.1 percentage points, confidence level unspecified; release date 2026-06-30; board checked 2026-09-07","score":12.4,"warning":null},{"id":"6378f4d933273f336b571e3d","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"medium","sourceLabel":"Claude Sonnet 5 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":35.199999999999996,"warning":null},{"id":"668028a9e1437683d6c27dea","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"high","sourceLabel":"Claude Opus 5 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":47.99,"warning":null},{"id":"66ba0759f64f15955b12acec","modelId":"gemini-3.8-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":53.449999999999996,"warning":null},{"id":"67d76f5adea449a9001331d3","modelId":"gpt-6-astra","benchmarkId":"arc3-provider-adapter","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-astra; variant provider-adapter-max; public-demo task scores are excluded","score":98.55074288592294,"warning":null},{"id":"6958a5ca37b2c58d4c9c3e9d","modelId":"grok-4.6","benchmarkId":"frontiercode-1.1-extended-grok-build","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; grok-build; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0047","score":61.309999999999995,"warning":null},{"id":"6aa803cb83233f756479ec7d","modelId":"minimax-m3","benchmarkId":"frontiercode-1.1-main-mini-swe-agent","level":"unspecified","sourceLabel":"MiniMax M3 (none)","configuration":"FrontierCode 1.1; main; 100 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.015","score":14.7,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"6bc123e800f7cf03d59f006c","modelId":"gemini-3.8-flash","benchmarkId":"terminal4-minisweagent","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"Terminal-Bench 4.0.0; 66 tasks; mini-SWE-agent; effort high; reported margin ±3.4 percentage points, confidence level unspecified; release date 2026-09-02; board checked 2026-09-07","score":19.1,"warning":null},{"id":"6bd6cfd3abfed443b703c64c","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-extended-codex","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":63.07000000000001,"warning":null},{"id":"6dd3175afce39f643aa12476","modelId":"claude-sonnet-4-6","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"high","sourceLabel":"Claude Sonnet 4.6 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":39.86,"warning":null},{"id":"6de659b8ed7b026127969cf3","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-extended-codex","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":47.660000000000004,"warning":null},{"id":"739cb0ae8374d5569ce1d129","modelId":"glm-5.3","benchmarkId":"frontiercode-1.1-main-chisel","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":40.14,"warning":null},{"id":"74826bf1588713bdce3f6257","modelId":"grok-4.6","benchmarkId":"frontiercode-1.1-extended-grok-build","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; grok-build; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":55.02,"warning":null},{"id":"750e6cc699e912bef459e45b","modelId":"gemini-3.7-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":43.59,"warning":null},{"id":"7879d0685c077f756cc44783","modelId":"qwen3.7-plus","benchmarkId":"frontiercode-1.1-extended-mini-swe-agent","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (none)","configuration":"FrontierCode 1.1; extended; 150 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.006","score":21.78,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"78cbe45f9b9ed1991de85fd0","modelId":"deepseek-v4-pro","benchmarkId":"frontiercode-1.1-main-chisel","level":"high","sourceLabel":"DeepSeek V4 Pro 0813 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.106","score":28.549999999999997,"warning":null},{"id":"79f0600c94bfc8d4dbc0b58a","modelId":"gpt-5.6-luna","benchmarkId":"arc3-standard","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-luna; variant medium; public-demo task scores are excluded","score":0.16999999999999998,"warning":null},{"id":"7b0f1b3e720e4f33cde4257b","modelId":"gpt-5.6-sol","benchmarkId":"arc3-standard","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-sol; variant medium; public-demo task scores are excluded","score":1.0699999999999998,"warning":null},{"id":"7d8be1469a7c57ca60300f6b","modelId":"claude-opus-5","benchmarkId":"arc3-standard","level":"high","sourceLabel":"Claude Opus 5 (high)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group anthropic-claude-opus-5; variant high; public-demo task scores are excluded","score":30.159999999999997,"warning":null},{"id":"7d95380d1954ae5d145cb859","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-main-codex","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":45.269999999999996,"warning":null},{"id":"7da2111f1593f8d5dbf745f9","modelId":"gpt-5.4-mini","benchmarkId":"frontiercode-1.1-main-codex","level":"xhigh","sourceLabel":"GPT-5.4-mini (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":27.04,"warning":null},{"id":"7db12365ec82e0beae8240ba","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-main-claude-code","level":"max","sourceLabel":"Claude Opus 4.7 (max)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":38.54,"warning":null},{"id":"7f33b674105fc71448617806","modelId":"deepseek-v4-pro","benchmarkId":"frontiercode-1.1-extended-chisel","level":"high","sourceLabel":"DeepSeek V4 Pro 0813 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.076","score":44.45,"warning":null},{"id":"7fe01339271092343301c357","modelId":"grok-4.5","benchmarkId":"arc3-standard","level":"low","sourceLabel":"Grok 4.5 (low)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group xai-grok-4-5; variant low; public-demo task scores are excluded","score":0.26,"warning":null},{"id":"8127d6db140d93c6a2a6f0fb","modelId":"glm-5.2","benchmarkId":"frontiercode-1.1-main-mini-swe-agent","level":"unspecified","sourceLabel":"GLM 5.2 (none)","configuration":"FrontierCode 1.1; main; 100 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":24.5,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"8181883cb35a2a27684ba034","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"low","sourceLabel":"Claude Sonnet 5 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":44.46,"warning":null},{"id":"826615a0c654de07c920208e","modelId":"grok-4.5","benchmarkId":"frontiercode-1.1-extended-grok-build","level":"low","sourceLabel":"Grok 4.5 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; grok-build; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":53.14,"warning":null},{"id":"82d8e132cdcc601f53c1c7d6","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-main-codex","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":36.89,"warning":null},{"id":"8be54fd7c609e5e4264162aa","modelId":"gemini-3.7-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":54.74,"warning":null},{"id":"8bfe922d1f0ae206b1b1ed3f","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-extended-codex","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0008","score":58.74,"warning":null},{"id":"8d972c585034853563988a88","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-main-codex","level":"medium","sourceLabel":"GPT-5.6 Terra (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":33.879999999999995,"warning":null},{"id":"8e0070188f79ecf6c53cc2c3","modelId":"gemini-3.8-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"medium","sourceLabel":"Gemini 3.8 Flash (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":41.19,"warning":null},{"id":"8f27604b87c7e9ff3a19d10d","modelId":"gpt-5.4-mini","benchmarkId":"frontiercode-1.1-extended-codex","level":"medium","sourceLabel":"GPT-5.4-mini (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":35.06,"warning":null},{"id":"8f57b7f23dea1aca619ea9db","modelId":"claude-opus-4-6","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"medium","sourceLabel":"Claude Opus 4.6 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":38.65,"warning":null},{"id":"8fa122a380d849f4f7cb625e","modelId":"gpt-5.4-mini","benchmarkId":"frontiercode-1.1-extended-codex","level":"high","sourceLabel":"GPT-5.4-mini (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":37.19,"warning":null},{"id":"906266917f34d4a9235d8c64","modelId":"gpt-5.5","benchmarkId":"frontiercode-1.1-extended-codex","level":"medium","sourceLabel":"GPT-5.5 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":51.370000000000005,"warning":null},{"id":"909381319a7974fd682e23e2","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-main-claude-code","level":"xhigh","sourceLabel":"Claude Opus 4.7 (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004","score":34.910000000000004,"warning":null},{"id":"9183ca03c441d129fd6a8992","modelId":"claude-opus-4-6","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"low","sourceLabel":"Claude Opus 4.6 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":32.93,"warning":null},{"id":"919bc7aa1df6867a3297a658","modelId":"gemini-3.7-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"medium","sourceLabel":"Gemini 3.7 Flash (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":56.269999999999996,"warning":null},{"id":"93062cdb2abb0e270b7b4742","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"high","sourceLabel":"Claude Fable 5 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":52.73,"warning":null},{"id":"938dfc674e40641fd737bed8","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-extended-codex","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":57.4,"warning":null},{"id":"978ae4621dc780ed9f07a974","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"xhigh","sourceLabel":"Claude Opus 4.7 (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0027","score":51.41,"warning":null},{"id":"984e727c945e5302e01c261a","modelId":"gpt-5.5","benchmarkId":"frontiercode-1.1-main-codex","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004","score":42.96,"warning":null},{"id":"99e65bc1e02ebf4fee08b548","modelId":"grok-4.5","benchmarkId":"arc3-standard","level":"medium","sourceLabel":"Grok 4.5 (medium)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group xai-grok-4-5; variant medium; public-demo task scores are excluded","score":0.32,"warning":null},{"id":"9b3960b33adb0f097551e5de","modelId":"gemini-3.7-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"low","sourceLabel":"Gemini 3.7 Flash (low)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":36.91,"warning":null},{"id":"9bb740f8253baa1d17ef962a","modelId":"gpt-5.5","benchmarkId":"frontiercode-1.1-main-codex","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":30.55,"warning":null},{"id":"9d0d05ab12b44fcb34eddc63","modelId":"gemini-3.8-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":37.96,"warning":null},{"id":"9e535e58aacd4dc5813160b9","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-main-codex","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":48.83,"warning":null},{"id":"a00271826c96f0bc443bc92d","modelId":"grok-4.6","benchmarkId":"frontiercode-1.1-main-grok-build","level":"low","sourceLabel":"Grok 4.6 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; grok-build; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":40.11,"warning":null},{"id":"a0921a61b310776b40a299af","modelId":"gpt-6-astra","benchmarkId":"arc3-standard","level":"high","sourceLabel":"GPT-6 Astra (high)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-astra; variant high; public-demo task scores are excluded","score":54.81905163612231,"warning":null},{"id":"a0e5300dff64fa35e75d78f1","modelId":"gpt-6-astra","benchmarkId":"arc3-standard","level":"medium","sourceLabel":"GPT-6 Astra (medium)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-astra; variant medium; public-demo task scores are excluded","score":38.58757449733784,"warning":null},{"id":"a157cb960b29b4f9e0e482d3","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-extended-codex","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":62.12,"warning":null},{"id":"a24f67306456001f98c23e75","modelId":"gpt-5.4-mini","benchmarkId":"frontiercode-1.1-main-codex","level":"medium","sourceLabel":"GPT-5.4-mini (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":20.78,"warning":null},{"id":"a3f23bb0246903333cdc1388","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"high","sourceLabel":"Claude Sonnet 5 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":52.71,"warning":null},{"id":"a4313e77019bc32a716730f9","modelId":"claude-sonnet-4-6","benchmarkId":"frontiercode-1.1-main-claude-code","level":"low","sourceLabel":"Claude Sonnet 4.6 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":15.03,"warning":null},{"id":"a445e097ad5e39979d7aa81d","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-main-codex","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":15.379999999999999,"warning":null},{"id":"a47e1f9779f4cb809ad3770e","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-main-codex","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":41.31,"warning":null},{"id":"a825739422e65a8fe0204db4","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"high","sourceLabel":"Claude Fable 5 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":64.25,"warning":null},{"id":"a889d1ce384914e2806e70c7","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-extended-codex","level":"high","sourceLabel":"GPT-5.6 Luna (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":50.519999999999996,"warning":null},{"id":"aa2c038898f84e93e7834f06","modelId":"gpt-5.5","benchmarkId":"frontiercode-1.1-main-codex","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.003","score":40.56,"warning":null},{"id":"ae189fcaebaa21a3fe020a5f","modelId":"deepseek-v4-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.2547","score":18.8,"warning":null},{"id":"afbecdd463048a0daf4430c6","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"low","sourceLabel":"Claude Fable 5 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":48.010000000000005,"warning":null},{"id":"b1f2936eb97f6064636f0b09","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-main-claude-code","level":"high","sourceLabel":"Claude Opus 4.7 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":35.17,"warning":null},{"id":"b1f91824de3ef9411c7d0e7a","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-main-codex","level":"low","sourceLabel":"GPT-5.6 Sol (low)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":35.44,"warning":null},{"id":"b21f635f0c1b98c573a8cec0","modelId":"gpt-6-astra","benchmarkId":"arc3-standard","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-astra; variant low; public-demo task scores are excluded","score":17.452190401133805,"warning":null},{"id":"b36e1936d9f1400c7a8303c6","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"xhigh","sourceLabel":"Claude Sonnet 5 (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.005","score":42.730000000000004,"warning":null},{"id":"b3e20f0dbe09ce936f270b9e","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-main-codex","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":45.06,"warning":null},{"id":"b3ef1bc9e68ff51e017bc544","modelId":"deepseek-v4-pro","benchmarkId":"frontiercode-1.1-main-mini-swe-agent","level":"unspecified","sourceLabel":"DeepSeek V4 Pro (none)","configuration":"FrontierCode 1.1; main; 100 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.01","score":17.64,"warning":"DeepSeek V4 Pro checkpoint is unspecified; April and August must remain separate."},{"id":"b4505193e0e1f1e917b5cabb","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"xhigh","sourceLabel":"Claude Fable 5.1 (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":61.35,"warning":null},{"id":"b54fdd6462a56cf9fbbff457","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"xhigh","sourceLabel":"Claude Fable 5 (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":64.94,"warning":null},{"id":"b56938a2e49c9671f1657923","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"xhigh","sourceLabel":"Claude Opus 4.8 (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0033","score":59.45,"warning":null},{"id":"b7467edb46036b2935325b6c","modelId":"grok-4.5","benchmarkId":"frontiercode-1.1-extended-grok-build","level":"medium","sourceLabel":"Grok 4.5 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; grok-build; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":56.07,"warning":null},{"id":"b769c16ec2b4277cdc9cd0c9","modelId":"gemini-3.7-flash","benchmarkId":"terminal4-minisweagent","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"Terminal-Bench 4.0.0; 66 tasks; mini-SWE-agent; effort high; reported margin ±2.4 percentage points, confidence level unspecified; release date 2026-08-13; board checked 2026-09-07","score":11.2,"warning":null},{"id":"b7d96566d6b6b34d9e314f79","modelId":"claude-sonnet-4-6","benchmarkId":"frontiercode-1.1-main-claude-code","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":24.310000000000002,"warning":null},{"id":"b911c4d9f13d8188e2de86a1","modelId":"glm-5.3-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":31.830000000000002,"warning":null},{"id":"b99056688b2b172aff603206","modelId":"gpt-6-astra","benchmarkId":"arc3-provider-adapter","level":"low","sourceLabel":"GPT-6 Astra (low)","configuration":"ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-astra; variant provider-adapter-low; public-demo task scores are excluded","score":98.02838165829648,"warning":null},{"id":"ba391b95e256d194ae244169","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"low","sourceLabel":"Claude Opus 5 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0021","score":41.949999999999996,"warning":null},{"id":"ba8ff35e294d29a743fa5c65","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-main-claude-code","level":"xhigh","sourceLabel":"Claude Opus 4.8 (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.005","score":45.49,"warning":null},{"id":"bced9c84bedddd36c1d85054","modelId":"claude-opus-4-6","benchmarkId":"frontiercode-1.1-main-claude-code","level":"medium","sourceLabel":"Claude Opus 4.6 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":23.669999999999998,"warning":null},{"id":"bd377043899ff0ae0b462963","modelId":"claude-sonnet-4-6","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"medium","sourceLabel":"Claude Sonnet 4.6 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":37.49,"warning":null},{"id":"be5258d2d7a78bcec434049d","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-main-codex","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":47.49,"warning":null},{"id":"bf209e5b4b2da520e58b7863","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-main-claude-code","level":"xhigh","sourceLabel":"Claude Fable 5.1 (xhigh)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":48.730000000000004,"warning":null},{"id":"bf764fb9af20b8b9fff21eb8","modelId":"gpt-5.6-terra","benchmarkId":"frontiercode-1.1-extended-codex","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":55.84,"warning":null},{"id":"bfe462efb459731aff29651b","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-main-claude-code","level":"high","sourceLabel":"Claude Fable 5.1 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":50.339999999999996,"warning":null},{"id":"c02f418374e14634d8639cb0","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":51.57000000000001,"warning":null},{"id":"c0a21b210841792f09e6eaa9","modelId":"gemini-3.6-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"medium","sourceLabel":"Gemini 3.6 Flash (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":34.37,"warning":null},{"id":"c16b09ec865ee083d20ed15f","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004","score":59.599999999999994,"warning":null},{"id":"c29400f51cb09e46a04ec2da","modelId":"gpt-5.6-sol","benchmarkId":"terminal4-codex","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Codex; effort max; reported margin ±3.8 percentage points, confidence level unspecified; release date 2026-06-26; board checked 2026-09-07","score":37.3,"warning":null},{"id":"c2cebdbb75fc439d384a1645","modelId":"qwen3.7-plus","benchmarkId":"frontiercode-1.1-main-mini-swe-agent","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (none)","configuration":"FrontierCode 1.1; main; 100 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.009","score":10.2,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"c30c3f0dc62b17786a57f7cc","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"high","sourceLabel":"Claude Opus 5 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":58.45,"warning":null},{"id":"c3b6ec43cb1015de697c37c0","modelId":"glm-5.3","benchmarkId":"terminal4-claudecode","level":"max","sourceLabel":"GLM-5.3 (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.2 percentage points, confidence level unspecified; release date 2026-08-14; board checked 2026-09-07","score":41.8,"warning":null},{"id":"c7981128f2cb3799b53b66ec","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"low","sourceLabel":"Claude Opus 4.8 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":50.83,"warning":null},{"id":"c9b43e92020f700c0d052db9","modelId":"grok-4.5","benchmarkId":"frontiercode-1.1-main-grok-build","level":"low","sourceLabel":"Grok 4.5 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; grok-build; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":37.86,"warning":null},{"id":"c9e1fea0c53568fa87547d39","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-main-codex","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":39.93,"warning":null},{"id":"c9ea93dd77a44efafd8b2823","modelId":"mistral-medium-3.5","benchmarkId":"frontiercode-1.1-main-chisel","level":"unspecified","sourceLabel":"Mistral 3.5 Medium (none)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.006","score":8,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"ca8bd8b35520f3df29860eb1","modelId":"gemini-3.6-flash","benchmarkId":"frontiercode-1.1-extended-chisel","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":47.58,"warning":null},{"id":"cba8b60609ec8ba2d384bac4","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"xhigh","sourceLabel":"Claude Opus 5 (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0097","score":56.87,"warning":null},{"id":"cc50f474e4bed017002a068b","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-main-codex","level":"medium","sourceLabel":"GPT-5.6 Luna (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":25.740000000000002,"warning":null},{"id":"cd453778d2e3302b302d0232","modelId":"claude-fable-5","benchmarkId":"terminal4-claudecode","level":"max","sourceLabel":"Fable 5 (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.8 percentage points, confidence level unspecified; release date 2026-06-09; board checked 2026-09-07","score":44.5,"warning":null},{"id":"cdcc8b915ddf149c14044a7f","modelId":"gpt-5.6-luna","benchmarkId":"terminal4-codex","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Codex; effort max; reported margin ±2.8 percentage points, confidence level unspecified; release date 2026-06-26; board checked 2026-09-07","score":17.3,"warning":null},{"id":"cf038268638355842fabacec","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-extended-codex","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":60.550000000000004,"warning":null},{"id":"d1018d5f46b97e159d2f0a02","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-extended-codex","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":55.059999999999995,"warning":null},{"id":"d2bdad5d6d457b8f28281e8f","modelId":"glm-5.2","benchmarkId":"frontiercode-1.1-extended-mini-swe-agent","level":"unspecified","sourceLabel":"GLM 5.2 (none)","configuration":"FrontierCode 1.1; extended; 150 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":40.050000000000004,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"d4b90ed9c9a977ac490e95b4","modelId":"gemini-3.6-flash","benchmarkId":"frontiercode-1.1-main-chisel","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"FrontierCode 1.1; main; 100 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":33.69,"warning":null},{"id":"d4de4a5ced8821eb86459630","modelId":"gpt-5.5","benchmarkId":"frontiercode-1.1-extended-codex","level":"low","sourceLabel":"GPT-5.5 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":45.550000000000004,"warning":null},{"id":"d548bd134bae40904bdbe4de","modelId":"gpt-6-astra","benchmarkId":"terminal4-codex","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Codex; effort max; reported margin ±2.8 percentage points, confidence level unspecified; release date 2026-09-03; board checked 2026-09-07","score":58.2,"warning":null},{"id":"d667c01aa76eb58a13006db0","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-extended-codex","level":"medium","sourceLabel":"GPT-5.6 Sol (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0013","score":54.67999999999999,"warning":null},{"id":"d9ff43c2ee3145f93fa639e1","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"low","sourceLabel":"Claude Opus 4.7 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":43.6,"warning":null},{"id":"da08a3f2efd54d7cb540441b","modelId":"gpt-5.6-luna","benchmarkId":"arc3-standard","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-luna; variant max; public-demo task scores are excluded","score":0.18,"warning":null},{"id":"dae492a117175343395ae164","modelId":"claude-fable-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"low","sourceLabel":"Claude Fable 5 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":60.8,"warning":null},{"id":"daf9afd286691adc70b10a5b","modelId":"gpt-5.6-terra","benchmarkId":"arc3-standard","level":"high","sourceLabel":"GPT-5.6 Terra (high)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-terra; variant high; public-demo task scores are excluded","score":0.49,"warning":null},{"id":"db8204b5e5c7174d88f5e8a4","modelId":"gpt-5.4-mini","benchmarkId":"frontiercode-1.1-main-codex","level":"low","sourceLabel":"GPT-5.4-mini (low)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":9.25,"warning":null},{"id":"dc357b19b6bea4e41d45b423","modelId":"gpt-5.6-luna","benchmarkId":"arc3-standard","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-luna; variant low; public-demo task scores are excluded","score":0.16999999999999998,"warning":null},{"id":"dcbdda875af63c9d559ccae4","modelId":"grok-4.6","benchmarkId":"arc3-standard","level":"xhigh","sourceLabel":"Grok 4.6 (xhigh)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group xai-grok-4-6; variant xhigh; public-demo task scores are excluded","score":2.11,"warning":null},{"id":"dd27c86aaec46afa668fb3ed","modelId":"grok-4.5","benchmarkId":"arc3-standard","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group xai-grok-4-5; variant high; public-demo task scores are excluded","score":0.3,"warning":null},{"id":"ddfef6cc7d43c0b169169e45","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"low","sourceLabel":"Claude Opus 5 (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0041","score":55.75,"warning":null},{"id":"de359ceaf316774036c9cd92","modelId":"grok-4.5","benchmarkId":"frontiercode-1.1-main-grok-build","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; grok-build; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":42.44,"warning":null},{"id":"e0e844ac4fa5c437d7f9afe6","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"high","sourceLabel":"Claude Sonnet 5 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":39.35,"warning":null},{"id":"e182040a6b20731b3805613d","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"medium","sourceLabel":"Claude Fable 5.1 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":63.6,"warning":null},{"id":"e2c3b944130f3a5e4b806d94","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-main-claude-code","level":"low","sourceLabel":"Claude Opus 4.8 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":35.14,"warning":null},{"id":"e554b93428a677182f0b4906","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"low","sourceLabel":"Claude Sonnet 5 (low)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":28.71,"warning":null},{"id":"e5f0edaa48b4e6162542d4d5","modelId":"minimax-m3","benchmarkId":"frontiercode-1.1-extended-mini-swe-agent","level":"unspecified","sourceLabel":"MiniMax M3 (none)","configuration":"FrontierCode 1.1; extended; 150 tasks; mini-swe-agent; source effort none; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0107","score":28.54,"warning":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"e61670a23ffd1d53d4575c95","modelId":"gpt-5.6-sol","benchmarkId":"frontiercode-1.1-extended-codex","level":"xhigh","sourceLabel":"GPT-5.6 Sol (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":59.98,"warning":null},{"id":"e638e44f7a00fc2c77bd320a","modelId":"gpt-5.4-mini","benchmarkId":"frontiercode-1.1-main-codex","level":"high","sourceLabel":"GPT-5.4-mini (high)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.001","score":23.080000000000002,"warning":null},{"id":"e78de1fe1b2913b438e8bfb4","modelId":"gpt-5.6-luna","benchmarkId":"frontiercode-1.1-extended-codex","level":"low","sourceLabel":"GPT-5.6 Luna (low)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":29.020000000000003,"warning":null},{"id":"e7a90181ff22c2632f726d32","modelId":"gpt-5.5","benchmarkId":"frontiercode-1.1-extended-codex","level":"high","sourceLabel":"GPT-5.5 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.002","score":53.99,"warning":null},{"id":"e83c78ee104f6ac791b27a26","modelId":"grok-4.6","benchmarkId":"frontiercode-1.1-main-grok-build","level":"medium","sourceLabel":"Grok 4.6 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; grok-build; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.006","score":46.06,"warning":null},{"id":"e93116c3e86f122b9ce063bf","modelId":"gpt-6-astra","benchmarkId":"arc3-provider-adapter","level":"none","sourceLabel":"GPT-6 Astra (none)","configuration":"ARC-AGI-3 Semi-Private verified summary; Provider Adapter harness; source group openai-gpt-6-astra; variant provider-adapter-none; public-demo task scores are excluded","score":96.72021831785531,"warning":"Source-reported None does not establish a supported Astra API setting."},{"id":"e97f395dde5500c89744b1bc","modelId":"gpt-5.6-terra","benchmarkId":"arc3-standard","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-terra; variant max; public-demo task scores are excluded","score":0.8,"warning":null},{"id":"ea6ce5e67b0ac25bebd66ef3","modelId":"claude-fable-5-1","benchmarkId":"terminal4-claudecode","level":"max","sourceLabel":"Fable 5.1 (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.8 percentage points, confidence level unspecified; release date 2026-09-01; board checked 2026-09-07","score":57.9,"warning":null},{"id":"eaf538a9130f43391ba85bbf","modelId":"grok-4.5","benchmarkId":"frontiercode-1.1-main-grok-build","level":"medium","sourceLabel":"Grok 4.5 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; grok-build; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":41.93,"warning":null},{"id":"ec5579f64a5a32bfa01b650d","modelId":"grok-4.5","benchmarkId":"terminal4-grokbuild","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Grok Build; effort high; reported margin ±2.6 percentage points, confidence level unspecified; release date 2026-07-16; board checked 2026-09-07","score":12.4,"warning":null},{"id":"ef3184b2503a57f0077f8932","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":62.029999999999994,"warning":null},{"id":"f019be82c0b7b5fcd5e1527b","modelId":"gpt-5.6-terra","benchmarkId":"arc3-standard","level":"low","sourceLabel":"GPT-5.6 Terra (low)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-terra; variant low; public-demo task scores are excluded","score":0.01,"warning":null},{"id":"f069bb43a49e2e73d5a979fd","modelId":"claude-sonnet-4-6","benchmarkId":"frontiercode-1.1-main-claude-code","level":"high","sourceLabel":"Claude Sonnet 4.6 (high)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":23.47,"warning":null},{"id":"f0c644f9ca0c8b80a60b8f6e","modelId":"claude-opus-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"medium","sourceLabel":"Claude Opus 5 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.006","score":53.38,"warning":null},{"id":"f1474950f0a1512219e1d401","modelId":"claude-fable-5-1","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"high","sourceLabel":"Claude Fable 5.1 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0","score":62.68,"warning":null},{"id":"f197d86f96a3cd32ba83cf18","modelId":"claude-opus-5","benchmarkId":"terminal4-claudecode","level":"max","sourceLabel":"Opus 5 (max)","configuration":"Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.4 percentage points, confidence level unspecified; release date 2026-07-24; board checked 2026-09-07","score":51.8,"warning":null},{"id":"f1edd38ed72382bd57766812","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"medium","sourceLabel":"Claude Opus 4.8 (medium)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.004","score":55.37,"warning":null},{"id":"f1f80cdfdf2fedc08b3c8e7d","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"max","sourceLabel":"Claude Opus 4.7 (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":53.93,"warning":null},{"id":"f38a139c5a520dd21aaf9132","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-main-claude-code","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.003","score":42.36,"warning":null},{"id":"f555b0cbf804f18f2f97e3a6","modelId":"gpt-6-astra","benchmarkId":"frontiercode-1.1-main-codex","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"FrontierCode 1.1; main; 100 tasks; codex; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate unspecified","score":53.26,"warning":null},{"id":"f55940d0d324a594d2e7cb02","modelId":"gpt-5.6-sol","benchmarkId":"arc3-standard","level":"high","sourceLabel":"GPT-5.6 Sol (high)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-5-6-sol; variant high; public-demo task scores are excluded","score":2.15,"warning":null},{"id":"f6c40a31975168e070d2cb4c","modelId":"claude-sonnet-5","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0053","score":54.85,"warning":null},{"id":"fa5c692bcb2cab6ed2609402","modelId":"gpt-5.5","benchmarkId":"frontiercode-1.1-extended-codex","level":"xhigh","sourceLabel":"GPT-5.5 (xhigh)","configuration":"FrontierCode 1.1; extended; 150 tasks; codex; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0027","score":56.66,"warning":null},{"id":"fa6ed88eb7e904aa6955ebfb","modelId":"claude-opus-4-7","benchmarkId":"frontiercode-1.1-extended-claude-code","level":"high","sourceLabel":"Claude Opus 4.7 (high)","configuration":"FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.0007","score":51.12,"warning":null},{"id":"fd19565d5d4088b6dfc79064","modelId":"claude-opus-4-8","benchmarkId":"frontiercode-1.1-main-claude-code","level":"medium","sourceLabel":"Claude Opus 4.8 (medium)","configuration":"FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0.005","score":40.46,"warning":null},{"id":"ff9e159dda586ac4a0349062","modelId":"gpt-6-astra","benchmarkId":"arc3-standard","level":"xhigh","sourceLabel":"GPT-6 Astra (xhigh)","configuration":"ARC-AGI-3 Semi-Private verified summary; Standard harness; source group openai-gpt-6-astra; variant xhigh; public-demo task scores are excluded","score":59.342954091460555,"warning":null},{"id":"01e44fc757e76a75628ede29","modelId":"claude-opus-5","benchmarkId":"scale-sweatlas-qna-claudecode","level":"xhigh","sourceLabel":"Opus 5 (Claude Code) xHigh","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-08-04T16:11:53.000Z; reported margin ±5.01 percentage points; No contamination annotation reported (not proof of absence)","score":63.17,"warning":null},{"id":"07b714836f4d50d2545a5455","modelId":"gpt-5.4","benchmarkId":"scale-sweatlas-tw-codex","level":"xhigh","sourceLabel":"GPT-5.4 (Codex) xHigh","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-03-26T18:24:53.000Z; reported margin ±6.04 percentage points; No contamination annotation reported (not proof of absence)","score":44.36,"warning":null},{"id":"0e5a24ad5a3aa10c27a55eb7","modelId":"claude-fable-5-1","benchmarkId":"scale-sweatlas-tw-claudecode","level":"xhigh","sourceLabel":"Fable-5.1 (Claude Code) xHigh*","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-09-02T19:02:52.000Z; reported margin ±5.33 percentage points; No contamination annotation reported (not proof of absence)","score":67.04,"warning":"Starred protocol annotation requires row-specific review before ranking."},{"id":"0eb870f9f6496683cda2ff7a","modelId":"gpt-6-astra","benchmarkId":"scale-sweatlas-tw-codex","level":"xhigh","sourceLabel":"GPT 6 Astra (Codex) xHigh","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-09-09T19:19:03.000Z; reported margin ±5.91 percentage points; No contamination annotation reported (not proof of absence)","score":50.74,"warning":null},{"id":"129ef34aa55c39c9f65a8288","modelId":"claude-fable-5-1","benchmarkId":"scale-sweatlas-refactoring-claudecode","level":"xhigh","sourceLabel":"Fable-5.1 (Claude Code) xHigh","configuration":"70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.; published row 2026-09-02T21:52:32.000Z; reported margin ±6.52 percentage points; No contamination annotation reported (not proof of absence)","score":56.67,"warning":null},{"id":"1ce57fce710e63f4fde5f000","modelId":"claude-opus-4-6","benchmarkId":"scale-humanitys_last_exam-scaleofficialevaluation","level":"non-reasoning","sourceLabel":"claude-opus-4-6 (Non-Thinking)","configuration":"Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.; published row 2026-02-17T17:05:29.000Z; reported margin ±1.54 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":19,"warning":null},{"id":"22863bca1313db0d07725e03","modelId":"claude-fable-5","benchmarkId":"scale-sweatlas-qna-claudecode","level":"xhigh","sourceLabel":"Fable-5 (Claude Code) xHigh*","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-03-02T20:20:06.000Z; reported margin ±5 percentage points; No contamination annotation reported (not proof of absence); Board footnote: elevated refusals on benign tasks are scored zero by the evaluator and remain in the published score.","score":39,"warning":null},{"id":"22f827b71cc6c1cb3e229440","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929-thinking","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2025-10-02T17:29:42.000Z; reported margin ±1.47 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. ","score":14.09,"warning":null},{"id":"25753b4cde30cf31c9192afb","modelId":"gpt-5.1","benchmarkId":"scale-humanitys_last_exam-scaleofficialevaluation","level":"thinking","sourceLabel":"gpt-5.1-thinking","configuration":"Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.; published row 2025-11-26T20:24:19.000Z; reported margin ±1.67 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":23.68,"warning":null},{"id":"294120a57d522f24c679c51f","modelId":"gpt-5.6-sol","benchmarkId":"scale-sweatlas-qna-codex","level":"xhigh","sourceLabel":"GPT-5.6-Sol (Codex) xHigh*","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-03-02T20:20:06.000Z; reported margin ±5 percentage points; No contamination annotation reported (not proof of absence); Board footnote: elevated refusals on benign tasks are scored zero by the evaluator and remain in the published score.","score":46,"warning":null},{"id":"2b65412a084daf79b87e4b34","modelId":"gpt-5.1","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"thinking","sourceLabel":"gpt-5.1-thinking","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2025-11-26T20:28:20.000Z; reported margin ±1.82 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":24.65,"warning":null},{"id":"308c1446bec689a5b5f02280","modelId":"gpt-6-astra","benchmarkId":"scale-sweatlas-refactoring-codex","level":"xhigh","sourceLabel":"GPT 6 Astra (Codex) xHigh","configuration":"70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.; published row 2026-09-09T19:16:22.000Z; reported margin ±6.43 percentage points; No contamination annotation reported (not proof of absence)","score":59.05,"warning":null},{"id":"3203239d5cb0c63824c2a86d","modelId":"claude-fable-5","benchmarkId":"scale-enigma_eval-scaleofficialevaluation","level":"high","sourceLabel":"claude-fable-5-high","configuration":"Scale EnigmaEval puzzle-hunt accuracy; source-reported reasoning effort.; published row 2026-03-23T21:18:50.000Z; reported margin ±2.8 percentage points; No contamination annotation reported (not proof of absence)","score":39.28,"warning":null},{"id":"34bc44371787dfc935087f65","modelId":"gpt-5.4","benchmarkId":"scale-sweatlas-tw-miniswe","level":"xhigh","sourceLabel":"GPT-5.4 (Mini-SWE) xHigh","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-03-26T18:24:57.000Z; reported margin ±6 percentage points; No contamination annotation reported (not proof of absence)","score":40,"warning":null},{"id":"3668be0998ee9f9dbe1cb4b4","modelId":"claude-opus-4-6","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"max","sourceLabel":"claude-opus-4-6-thinking-max","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2026-02-17T17:06:06.000Z; reported margin ±2.03 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":36.24,"warning":null},{"id":"3836c4d32eeadb2f5ad4990c","modelId":"gpt-5.5","benchmarkId":"scale-sweatlas-refactoring-codex","level":"xhigh","sourceLabel":"GPT-5.5 (Codex) xHigh","configuration":"70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.; published row 2026-05-06T01:44:12.000Z; reported margin ±6.76 percentage points; No contamination annotation reported (not proof of absence)","score":44.79,"warning":null},{"id":"38da8dccc01df7999a09d824","modelId":"claude-opus-4-5-20251101","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"thinking","sourceLabel":"claude-opus-4-5-20251101-thinking","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2025-11-26T20:27:42.000Z; reported margin ±1.86 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":26.32,"warning":null},{"id":"445b1683e6ecba6cbf9f044a","modelId":"gpt-5.5","benchmarkId":"scale-sweatlas-qna-codex","level":"xhigh","sourceLabel":"GPT 5.5 (Codex) xHigh","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-05-07T15:50:31.000Z; reported margin ±5.08 percentage points; No contamination annotation reported (not proof of absence)","score":45.43,"warning":null},{"id":"488e21e807236e118e34fcf6","modelId":"claude-fable-5","benchmarkId":"scale-sweatlas-refactoring-claudecode","level":"xhigh","sourceLabel":"Fable-5 (Claude Code) xHigh","configuration":"70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.; published row 2026-06-11T17:55:16.000Z; reported margin ±6.76 percentage points; No contamination annotation reported (not proof of absence)","score":54.76,"warning":null},{"id":"595d203626f42c7eaf274a4d","modelId":"gpt-5.4","benchmarkId":"scale-sweatlas-refactoring-codex","level":"xhigh","sourceLabel":"GPT 5.4 (Codex) xHigh","configuration":"70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.; published row 2026-05-06T01:44:16.000Z; reported margin ±6.76 percentage points; No contamination annotation reported (not proof of absence)","score":44.29,"warning":null},{"id":"5982871718a1d5284ac2e401","modelId":"claude-opus-4-6","benchmarkId":"scale-humanitys_last_exam-scaleofficialevaluation","level":"max","sourceLabel":"claude-opus-4-6-thinking-max","configuration":"Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.; published row 2026-02-17T17:04:32.000Z; reported margin ±1.86 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":34.44,"warning":null},{"id":"5d521eed35c933b8c0cf6ca3","modelId":"gpt-5.6-sol","benchmarkId":"scale-enigma_eval-scaleofficialevaluation","level":"high","sourceLabel":"gpt-5.6-sol-high","configuration":"Scale EnigmaEval puzzle-hunt accuracy; source-reported reasoning effort.; published row 2026-03-25T18:48:38.000Z; reported margin ±2.8 percentage points; No contamination annotation reported (not proof of absence)","score":37.12,"warning":null},{"id":"60804685f644d5cf0ad52320","modelId":"gemini-3.5-flash","benchmarkId":"scale-enigma_eval-scaleofficialevaluation","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"Scale EnigmaEval puzzle-hunt accuracy; source-reported reasoning effort.; published row 2025-11-19T23:53:27.000Z; reported margin ±2.45 percentage points; No contamination annotation reported (not proof of absence)","score":25.41,"warning":null},{"id":"60b0d52dd406e2a990549468","modelId":"gpt-6-astra","benchmarkId":"scale-sweatlas-qna-codex","level":"xhigh","sourceLabel":"GPT 6 Astra (Codex) xHigh*","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-09-09T19:17:58.000Z; reported margin ±4.88 percentage points; No contamination annotation reported (not proof of absence)","score":59.14,"warning":"Starred protocol annotation requires row-specific review before ranking."},{"id":"6c79741b5a7ecef0ff4d0346","modelId":"muse-spark-1.1","benchmarkId":"scale-sweatlas-qna-miniswe","level":"xhigh","sourceLabel":"Muse Spark 1.1 (Mini-SWE-Agent) xHigh","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-07-09T21:00:32.000Z; reported margin ±5.08 percentage points; No contamination annotation reported (not proof of absence)","score":42.2,"warning":null},{"id":"79db12d910dc9b17468fc07c","modelId":"gpt-5.4","benchmarkId":"scale-sweatlas-qna-codex","level":"xhigh","sourceLabel":"GPT 5.4 (Codex) xHigh","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-03-09T16:27:54.000Z; reported margin ±5.1 percentage points; No contamination annotation reported (not proof of absence)","score":40.8,"warning":null},{"id":"8141013d16a793653a973079","modelId":"claude-opus-4-8","benchmarkId":"scale-enigma_eval-scaleofficialevaluation","level":"xhigh","sourceLabel":"claude-opus-4-8-xhigh","configuration":"Scale EnigmaEval puzzle-hunt accuracy; source-reported reasoning effort.; published row 2026-03-10T21:12:05.000Z; reported margin ±2.41 percentage points; No contamination annotation reported (not proof of absence)","score":23.51,"warning":null},{"id":"8154d53aea81c7edfd9708c9","modelId":"muse-spark-1.1","benchmarkId":"scale-sweatlas-tw-miniswe","level":"xhigh","sourceLabel":"Muse Spark 1.1 (Mini-SWE-Agent) xHigh","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-07-09T21:02:58.000Z; reported margin ±5.96 percentage points; No contamination annotation reported (not proof of absence)","score":41.48,"warning":null},{"id":"8adcbb20f22ee3ada097baa2","modelId":"claude-fable-5-1","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"xhigh","sourceLabel":"Fable 5.1 (xhigh)","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2026-09-03T18:19:45.000Z; reported margin ±2.1 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":46.8,"warning":null},{"id":"8b77418f10a0d2c871504615","modelId":"claude-fable-5-1","benchmarkId":"scale-humanitys_last_exam-scaleofficialevaluation","level":"xhigh","sourceLabel":"Fable 5.1 (xhigh)","configuration":"Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.; published row 2026-09-03T18:22:21.000Z; reported margin ±2 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":46.5,"warning":null},{"id":"9a7a2837429ecbebf2d957b1","modelId":"claude-opus-4-6","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"non-reasoning","sourceLabel":"claude-opus-4-6 (Non-Thinking)","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2026-02-17T17:06:51.000Z; reported margin ±1.67 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. ","score":19.37,"warning":null},{"id":"a71c17d0e87547e9f30a79b2","modelId":"claude-opus-4-5-20251101","benchmarkId":"scale-humanitys_last_exam-scaleofficialevaluation","level":"thinking","sourceLabel":"claude-opus-4-5-20251101-thinking","configuration":"Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.; published row 2025-11-26T20:23:24.000Z; reported margin ±1.7 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":25.2,"warning":null},{"id":"b406780519719b231c94f076","modelId":"claude-opus-5","benchmarkId":"scale-sweatlas-tw-claudecode","level":"xhigh","sourceLabel":"Opus 5 (Claude Code) xHigh","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-08-04T16:09:52.000Z; reported margin ±5.58 percentage points; No contamination annotation reported (not proof of absence)","score":62.22,"warning":null},{"id":"ba265c887f15f603db7f5f80","modelId":"claude-opus-4-8","benchmarkId":"scale-sweatlas-qna-claudecode","level":"xhigh","sourceLabel":"Opus 4.8 (Claude Code) xhigh","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-06-08T20:50:16.000Z; reported margin ±4.93 percentage points; No contamination annotation reported (not proof of absence)","score":57.26,"warning":null},{"id":"bfc3139a28a8c37b769ae912","modelId":"claude-fable-5-1","benchmarkId":"scale-sweatlas-qna-claudecode","level":"xhigh","sourceLabel":"Fable-5.1 (Claude Code) xHigh*","configuration":"124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-03-02T20:57:11.000Z; reported margin ±4.85 percentage points; No contamination annotation reported (not proof of absence)","score":59.95,"warning":"Starred protocol annotation requires row-specific review before ranking."},{"id":"c457ac399b0c7c755bf0adbb","modelId":"o3-mini","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"high","sourceLabel":"o3 mini (high)","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2025-04-10T19:29:02.000Z; reported margin ±1.44 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":13.37,"warning":null},{"id":"caa92a3ee80886991f302d07","modelId":"o3-mini","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"medium","sourceLabel":"o3 mini (medium)","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2025-04-10T19:29:02.000Z; reported margin ±1.28 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":10.31,"warning":null},{"id":"cbc2db363833abfb6c9f650d","modelId":"gemini-3.1-pro","benchmarkId":"scale-humanitys_last_exam-scaleofficialevaluation","level":"high","sourceLabel":"gemini-3.1-pro-preview (thinking high)","configuration":"Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.; published row 2026-04-10T15:51:06.000Z; reported margin ±1.96 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":46.44,"warning":null},{"id":"cd7d373c2c6d5a8b1501e762","modelId":"gpt-5.5","benchmarkId":"scale-sweatlas-tw-codex","level":"xhigh","sourceLabel":"GPT-5.5 (Codex) xHigh","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-05-07T16:02:36.000Z; reported margin ±5.96 percentage points; No contamination annotation reported (not proof of absence)","score":42.59,"warning":null},{"id":"d11e9cc7b5eb05e0e97dbb6d","modelId":"claude-opus-4-8","benchmarkId":"scale-sweatlas-tw-claudecode","level":"xhigh","sourceLabel":"Opus 4.8 (Claude Code) xhigh","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-06-08T20:53:39.000Z; reported margin ±5.93 percentage points; No contamination annotation reported (not proof of absence)","score":49.63,"warning":null},{"id":"da0ddcdb318167ad7f56f77a","modelId":"gemini-3.1-pro","benchmarkId":"scale-enigma_eval-scaleofficialevaluation","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"Scale EnigmaEval puzzle-hunt accuracy; source-reported reasoning effort.; published row 2025-11-06T22:52:23.000Z; reported margin ±2.71 percentage points; No contamination annotation reported (not proof of absence)","score":36.78,"warning":null},{"id":"f621460ea8cfcfd9a6843901","modelId":"gemini-3.1-pro","benchmarkId":"scale-humanitys_last_exam_text_only-scaleofficialevaluation","level":"high","sourceLabel":"gemini-3.1-pro-preview (thinking high)","configuration":"Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2026-04-10T15:51:36.000Z; reported margin ±2.11 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":47.31,"warning":null},{"id":"fc3ef3bbe098fd394ff0d2c8","modelId":"gpt-5.6-sol","benchmarkId":"scale-sweatlas-tw-codex","level":"xhigh","sourceLabel":"GPT-5.6-Sol (Codex) xHigh*","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-07-28T19:54:06.000Z; reported margin ±6 percentage points; No contamination annotation reported (not proof of absence)","score":45.9,"warning":"Starred protocol annotation requires row-specific review before ranking."},{"id":"fdcbe9f44fc9ad3996aa935f","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"scale-humanitys_last_exam-scaleofficialevaluation","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929-thinking","configuration":"Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.; published row 2025-10-02T17:27:45.000Z; reported margin ±1.35 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.","score":13.72,"warning":null},{"id":"ffc0fa711ef42f89ea97e2b2","modelId":"claude-fable-5","benchmarkId":"scale-sweatlas-tw-claudecode","level":"xhigh","sourceLabel":"Fable-5 (Claude Code) xHigh*","configuration":"90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-06-11T17:41:27.000Z; reported margin ±5.8 percentage points; No contamination annotation reported (not proof of absence); Board footnote: elevated refusals on benign tasks are scored zero by the evaluator and remain in the published score.","score":55.6,"warning":null},{"id":"panel-ea6e6bc84b19cbbf13457f52","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":99,"warning":null},{"id":"panel-6be887e1f44cda444a386e7b","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":99,"warning":null},{"id":"panel-c8dfdb832c728882285c9b8a","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":99,"warning":null},{"id":"panel-b3c92aa9680c3988ba1d0614","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":97,"warning":null},{"id":"panel-47f44e2cf6028a348add9648","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":98,"warning":null},{"id":"panel-c2408725a1995f2f76a38c0a","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":98,"warning":null},{"id":"panel-d19da72f8f3dcc7122fa23c7","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":99.01,"warning":null},{"id":"panel-727e4929c5b77b8d68e9616f","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":76,"warning":null},{"id":"panel-cac9ea3d75b90f9f8e22b2f6","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":98,"warning":null},{"id":"panel-9ee205c15ad677241207d058","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":98,"warning":null},{"id":"panel-4ef118c3fb039ddcd97965c7","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":98,"warning":null},{"id":"panel-51cb8fa9a9f00859384ed176","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":95,"warning":null},{"id":"panel-f31c0e7a8f4e830bbd7f64c2","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":98,"warning":null},{"id":"panel-9705c757dfdbd2feabac032e","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":98,"warning":null},{"id":"panel-96b3bfd402ebd013b9937af0","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":99,"warning":null},{"id":"panel-fa6c72914cd97c024b6e360a","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":97,"warning":null},{"id":"panel-277c823db47aca935fcfe21d","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":98,"warning":null},{"id":"panel-04f87e2aec3acc7b9cc4f944","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":97,"warning":null},{"id":"panel-79cea26fdffed0236a191bec","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":98,"warning":null},{"id":"panel-8523e2132a25c138914b8459","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":97,"warning":null},{"id":"panel-d24bd2a1ac9eaf9d9494ddaf","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":98,"warning":null},{"id":"panel-0a6ba849134e0075a7f8d9bb","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":98,"warning":null},{"id":"panel-7dbc7ec6565a0f02cf88e3df","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":98,"warning":null},{"id":"panel-3f8750e2188da7c334cd0e4e","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gpt-6-astra-max; checkpoint=gpt-6-astra","score":98,"warning":null},{"id":"panel-d1592c494c0bc37b96c4b13e","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":82,"warning":null},{"id":"panel-5db4666fe0d22748d017fabf","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":89,"warning":null},{"id":"panel-e21e4fca1c3e3b98e1bc5a8c","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-AMPS_Hard","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":99,"warning":null},{"id":"panel-662dfda40adfc5a2caa14820","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-code_completion","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":80.435,"warning":null},{"id":"panel-641076241a9a5fb731ab01d0","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-code_completion","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":82.609,"warning":null},{"id":"panel-d40fdcb405336ff7b0641bc7","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":80.435,"warning":null},{"id":"panel-c7a6b32798ef20c70836ed4e","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":76.087,"warning":null},{"id":"panel-d622ba2d226d053585bbe3b8","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":78.261,"warning":null},{"id":"panel-335d542464864769d1ca1bdf","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-code_completion","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":84.783,"warning":null},{"id":"panel-8dfe6e73a7070dd2ca731ec5","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-code_completion","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":82.609,"warning":null},{"id":"panel-5c66ecc29c060d251f32641f","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-code_completion","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":78.261,"warning":null},{"id":"panel-090d54d836ee129f1e5e6609","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":78.261,"warning":null},{"id":"panel-d3127514aeabe252e43231e1","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":78.261,"warning":null},{"id":"panel-1a02f6b51825ce2ca2fe0cc6","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":76.087,"warning":null},{"id":"panel-607345e5f467b95cf251d99d","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":76.087,"warning":null},{"id":"panel-37f739dcc05b39207d9d2861","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":78.261,"warning":null},{"id":"panel-c117f17c51149f80018795a6","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":76.087,"warning":null},{"id":"panel-3c33dcbb8642d300cb0bd6fa","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":71.739,"warning":null},{"id":"panel-b6daeef5e5290527aac86f54","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-code_completion","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":76.087,"warning":null},{"id":"panel-32aa6b03fa6b1e2b8df86c7b","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":80.435,"warning":null},{"id":"panel-5babfb32a1f20b6e99a59e4e","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":75.556,"warning":null},{"id":"panel-ab5cc700d3ab0b9b4f6bbc85","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":67.391,"warning":null},{"id":"panel-778414f94d6574b36b6dab61","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":82.609,"warning":null},{"id":"panel-f33cd6ce63480f276b68ccdd","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-code_completion","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":86.957,"warning":null},{"id":"panel-c08eb2b8012e609064d33ada","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-code_completion","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":84.783,"warning":null},{"id":"panel-09a415daaa3ba1bf4182a0f7","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-code_completion","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":80.435,"warning":null},{"id":"panel-e91cb820ea7d82b6f4b05678","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-code_completion","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; gpt-6-astra-max; checkpoint=gpt-6-astra","score":80.435,"warning":null},{"id":"panel-7e01c14d29d1b99014cf62ea","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":78.261,"warning":null},{"id":"panel-31199fc389abf8c37e97a1ef","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":80.435,"warning":null},{"id":"panel-e762d325f86c557f5d10186f","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-code_completion","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_completion; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":80.435,"warning":null},{"id":"panel-8a3152b9d28a7530dac28f3d","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-code_generation","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":91.549,"warning":null},{"id":"panel-32989ffe22dc5dd32f1b1f83","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-code_generation","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":90.141,"warning":null},{"id":"panel-e7ab002c6f6098191728383d","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":78.873,"warning":null},{"id":"panel-bfd076ce374bb30a922457d6","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":80.282,"warning":null},{"id":"panel-3eeb212b0c0bb0dc2e478ffa","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":85.915,"warning":null},{"id":"panel-e79c5684c29cd6b303b8c12e","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-code_generation","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":78.873,"warning":null},{"id":"panel-6a2c68e12f2d8caab35e1330","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-code_generation","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":80.282,"warning":null},{"id":"panel-8e215924ae06b331fbc47123","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-code_generation","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":80.282,"warning":null},{"id":"panel-794d65e981554bcb3f0e92e4","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":83.099,"warning":null},{"id":"panel-2d4783c770d432f985707cfd","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":74.648,"warning":null},{"id":"panel-4dca8fee9d98c7ddb0581ad6","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":80.282,"warning":null},{"id":"panel-4d93b113c1ffbccf10888778","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":76.056,"warning":null},{"id":"panel-8326dae2469e1a9f74d18cfa","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":77.465,"warning":null},{"id":"panel-7fc55c6792c58d44fdf6c60a","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":81.69,"warning":null},{"id":"panel-00e8a0af372be006ba3d084d","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":73.239,"warning":null},{"id":"panel-da3a0ed56d6a64f954659fa2","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-code_generation","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":76.056,"warning":null},{"id":"panel-e93f929cb0853d27c95d04b3","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":74.648,"warning":null},{"id":"panel-054ddbbb05cbeafd60110ea3","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":67.692,"warning":null},{"id":"panel-28232fc4ce54814ba09b4d62","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":74.286,"warning":null},{"id":"panel-52c6e1962b976902f29d09a8","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":81.69,"warning":null},{"id":"panel-d63e27e1819ee0b204cf74ed","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-code_generation","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":78.873,"warning":null},{"id":"panel-ada0ae4411fcde2f346dd40e","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-code_generation","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":83.099,"warning":null},{"id":"panel-ca7c8b7e35ea3b5ded4662c3","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-code_generation","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":76.056,"warning":null},{"id":"panel-353e8b3bee4e37d087e93bed","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-code_generation","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; gpt-6-astra-max; checkpoint=gpt-6-astra","score":80.282,"warning":null},{"id":"panel-6baf6c794bf4aaf644c7b7c3","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":76.056,"warning":null},{"id":"panel-90609ba61b59695b58129751","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":74.648,"warning":null},{"id":"panel-4d93f01d1e8e2402aaeb5616","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-code_generation","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-code_generation; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":81.69,"warning":null},{"id":"panel-cfb0683f76806bf4fb0265d0","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-connections","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":99.333,"warning":null},{"id":"panel-ad218815ebcfbb1c50b5859c","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-connections","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":99.333,"warning":null},{"id":"panel-d3216c623cce0c30a3549af3","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":99.333,"warning":null},{"id":"panel-02715a3959bcec12a2118d77","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":99.333,"warning":null},{"id":"panel-fd74c890d8cbdc78ca4926f7","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":92.333,"warning":null},{"id":"panel-de5882ae22989b74ec6dc0e7","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-connections","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":99.333,"warning":null},{"id":"panel-da44c7f3cf2a9599579e7cea","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-connections","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":99.333,"warning":null},{"id":"panel-30450bbe2cd94e48badcae38","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-connections","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":99.333,"warning":null},{"id":"panel-4f59778a92b6497855298360","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":95.5,"warning":null},{"id":"panel-6fb4bc1b60f839623c5d4381","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":100,"warning":null},{"id":"panel-828ad3db06596510a3a5b361","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":100,"warning":null},{"id":"panel-85e5f51bb280d552f8a1344b","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":92,"warning":null},{"id":"panel-99585dbf3dfb57868d6e94e8","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":100,"warning":null},{"id":"panel-f4dc253f7a805058432fb239","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":100,"warning":null},{"id":"panel-4d73f7faa8106fea92f3fb4d","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":100,"warning":null},{"id":"panel-77f63d80977191cf2c481d68","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-connections","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":99,"warning":null},{"id":"panel-424fc5747345bdb81336e06a","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":100,"warning":null},{"id":"panel-7ad1f49952e339692c304819","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":98.98,"warning":null},{"id":"panel-342d090b1be63195b7fa706e","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":94.388,"warning":null},{"id":"panel-f8a70bbbcd0f698be7bc1a43","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":100,"warning":null},{"id":"panel-f55d9d7148753278f84c2df4","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-connections","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":96.5,"warning":null},{"id":"panel-014e5b85ba751dcc8149108e","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-connections","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":100,"warning":null},{"id":"panel-de29cc4390253be5d2777e81","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-connections","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":93,"warning":null},{"id":"panel-c1b3d7f5a165e5b35bf2018b","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-connections","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; gpt-6-astra-max; checkpoint=gpt-6-astra","score":100,"warning":null},{"id":"panel-1cba090af30c55faf508a232","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":98,"warning":null},{"id":"panel-bbd53ca4e345a1af051f9838","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":100,"warning":null},{"id":"panel-d86a15e1a604826048816160","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-connections","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-connections; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":94,"warning":null},{"id":"panel-190855818b7e1222a48e2eae","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":91.36,"warning":null},{"id":"panel-fd99f744a0c951b883b6eaea","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":90.555,"warning":null},{"id":"panel-9fbf2f2774c52b4c65e96782","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":79.363,"warning":null},{"id":"panel-39728f4c4f0069938bbfdf20","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":63.467,"warning":null},{"id":"panel-1b8be849869ca37987fe3c9f","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":89.521,"warning":null},{"id":"panel-dd863a0d16624af984380aa0","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":52.905,"warning":null},{"id":"panel-2aa437a8829dbf56b4b5d351","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":77.571,"warning":null},{"id":"panel-9a9cff8685184797af933836","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":92.683,"warning":null},{"id":"panel-dc52f3d94a18a75b842b27ef","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":74.741,"warning":null},{"id":"panel-b70f7219a2898aed69af5a1b","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":85.239,"warning":null},{"id":"panel-c0f6c7ecaaece53d8096cb1a","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":47.994,"warning":null},{"id":"panel-27b4ef02c7a063ec88c3ddc7","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":21.095,"warning":null},{"id":"panel-56f7440caf2be4e507c56b62","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":43.824,"warning":null},{"id":"panel-c7924ab86a4819c0c3bc7f8f","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":60.373,"warning":null},{"id":"panel-147c821e2fbfd731f109691d","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":20.612,"warning":null},{"id":"panel-a2b9872bb59a3f7ac3aff0c0","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":88.913,"warning":null},{"id":"panel-686153cb0b44a71199a0619d","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":86.19,"warning":null},{"id":"panel-8afc38f69537e97bbf2c5a67","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":62.972,"warning":null},{"id":"panel-7b24c6ef6a4016a1ce0ec99a","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":54.301,"warning":null},{"id":"panel-8f65ef6ded7e915b5df1386a","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":88.823,"warning":null},{"id":"panel-ebc66a99e1b9d323c3fa4812","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":86.504,"warning":null},{"id":"panel-1f6eb2d767a08535a94cb732","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":90.214,"warning":null},{"id":"panel-cf82c90989f66444fdc5693d","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":87.67,"warning":null},{"id":"panel-ec9906abde481a797aa4cc9a","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; gpt-6-astra-max; checkpoint=gpt-6-astra","score":90.555,"warning":null},{"id":"panel-b0e641583182f918dc7c7607","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":71.086,"warning":null},{"id":"panel-dbe6aa071a22ccaa40e097c9","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":82.548,"warning":null},{"id":"panel-9b4dc6b2d88a35de49975d62","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-consecutive_events","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":90.504,"warning":null},{"id":"panel-1330ccf27b12cf2611c21dbe","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":97,"warning":null},{"id":"panel-65c52ed61e13ff7b3b9fb1e6","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":99,"warning":null},{"id":"panel-1ee6676d7e81096dff4bb6b9","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":78,"warning":null},{"id":"panel-fb548e320f80168b36d88c76","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":73,"warning":null},{"id":"panel-cf976805e5a88ef22e6c1aa3","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":84,"warning":null},{"id":"panel-5610f87659e4a35f39fc8224","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":89,"warning":null},{"id":"panel-f717d2864a445467e54f0414","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":97,"warning":null},{"id":"panel-e9fc47dbe181087a7a1a77db","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":90,"warning":null},{"id":"panel-130f53a4fe944096e9fb6b61","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":88,"warning":null},{"id":"panel-4f12ebc87581a8b3fead6ca5","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":78,"warning":null},{"id":"panel-6ffc749529292fd222d18cba","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":68,"warning":null},{"id":"panel-f573c5db18f106fe09304de4","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":26,"warning":null},{"id":"panel-45e2f893822c593c4ecd6e28","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":63,"warning":null},{"id":"panel-78e254545a2ae1a666fe3269","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":88,"warning":null},{"id":"panel-20246bf3e3306bd736a3c80c","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":80,"warning":null},{"id":"panel-2c75d7123d8291e5be81a00b","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":92,"warning":null},{"id":"panel-ead1203dc409c40234d5fee4","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":93,"warning":null},{"id":"panel-4305d4d3278517373e3f5b3e","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":37,"warning":null},{"id":"panel-7934928ca32eaec604963700","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":82.828,"warning":null},{"id":"panel-87b260b8aea4065b7af8575f","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":99,"warning":null},{"id":"panel-bb3ced238358ea1c61780784","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":70,"warning":null},{"id":"panel-e42b32e0c02a97ebf85ee088","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":100,"warning":null},{"id":"panel-a9f487811c15538616e240dc","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":95,"warning":null},{"id":"panel-1a8d0032f7d3827254000690","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; gpt-6-astra-max; checkpoint=gpt-6-astra","score":100,"warning":null},{"id":"panel-ff7deaad8514a735c60215cd","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":83,"warning":null},{"id":"panel-939b2284f37f61d8eb5f67b6","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":91,"warning":null},{"id":"panel-ea3620ceae6503098460020c","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-integrals_with_game","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":96,"warning":null},{"id":"panel-9e636b17bbcae275ecd8ee17","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-javascript","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":68.182,"warning":null},{"id":"panel-dfcdc9973f2a0d00f0fc919c","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-javascript","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":68.182,"warning":null},{"id":"panel-e7184a5ecfae339d037a2b4e","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":59.091,"warning":null},{"id":"panel-6414676946387e29fa05c0a8","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":63.636,"warning":null},{"id":"panel-33d654882b80b1889204d2e4","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":63.636,"warning":null},{"id":"panel-af8e1e7afb22e13a8161b804","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-javascript","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":68.182,"warning":null},{"id":"panel-1915dc0e10000252e26496f2","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-javascript","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":77.273,"warning":null},{"id":"panel-239cfd267c6875696e83c9cb","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-javascript","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":54.545,"warning":null},{"id":"panel-e6a2705861cdce46400bf7cb","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":68.182,"warning":null},{"id":"panel-58aac2c2dde4fbb0c2408d75","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":59.091,"warning":null},{"id":"panel-f9834bac2c8a90d6c7ce4e5e","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":63.636,"warning":null},{"id":"panel-5c58f2a3098155c426bac27d","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":59.091,"warning":null},{"id":"panel-f2c256a295bd7932f236f885","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":63.636,"warning":null},{"id":"panel-36628f2999915365afee11c0","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":68.182,"warning":null},{"id":"panel-eaf227f5b755476d39c81ae7","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":72.727,"warning":null},{"id":"panel-49c4b3d4d02e77f4afa7ec01","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-javascript","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":59.091,"warning":null},{"id":"panel-53e2e2b8cbdb216a093034bf","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":68.182,"warning":null},{"id":"panel-422822cff2d0c951a07e107d","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":50,"warning":null},{"id":"panel-ed27fdf022a823e0abcb4c54","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":63.636,"warning":null},{"id":"panel-1de01be8339431f506375fa6","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":63.636,"warning":null},{"id":"panel-0468cbf93870ad38beab1059","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-javascript","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":63.636,"warning":null},{"id":"panel-e366b9965c11ca7171a26c5e","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-javascript","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":63.636,"warning":null},{"id":"panel-b227ac7dafc453027f546347","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-javascript","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":68.182,"warning":null},{"id":"panel-d0d17e92e62bfc0685fa0240","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-javascript","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; gpt-6-astra-max; checkpoint=gpt-6-astra","score":63.636,"warning":null},{"id":"panel-6bdc2206bd256d34c7fd7650","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":77.273,"warning":null},{"id":"panel-c37413eeb9c7e46ddfc253d2","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":72.727,"warning":null},{"id":"panel-e2b90ad9ff025816b82efbba","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-javascript","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":77.273,"warning":null},{"id":"panel-fb6b440bc03b13ca1c9f354c","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":78,"warning":null},{"id":"panel-8f0343e8b72f79cdda804ff7","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":86,"warning":null},{"id":"panel-5391f4e5c06b72826fee1ad5","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":68,"warning":null},{"id":"panel-f1f80cee7d1e762d01154e92","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":80,"warning":null},{"id":"panel-4172bd2caec615ab3eff3b0c","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":70,"warning":null},{"id":"panel-c3668fe9c1af9e1f815034dc","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":78,"warning":null},{"id":"panel-8b775d5d773456b6ab271308","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":86,"warning":null},{"id":"panel-d4d1042248b561833a92f2c4","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":70,"warning":null},{"id":"panel-e8a89b55eb0543d94e2cc816","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":86,"warning":null},{"id":"panel-4d524cc2ad780da119be2cf9","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":72,"warning":null},{"id":"panel-79730153cbde8d293d44213a","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":74,"warning":null},{"id":"panel-873971713d4ce0742cfd0e18","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":68,"warning":null},{"id":"panel-19da7fc7d58c0bfc47ec9a8c","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":76,"warning":null},{"id":"panel-e23f33b25b7acb309969ee70","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":74,"warning":null},{"id":"panel-4000faefeda3951617e07ec9","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":82,"warning":null},{"id":"panel-50a0a1f23eeb2eceab0f4c4a","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":74,"warning":null},{"id":"panel-ce06ee813be216293e7004cf","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":68,"warning":null},{"id":"panel-603dd81fba10b50320567b1e","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":60,"warning":null},{"id":"panel-76844476c511fb7c5531e3e8","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":64,"warning":null},{"id":"panel-ad21b2b9b3a285f669bede29","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":76,"warning":null},{"id":"panel-c2188e8931d7269e78bdf635","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":80,"warning":null},{"id":"panel-51a4f42f816be6130de2f015","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":82,"warning":null},{"id":"panel-f9e413513f7da7d9e60b6964","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":76,"warning":null},{"id":"panel-60bacf6417f2d976a9991114","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; gpt-6-astra-max; checkpoint=gpt-6-astra","score":88,"warning":null},{"id":"panel-eb8e759c8756c57a6678b38c","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":78,"warning":null},{"id":"panel-4a402a6edf729fb609faca1b","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":88,"warning":null},{"id":"panel-a608739b95a5826c41cbb0bc","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-logic_with_navigation","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":76,"warning":null},{"id":"panel-bdae59106882e6ce30423560","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-math_comp","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":95.098,"warning":null},{"id":"panel-67e783f1c412af0bc138d97d","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-math_comp","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":97.059,"warning":null},{"id":"panel-f4611dea0f98ae60341b3497","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":95.098,"warning":null},{"id":"panel-9af7f61af6179d5eac0c51be","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":95.098,"warning":null},{"id":"panel-9266dd9fd15700366b37c0ed","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":98.039,"warning":null},{"id":"panel-3dd977ca39f5c684439cf98e","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-math_comp","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":98.039,"warning":null},{"id":"panel-919a5557dc2a750353058ef4","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-math_comp","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":94.118,"warning":null},{"id":"panel-61b37a37ffa13a56ab533193","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-math_comp","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":94.118,"warning":null},{"id":"panel-a2e219e671bd391642993295","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":95.098,"warning":null},{"id":"panel-dd35ef007b87680fc5d395d0","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":96.078,"warning":null},{"id":"panel-65f8d6e0729b9c5c42dba5c9","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":95.098,"warning":null},{"id":"panel-d44be38166189727bb5717a2","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":92.157,"warning":null},{"id":"panel-ef97c9d27235b86d73fda913","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":94.118,"warning":null},{"id":"panel-6fcbe883dd2cc95616b54d6f","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":96.078,"warning":null},{"id":"panel-51fe9f895027fea4c0ae2759","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":95.098,"warning":null},{"id":"panel-fbcbde600561c3d3696be83c","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-math_comp","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":95.098,"warning":null},{"id":"panel-14b8986f6045509b1190f001","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":94.118,"warning":null},{"id":"panel-1eb69e1e8bf07bc6c2dd0181","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":94.118,"warning":null},{"id":"panel-21ace49cde007a4ad2f4e1f5","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":95.098,"warning":null},{"id":"panel-f845a78cc2cb4939b0d457d3","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":96.078,"warning":null},{"id":"panel-336ccdda131c10a4ceb1c659","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-math_comp","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":92.157,"warning":null},{"id":"panel-b2d8d393da701a3f89530fc2","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-math_comp","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":95.098,"warning":null},{"id":"panel-a3408fd345658854b48ac897","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-math_comp","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":95.098,"warning":null},{"id":"panel-49cb0eef818478e18b9fc73e","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-math_comp","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; gpt-6-astra-max; checkpoint=gpt-6-astra","score":97.059,"warning":null},{"id":"panel-9a71dad62d416416d1786c72","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":96.078,"warning":null},{"id":"panel-b4abe05d293dd2f434bf065b","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":97.059,"warning":null},{"id":"panel-eb4ce80a488879c6c664dde7","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-math_comp","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-math_comp; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":97.059,"warning":null},{"id":"panel-43a711c2e4bf1032ca789322","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-olympiad","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":92.845,"warning":null},{"id":"panel-6c18356f3e605ccf870bc0e4","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-olympiad","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":92.968,"warning":null},{"id":"panel-09c708f2367d5cdaf9f13aaf","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":89.458,"warning":null},{"id":"panel-0d7a1d9d2a51aa4564298f91","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":92.17,"warning":null},{"id":"panel-9569698400df06830af314ab","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":91.376,"warning":null},{"id":"panel-141f8c45edac9dc4154ac08a","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-olympiad","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":92.227,"warning":null},{"id":"panel-35992b4dd228235b40982727","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-olympiad","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":92.796,"warning":null},{"id":"panel-7d9064929591d93f9978bec5","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-olympiad","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":87.858,"warning":null},{"id":"panel-6ade069d452324b81f97d2d0","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":90.671,"warning":null},{"id":"panel-8272dd6e6a4ec9a8e6cbdc9f","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":92.102,"warning":null},{"id":"panel-43e3fa367afc5689d6e1a375","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":91.877,"warning":null},{"id":"panel-c72b7981866ef805a49330cf","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":81.801,"warning":null},{"id":"panel-c399a15bbae382124505b488","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":90.492,"warning":null},{"id":"panel-b0cd868f837f3c8d3ba378c0","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":91.794,"warning":null},{"id":"panel-0ebcff26b3dd1ee910c0e7d8","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":92.159,"warning":null},{"id":"panel-e236e8906de2ac79a50c15e6","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-olympiad","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":88.566,"warning":null},{"id":"panel-387ee41f45c34973406f6a99","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":91.474,"warning":null},{"id":"panel-1a9f74dc3ba9d5be73f6de46","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":85.73,"warning":null},{"id":"panel-261505d025f9d0d994bd7c1c","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":87.982,"warning":null},{"id":"panel-f7afb6dfa5602fcbcc94b9b9","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":91.351,"warning":null},{"id":"panel-f35f8aae0d8d575b94fd76cf","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-olympiad","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":88.646,"warning":null},{"id":"panel-5f7b8f51d17c740d7ce23328","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-olympiad","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":91.693,"warning":null},{"id":"panel-2ffe687d54dc27361f384c80","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-olympiad","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":91.535,"warning":null},{"id":"panel-c033816ccaa5e32d8fc2fa0d","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-olympiad","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; gpt-6-astra-max; checkpoint=gpt-6-astra","score":92.166,"warning":null},{"id":"panel-5f2ebc6018d88a7989407282","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":87.501,"warning":null},{"id":"panel-7d6cb0c0f64f505b9a71b6ff","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":87.755,"warning":null},{"id":"panel-ae4a0aa81365bb0ac625fdee","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-olympiad","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-olympiad; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":91.741,"warning":null},{"id":"panel-2be4cdc484550578181f30a1","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-paraphrase","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":77.65,"warning":null},{"id":"panel-7b21ddb3a6195cfe20acdf0f","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-paraphrase","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":71.517,"warning":null},{"id":"panel-b7c7abb64ed26c981fa97ecb","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":65.667,"warning":null},{"id":"panel-53612080416a8a2c52255475","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":62.817,"warning":null},{"id":"panel-369a3b2d9f40c49f3783f859","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":65.767,"warning":null},{"id":"panel-d1b3a97faa4ffcecfd7ad8f3","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-paraphrase","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":67.867,"warning":null},{"id":"panel-1099925f01eec7849c621575","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-paraphrase","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":65.733,"warning":null},{"id":"panel-c1f148c80800c7bb48207f5e","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-paraphrase","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":59.4,"warning":null},{"id":"panel-47835dba414723cbd89102e1","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":61.25,"warning":null},{"id":"panel-6730b76b0480a9ddba9ceb60","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":79.867,"warning":null},{"id":"panel-54d0390b13496c156fa846ab","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":75.517,"warning":null},{"id":"panel-e759c56964927bda6b798d1b","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":65,"warning":null},{"id":"panel-217316b453a05c8a737a5311","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":74.317,"warning":null},{"id":"panel-0973b8fdc8a954215ca48936","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":78.067,"warning":null},{"id":"panel-8e7c5485b183951578bf6f63","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":80,"warning":null},{"id":"panel-c0d042721929915c8645b57d","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-paraphrase","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":64.1,"warning":null},{"id":"panel-6212f1adcca2531c22bd97dc","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":63.433,"warning":null},{"id":"panel-20cb55fec83d1270c8d422e2","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":58.883,"warning":null},{"id":"panel-6ffae1ead5b7afc06bdb440c","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":66.649,"warning":null},{"id":"panel-67db00b7f19613b66461ba0f","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":71.733,"warning":null},{"id":"panel-f4035a99f61947c9e2d3a096","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-paraphrase","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":47.817,"warning":null},{"id":"panel-aee7349a79f0e6aea04d06f6","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-paraphrase","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":71.517,"warning":null},{"id":"panel-b9a05d343e2978f3dcffdc61","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-paraphrase","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":57.033,"warning":null},{"id":"panel-963e7b44cd565be1b3cc9695","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-paraphrase","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; gpt-6-astra-max; checkpoint=gpt-6-astra","score":78.25,"warning":null},{"id":"panel-64d9137045cdef710bd3ca92","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":69.4,"warning":null},{"id":"panel-d10f6d2cdabb5ddb7e4899d2","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":74.3,"warning":null},{"id":"panel-d4235d275b78c1d09ff5b633","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-paraphrase","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-paraphrase; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":78.617,"warning":null},{"id":"panel-03a1e315c4f027dcfd8299b7","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":78.719,"warning":null},{"id":"panel-d60952da8f212b02c5b80e5a","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":75.17,"warning":null},{"id":"panel-bd2cb017dd4aabc76d11d0f5","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":66.45,"warning":null},{"id":"panel-5db103e8c0d0940f23c1c437","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":66.476,"warning":null},{"id":"panel-9884a6b97b5686266ebc97bd","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":61.409,"warning":null},{"id":"panel-4ed8370e5706671ee5d2dd82","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":61.645,"warning":null},{"id":"panel-bf356ff8ba3d33e34d5d7695","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":74.731,"warning":null},{"id":"panel-57c9d66e18c45c4f050a462a","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":56.975,"warning":null},{"id":"panel-a7b7df43b105c928e66b1c2f","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":53.411,"warning":null},{"id":"panel-0662502669451fa91c907b36","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":74.128,"warning":null},{"id":"panel-e5935fb8a328a72c57a5ecc4","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":67.753,"warning":null},{"id":"panel-7393786a27fc26872419dcaa","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":49.461,"warning":null},{"id":"panel-f128b281d5845ab277063785","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":63.693,"warning":null},{"id":"panel-b18397a1aab14698db6506d5","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":66.365,"warning":null},{"id":"panel-21d2715c30bd186f37bdd468","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":73.378,"warning":null},{"id":"panel-91d118503479005ce69deb47","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":58.427,"warning":null},{"id":"panel-6fda03e93661f6c58ea5e7e4","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":65.901,"warning":null},{"id":"panel-776124249647ccf9c51344bb","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":43.875,"warning":null},{"id":"panel-62a295778554ce1fab5fb5a5","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":39.133,"warning":null},{"id":"panel-5990349629b3aae8b03c2734","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":74.089,"warning":null},{"id":"panel-e05a7d89da690e9010835fcf","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":51.201,"warning":null},{"id":"panel-76fb0a8d12e96d2ae0671a45","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":79.051,"warning":null},{"id":"panel-32a3607710de8dca34022897","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":69.678,"warning":null},{"id":"panel-299ef4c22b4342670d0dae08","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; gpt-6-astra-max; checkpoint=gpt-6-astra","score":86.292,"warning":null},{"id":"panel-3cfdcdd691354a0a5029cdd2","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":63.026,"warning":null},{"id":"panel-b100b1155d4fad7945551d5b","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":61.724,"warning":null},{"id":"panel-01d19abcae8228176928ff95","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-plot_unscrambling","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":68.381,"warning":null},{"id":"panel-a2de81d0984e710daa10737b","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-python","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":65,"warning":null},{"id":"panel-03d6d7332196ab2b7940014a","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-python","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":70,"warning":null},{"id":"panel-344cfa519ab6003234bf074c","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":40,"warning":null},{"id":"panel-b8667c26ba0685da759190a2","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":50,"warning":null},{"id":"panel-662364bb53927d6d913898d5","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":45,"warning":null},{"id":"panel-75a12802fa02fbeea400c4cb","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-python","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":50,"warning":null},{"id":"panel-679a950ffb35122c670ad6ba","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-python","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":75,"warning":null},{"id":"panel-c9dec434280ecd1032922f0a","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-python","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":50,"warning":null},{"id":"panel-667bd298eef009be052a0928","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":60,"warning":null},{"id":"panel-728ecc9a397966fe315b4b0a","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":50,"warning":null},{"id":"panel-f0a38c4adeea44226aae53f0","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":50,"warning":null},{"id":"panel-0e6208d14f6ce63317052579","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":50,"warning":null},{"id":"panel-8d9e48f418b10c02e9fa3a61","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":40,"warning":null},{"id":"panel-eaef80a81b2207fafc6cf592","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":60,"warning":null},{"id":"panel-aef8a69ac35010bb70d01430","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":50,"warning":null},{"id":"panel-09e4a65f3e19547b97c9aaf4","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-python","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":55,"warning":null},{"id":"panel-cd52404d183578937e22deac","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":50,"warning":null},{"id":"panel-e6821f14580e75e469839a58","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":55,"warning":null},{"id":"panel-26dd5319f2452d0d3e5920b6","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":50,"warning":null},{"id":"panel-843ad8b9e75ccb2e2e0290aa","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":55,"warning":null},{"id":"panel-3b0a9ae45b36b943f938ebee","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-python","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":45,"warning":null},{"id":"panel-c932d96633f436c5ab84fc2a","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-python","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":55,"warning":null},{"id":"panel-e1f754b895ac409b7ff2d1f9","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-python","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":50,"warning":null},{"id":"panel-d5ad12f947dad7a22a4caa26","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-python","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; gpt-6-astra-max; checkpoint=gpt-6-astra","score":65,"warning":null},{"id":"panel-cb4d12433d4ef2158a779de3","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":55,"warning":null},{"id":"panel-1c622171ac4a61c0905126a8","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":50,"warning":null},{"id":"panel-60b5fcefe36e164667e674a2","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-python","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":55,"warning":null},{"id":"panel-c8fc51de7487c1b2d258c0f2","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-simplify","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":72.033,"warning":null},{"id":"panel-e497283877b2504635abf48e","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-simplify","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":70.167,"warning":null},{"id":"panel-5df71994be4789f38c407267","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":54.95,"warning":null},{"id":"panel-19218562af1e33a655a35d87","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":59.15,"warning":null},{"id":"panel-74ec4158f36d43fe6107c6cb","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":65.5,"warning":null},{"id":"panel-69f8e076de1d08be8612d652","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-simplify","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":62,"warning":null},{"id":"panel-c4700c0736a7c76bf94c8d04","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-simplify","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":61.583,"warning":null},{"id":"panel-7395d6919946c2adfaf7424b","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-simplify","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":62.933,"warning":null},{"id":"panel-91e73f1dddb884058280f326","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":60.65,"warning":null},{"id":"panel-0e57c643f0410832cbc9fb48","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":71.05,"warning":null},{"id":"panel-7b35407610dfe74743495040","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":69.1,"warning":null},{"id":"panel-5c1bdcb24909d99616ed5841","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":68.017,"warning":null},{"id":"panel-ed8c7db295ec15f18a8163ae","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":75.7,"warning":null},{"id":"panel-c238833b50dc00f09d833ac6","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":74.617,"warning":null},{"id":"panel-117a0e497718ad4b2bcd3af5","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":75.4,"warning":null},{"id":"panel-790eb22013b7deb683b85849","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-simplify","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":54.083,"warning":null},{"id":"panel-6f5160d5e1a3874da330f091","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":70,"warning":null},{"id":"panel-7f34159560b42fbf4f72e29d","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":54.067,"warning":null},{"id":"panel-218cd2b7f3fa4ba48808e4fc","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":62.75,"warning":null},{"id":"panel-7f78f88694ccc33fb7e0c3d3","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":66.317,"warning":null},{"id":"panel-332b86a089da785cdea3f402","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-simplify","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":58.667,"warning":null},{"id":"panel-1bbc8f3b917da240bd97fec6","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-simplify","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":70.517,"warning":null},{"id":"panel-949d2db642838c34e2d944f3","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-simplify","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":61.433,"warning":null},{"id":"panel-759a23b0d450b5e3fb8ee226","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-simplify","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; gpt-6-astra-max; checkpoint=gpt-6-astra","score":70.533,"warning":null},{"id":"panel-fd205044a78778402333b4ab","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":65.7,"warning":null},{"id":"panel-c5de3c6d1577f440b4c8c784","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":68.733,"warning":null},{"id":"panel-21fd85624e4a16f80678eeb6","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-simplify","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-simplify; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":72.517,"warning":null},{"id":"panel-983329bcfa432e4151bc9bc2","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-spatial","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":96,"warning":null},{"id":"panel-a7d2871bbc6917780c8d21b3","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-spatial","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":100,"warning":null},{"id":"panel-870d52baedb6499434a24a51","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":96,"warning":null},{"id":"panel-a794216ca56ac67f785dad20","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":98,"warning":null},{"id":"panel-5d21ba95ec8fdb8b8e301fac","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":100,"warning":null},{"id":"panel-c8c35a24dc4b0f79d4adbb2f","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-spatial","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":98,"warning":null},{"id":"panel-ff77a6c3a9e65b6ccb8e3a7c","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-spatial","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":100,"warning":null},{"id":"panel-a0dacead0b0fff9e77e638df","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-spatial","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":100,"warning":null},{"id":"panel-6e17221392c2b73cb835e55c","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":100,"warning":null},{"id":"panel-6af50c99811132886f95297a","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":98,"warning":null},{"id":"panel-779fc91b62607caad532fe71","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":96,"warning":null},{"id":"panel-6a0b5beb7d2564d7dfeee8dd","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":90,"warning":null},{"id":"panel-62c1d3bad9ee9ff062c24b7c","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":100,"warning":null},{"id":"panel-bcfd094cfd1370b8184eb917","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":100,"warning":null},{"id":"panel-e0bda6cdff53e878f032c374","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":100,"warning":null},{"id":"panel-8cb5768c95cfc9d9ee948a32","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-spatial","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":96,"warning":null},{"id":"panel-52f73ccb84c0dad0faf4db74","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":98,"warning":null},{"id":"panel-cbdc096fb05b58e68fa0a78b","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":88,"warning":null},{"id":"panel-5871d8133517ae7eab0f50d6","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":82,"warning":null},{"id":"panel-a54de73dfe62d0d252c262de","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":98,"warning":null},{"id":"panel-6b6298d5105594af69577e2b","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-spatial","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":96,"warning":null},{"id":"panel-aa139a442c1d74acd762316c","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-spatial","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":100,"warning":null},{"id":"panel-d65e406870344792f02f74dc","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-spatial","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":100,"warning":null},{"id":"panel-29daa78a29277b8e3c4e1935","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-spatial","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; gpt-6-astra-max; checkpoint=gpt-6-astra","score":98,"warning":null},{"id":"panel-79c0b925029bc6018d77d2de","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":100,"warning":null},{"id":"panel-315c13eaf06cba3126de4186","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":96,"warning":null},{"id":"panel-6c3961f5f7f2f61d3927bbf6","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-spatial","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-spatial; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":100,"warning":null},{"id":"panel-2af525469b096e71b83c05f7","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-story_generation","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":71.7,"warning":null},{"id":"panel-cceb36ce7791a1eb1562144d","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-story_generation","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":78.1,"warning":null},{"id":"panel-e87a024bc711a8588ca5c4a5","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":65.85,"warning":null},{"id":"panel-ba137339713465f06d96bfe2","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":66.133,"warning":null},{"id":"panel-fb153f17dcaa7568a31cc10e","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":69.4,"warning":null},{"id":"panel-f24c3abaf143433907c54872","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-story_generation","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":80.6,"warning":null},{"id":"panel-3e98d27984c5af805c065745","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-story_generation","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":61.317,"warning":null},{"id":"panel-97a9005f0a93edb4193e1c8a","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-story_generation","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":68.9,"warning":null},{"id":"panel-6b40d917d05afe59030e43e3","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":62.317,"warning":null},{"id":"panel-1daa1fc476d17b814e17715a","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":77.25,"warning":null},{"id":"panel-8db1335a3d1c4eb91f13f494","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":75.2,"warning":null},{"id":"panel-c11b52096eae273aa28d6c38","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":67.467,"warning":null},{"id":"panel-3b96713def9718e318008623","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":75.6,"warning":null},{"id":"panel-386333b19f9f51f693fcf5f9","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":82.25,"warning":null},{"id":"panel-717fe68688b1cd88d3865fa7","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":82.75,"warning":null},{"id":"panel-eaa5fc61415b8aa88e767880","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-story_generation","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":65.7,"warning":null},{"id":"panel-930496933f2794492ab365b2","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":79.017,"warning":null},{"id":"panel-2d9a5f1ed5367f0741ff26d2","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":66.633,"warning":null},{"id":"panel-7a8291feea5ecd53861d115b","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":67.653,"warning":null},{"id":"panel-ecbe45e5b2d5de3f475a6b9a","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":72.55,"warning":null},{"id":"panel-cc1676839b16b4cae9c2b786","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-story_generation","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":69.067,"warning":null},{"id":"panel-f5913ad96576103aa18ce7e0","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-story_generation","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":75.917,"warning":null},{"id":"panel-acc39098a765b02240f927e9","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-story_generation","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":66.833,"warning":null},{"id":"panel-ea75961dc8f3284bcade8e4d","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-story_generation","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; gpt-6-astra-max; checkpoint=gpt-6-astra","score":73.983,"warning":null},{"id":"panel-643a2b102ca96cc1c855d0d9","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":69.15,"warning":null},{"id":"panel-6e422918805d22eb5f088d67","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":73.65,"warning":null},{"id":"panel-42a2d7c7037fb97d8e799de8","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-story_generation","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-story_generation; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":77.483,"warning":null},{"id":"panel-dc7ca75625f95fde3437e823","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-summarize","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":81.7,"warning":null},{"id":"panel-6c20b285e58d1c77b49b2468","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-summarize","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":72.167,"warning":null},{"id":"panel-d11017bb0a00fabdb4412bad","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":63.717,"warning":null},{"id":"panel-f627cd7090aff302ea1688bd","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":65.15,"warning":null},{"id":"panel-2feb2a233295800339a769e5","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":66.283,"warning":null},{"id":"panel-520b3b60cfad57f258de5139","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-summarize","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":77.667,"warning":null},{"id":"panel-f6473e04c058c6372d74263c","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-summarize","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":66.433,"warning":null},{"id":"panel-10dfde1dfd55d1050db26ccd","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-summarize","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":61.65,"warning":null},{"id":"panel-1a215fce1b280d87fa9122ee","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":71.217,"warning":null},{"id":"panel-0ae689afa56fc1952d84c292","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":88.233,"warning":null},{"id":"panel-69d89ddfd6815cc3c5feb368","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":82.583,"warning":null},{"id":"panel-82b98df2935ac4c2e6f10aba","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":68.467,"warning":null},{"id":"panel-422f1455cd480504d8bec31c","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":75.85,"warning":null},{"id":"panel-d4152f1599eec1bd1bc2db33","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":84.767,"warning":null},{"id":"panel-71ca1e47d78479714d961f87","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":87.5,"warning":null},{"id":"panel-14610010800749fab1e3696a","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-summarize","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":63.2,"warning":null},{"id":"panel-4844de203c7156b6d863ace0","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":68.417,"warning":null},{"id":"panel-8c3e5d2106f12b3a8b88ef1b","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":59.633,"warning":null},{"id":"panel-7c91d12d311b446ed2b720d6","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":71.767,"warning":null},{"id":"panel-cf744fd7b4c62f6358037653","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":72.317,"warning":null},{"id":"panel-2c494e13cd9d39187d4dfaf9","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-summarize","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":64.933,"warning":null},{"id":"panel-350f2da94844393f21c11f7e","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-summarize","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":69.433,"warning":null},{"id":"panel-eea8659463585ccb5e9e0a4b","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-summarize","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":73.167,"warning":null},{"id":"panel-947aa825ea0ab05af778ef0a","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-summarize","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; gpt-6-astra-max; checkpoint=gpt-6-astra","score":79.55,"warning":null},{"id":"panel-87b456d84438ff05a853f952","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":74.3,"warning":null},{"id":"panel-9e2379b2378edc420ca56706","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":80.617,"warning":null},{"id":"panel-753a406f6be326ef24fd319e","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-summarize","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-summarize; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":83.4,"warning":null},{"id":"panel-29667ef98b3f5bca5f681c85","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-tablejoin","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":56.135,"warning":null},{"id":"panel-0deb807684d82cf80a5af7d2","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-tablejoin","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":56.154,"warning":null},{"id":"panel-6e02eab7a3e609f6dd618035","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":45.923,"warning":null},{"id":"panel-83f1eb7d5def019910aba669","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":48.173,"warning":null},{"id":"panel-f2174ccbca480f517cbd3ca4","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":47.231,"warning":null},{"id":"panel-e90fea5b53cba5c187c6980e","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-tablejoin","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":51.077,"warning":null},{"id":"panel-3f2a9bc3bdb1688bb3f3d825","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-tablejoin","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":51.962,"warning":null},{"id":"panel-2159cc97a8071f41f95b2bac","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-tablejoin","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":45.077,"warning":null},{"id":"panel-393d1ac80d2e548ca5be81d3","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":42.442,"warning":null},{"id":"panel-35844166e61bc0d5a71876d2","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":52.346,"warning":null},{"id":"panel-d341295ae8ea744fc27e72c3","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":50.5,"warning":null},{"id":"panel-6f800c82438e0951dfa9fdfc","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":40.615,"warning":null},{"id":"panel-40d49ac5b8305a87cd60dc70","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":47.135,"warning":null},{"id":"panel-e7c14e2adb74037187f0ec1c","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":45.481,"warning":null},{"id":"panel-850a0242aec8243d437d32ec","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":45.327,"warning":null},{"id":"panel-ef9a0693d34f00cba25d1252","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-tablejoin","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":45.577,"warning":null},{"id":"panel-eca935ff02296892416ebe55","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":51.75,"warning":null},{"id":"panel-5b692cff35fdaff8c4dbf68d","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":49.385,"warning":null},{"id":"panel-96e3931bb0118e7f37553bc7","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":50.588,"warning":null},{"id":"panel-4f0671e99c8eb258b957ac14","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":55.904,"warning":null},{"id":"panel-a08e802836cc62463a64dce4","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-tablejoin","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":47.596,"warning":null},{"id":"panel-b68a09f2b5c46d2ae1d93b4d","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-tablejoin","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":49.308,"warning":null},{"id":"panel-15c08139fc4d22bca2d29df2","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-tablejoin","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":50.25,"warning":null},{"id":"panel-f50eede8d326b80321f28443","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-tablejoin","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; gpt-6-astra-max; checkpoint=gpt-6-astra","score":58.365,"warning":null},{"id":"panel-378ce00ff970314e97d7c872","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":46.558,"warning":null},{"id":"panel-a4fc6c6ff3adc5d9f63e5f13","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":46.827,"warning":null},{"id":"panel-a024960d51ddeaa1a98abbb1","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-tablejoin","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablejoin; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":48.192,"warning":null},{"id":"panel-1b4c3991513f3ba7d226a43b","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-tablereformat","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":94.118,"warning":null},{"id":"panel-c99273c2737ca494de2a88bb","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-tablereformat","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":94.118,"warning":null},{"id":"panel-4e535ae7a8b06ef2cbfa9172","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":98.039,"warning":null},{"id":"panel-4d1ffd4d663cda024c844433","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":98.039,"warning":null},{"id":"panel-656470dfae4f4b91de1cf550","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":98.039,"warning":null},{"id":"panel-502f63677ac7031d9e46c35a","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-tablereformat","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":94.118,"warning":null},{"id":"panel-af88304c0bd2108ce908a459","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-tablereformat","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":94.118,"warning":null},{"id":"panel-a6622acee6854a8492d2d048","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-tablereformat","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":96.078,"warning":null},{"id":"panel-357d096335d24889fd34958c","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":98.039,"warning":null},{"id":"panel-7d205d81c52a64897f3ddf2c","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":98.039,"warning":null},{"id":"panel-3e5264e1650bf46bf9444836","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":96.078,"warning":null},{"id":"panel-e77cd1796c179d78dc2ff4d7","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":98.039,"warning":null},{"id":"panel-e651b88f8758433c31ceeef5","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":98.039,"warning":null},{"id":"panel-61db091bb2c1f4799d64c0bc","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":98.039,"warning":null},{"id":"panel-968500870cb002c7a5b28066","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":96.078,"warning":null},{"id":"panel-31682b190232b4280ccd06b0","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-tablereformat","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":100,"warning":null},{"id":"panel-dd7582c72728fb5b3755e281","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":100,"warning":null},{"id":"panel-068a45e1f7235cccd90ff94f","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":100,"warning":null},{"id":"panel-6db09ec2337dab314cc9e815","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":98.039,"warning":null},{"id":"panel-61761890b0724129ed2367e2","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":100,"warning":null},{"id":"panel-372faf44f31cc0197fc03175","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-tablereformat","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":100,"warning":null},{"id":"panel-3b4dca0a810d317164c9b966","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-tablereformat","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":100,"warning":null},{"id":"panel-eb688c9af7ea6d23fe75bb6f","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-tablereformat","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":100,"warning":null},{"id":"panel-1fc821825e1232dce70ea7f7","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-tablereformat","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; gpt-6-astra-max; checkpoint=gpt-6-astra","score":100,"warning":null},{"id":"panel-5f71b89ede220ebd20a0c531","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":100,"warning":null},{"id":"panel-860ece53551bde0e2391fb57","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":100,"warning":null},{"id":"panel-4e85d1ceaaff86a48099f140","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-tablereformat","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-tablereformat; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":100,"warning":null},{"id":"panel-3677adeb13582e5bebeb40d9","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":84.615,"warning":null},{"id":"panel-16ade649934f26164cea7aa7","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":80.769,"warning":null},{"id":"panel-9eb761881c53f420662c77f0","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":78.846,"warning":null},{"id":"panel-ef6437efce9a4ee894b838eb","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":82.692,"warning":null},{"id":"panel-7e46697958c6097bfdd5bb2c","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":80.769,"warning":null},{"id":"panel-f91ef1733b24ae4b57da78dc","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":80.769,"warning":null},{"id":"panel-3884a3a33eb9bae7cf35d1c8","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":78.846,"warning":null},{"id":"panel-e5f6c6af7b7b6563cbd85d04","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":73.077,"warning":null},{"id":"panel-ddb61e1c223050b01fe6a24d","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":80.769,"warning":null},{"id":"panel-6f887f9f34bf0ced09693be5","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":80.769,"warning":null},{"id":"panel-3130442bd69925da7c05ade7","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":80.769,"warning":null},{"id":"panel-0ee4308b1b8e689522786fba","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":50,"warning":null},{"id":"panel-6ca64d4b4bf1eb5d2a9614db","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":78.846,"warning":null},{"id":"panel-e9a18d4e2485815fbe9dcb90","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":82.692,"warning":null},{"id":"panel-7c589b3ec3b0735db386fb6c","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":76.923,"warning":null},{"id":"panel-46ee16e43dfcef55b9cdcc31","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":78.846,"warning":null},{"id":"panel-dd23f7bf3419e3011e2563f8","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":88.462,"warning":null},{"id":"panel-1be1c1a4d35577ac29967650","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":76.923,"warning":null},{"id":"panel-6dccf16089bfddf8511bc98e","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":80.769,"warning":null},{"id":"panel-c5a26905a6b81729ce07eee7","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":84.615,"warning":null},{"id":"panel-9f16b2319931415947e23f48","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":73.077,"warning":null},{"id":"panel-1b3605fdbbfa24a01c0f8ed7","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":84.615,"warning":null},{"id":"panel-0b801630aaf53bc41f3182dd","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":86.538,"warning":null},{"id":"panel-8fabb53ed27c9588a99748d3","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; gpt-6-astra-max; checkpoint=gpt-6-astra","score":84.615,"warning":null},{"id":"panel-a3b33640a7470089412d387c","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":76.923,"warning":null},{"id":"panel-2e9188c4762961d8b305cb9d","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":80.769,"warning":null},{"id":"panel-edd291968902d4d1849cd16d","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-theory_of_mind","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":84.615,"warning":null},{"id":"panel-802d1135b4384df772d4deb2","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-typescript","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":53.333,"warning":null},{"id":"panel-6edd971d60d57fb9f81575e2","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-typescript","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":60,"warning":null},{"id":"panel-4556b91816ae6e8c2fc6246c","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":20,"warning":null},{"id":"panel-0a0b1cc3b474cddeab9176c2","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":33.333,"warning":null},{"id":"panel-a9f78e146b99566e8c8961cb","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":43.333,"warning":null},{"id":"panel-56a4d57c73bfc7aaac0a1a33","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-typescript","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":33.333,"warning":null},{"id":"panel-ece90ea288dc3cb037efb07e","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-typescript","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":43.333,"warning":null},{"id":"panel-f97c66befa16467a34a3d8f2","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-typescript","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":23.333,"warning":null},{"id":"panel-85beb6c46f4ef1f3cb15eca8","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":50,"warning":null},{"id":"panel-da04aa901faef5abb22913ce","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":23.333,"warning":null},{"id":"panel-66a7edad755fbb5ac65ce9ed","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":33.333,"warning":null},{"id":"panel-430f81ce32b4f74a36ac8608","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":26.667,"warning":null},{"id":"panel-89ba0bd0c133f90bcefa0bbf","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":26.667,"warning":null},{"id":"panel-7e1e202586c5c977d8ba4553","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":46.667,"warning":null},{"id":"panel-72a945c6670ce4413e2c9775","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":40,"warning":null},{"id":"panel-53a731259937b873fe9b238a","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-typescript","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":36.667,"warning":null},{"id":"panel-1a73cedae57299fa448f67d8","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":43.333,"warning":null},{"id":"panel-228b8932fc82372013ddad69","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":20,"warning":null},{"id":"panel-7b17f5d1ffbaaf27acddab5b","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":26.667,"warning":null},{"id":"panel-d531c1e72e94cbf4adfbe973","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":43.333,"warning":null},{"id":"panel-d75beeb6ecb2a4aae441bdd4","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-typescript","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":36.667,"warning":null},{"id":"panel-c9c58ab541711b7aacf86522","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-typescript","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":50,"warning":null},{"id":"panel-5997db067bc91ad16df75ea2","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-typescript","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":46.667,"warning":null},{"id":"panel-c494b83960b7daa2e65bbace","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-typescript","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; gpt-6-astra-max; checkpoint=gpt-6-astra","score":43.333,"warning":null},{"id":"panel-ed41d716690c2b0b08f4b261","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":43.333,"warning":null},{"id":"panel-7c980646387d7ffe0fbb8f07","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":50,"warning":null},{"id":"panel-026b7d686de16b86eee55e61","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-typescript","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":60,"warning":null},{"id":"panel-1d9c88711562ca4bc4793bf0","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-typos","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":94,"warning":null},{"id":"panel-77e6cef54a0db4bdbe46d00b","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-typos","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":94,"warning":null},{"id":"panel-49a1a9a410cf8daaf0cf8f4e","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":78,"warning":null},{"id":"panel-025bcfd2e9a4b3b37fa9de55","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":84,"warning":null},{"id":"panel-4a63a7797adf849e01ab6269","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":80,"warning":null},{"id":"panel-5317018cf4f7cd8ae532c388","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-typos","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":78,"warning":null},{"id":"panel-2e71239f081d90f01235b7b9","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-typos","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":92,"warning":null},{"id":"panel-21d30b7156f9abf0cc4dad65","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-typos","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":72,"warning":null},{"id":"panel-d7fb1cbe942c47c63bd72721","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":76,"warning":null},{"id":"panel-ecfd0cf5293ccba5bfd04b78","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":82,"warning":null},{"id":"panel-b0514842d51bae1d0371113f","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":86,"warning":null},{"id":"panel-aa1c9bf038808a60c6fff323","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":74,"warning":null},{"id":"panel-5e5c864b2d0837ecf9a3a2cc","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":88,"warning":null},{"id":"panel-7d73d21d7873e5d779a4c384","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":90,"warning":null},{"id":"panel-38523bc85154f445a6cde6ac","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":90,"warning":null},{"id":"panel-cf1e57406dae14dbc01470ea","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-typos","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":82,"warning":null},{"id":"panel-699ecb5439422ac056781a58","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":82,"warning":null},{"id":"panel-6be68058cd3af8da1eca505d","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":70,"warning":null},{"id":"panel-8a84c38764db6738f2389ed4","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":54,"warning":null},{"id":"panel-9aa01fc84eae16b96abca291","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":88,"warning":null},{"id":"panel-d01a35ef69f7df80895aaa00","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-typos","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":70,"warning":null},{"id":"panel-ce3efb571062193428082f97","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-typos","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":84,"warning":null},{"id":"panel-5cc0741a795c50acdfcdf9c2","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-typos","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":86,"warning":null},{"id":"panel-0fef39ca040d37164c362ec0","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-typos","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; gpt-6-astra-max; checkpoint=gpt-6-astra","score":82,"warning":null},{"id":"panel-607ac2b71c6861f6dfcf5271","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":62,"warning":null},{"id":"panel-ca5efb697bbdbfd817a0dc54","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":74,"warning":null},{"id":"panel-9a0cadd9cf939c95da4dccd3","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-typos","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-typos; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":86,"warning":null},{"id":"panel-8da717a8690707003f08a090","modelId":"claude-fable-5","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"max","sourceLabel":"claude-fable-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-fable-5-max-effort; checkpoint=claude-fable-5","score":100,"warning":null},{"id":"panel-a7ae39b18ff37882f52d61dd","modelId":"claude-fable-5-1","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"max","sourceLabel":"claude-fable-5-1-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1","score":100,"warning":null},{"id":"panel-e723dff4aa878aa3b1f555c0","modelId":"claude-opus-4-5-20251101","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"claude-opus-4-5-20251101-thinking-64k-high-effort (thinking 64k; high effort)","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-opus-4-5-20251101-thinking-64k-high-effort; checkpoint=claude-opus-4-5-20251101","score":77.5,"warning":null},{"id":"panel-f1903bf3ae7784fac180c5c6","modelId":"claude-opus-4-6","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"claude-opus-4-6-thinking-auto-high-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-opus-4-6-thinking-auto-high-effort; checkpoint=claude-opus-4-6","score":94,"warning":null},{"id":"panel-a325f695a71ef6705d5a5597","modelId":"claude-opus-4-7","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"claude-opus-4-7-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7","score":98,"warning":null},{"id":"panel-7aab7aefea402a837eb331c7","modelId":"claude-opus-4-8","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"max","sourceLabel":"claude-opus-4-8-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-opus-4-8-max-effort; checkpoint=claude-opus-4-8","score":100,"warning":null},{"id":"panel-b76aa763373c89156231a6da","modelId":"claude-opus-5","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"max","sourceLabel":"claude-opus-5-max-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-opus-5-max-effort; checkpoint=claude-opus-5","score":100,"warning":null},{"id":"panel-9d65818b1f976a7825472a2f","modelId":"claude-sonnet-4-6","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"medium","sourceLabel":"claude-sonnet-4-6-thinking-auto-medium-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-sonnet-4-6-thinking-auto-medium-effort; checkpoint=claude-sonnet-4-6","score":96,"warning":null},{"id":"panel-fc47f8546d6a90f124e667fd","modelId":"claude-sonnet-5","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"claude-sonnet-5-xhigh-effort","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5","score":88,"warning":null},{"id":"panel-67097dc7f9543964f1eb66f1","modelId":"gemini-3.1-pro","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"gemini-3.1-pro-preview-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gemini-3.1-pro-preview-high; checkpoint=gemini-3.1-pro","score":85.25,"warning":null},{"id":"panel-99a523bc66fc8f9af24e40c7","modelId":"gemini-3.5-flash","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"gemini-3.5-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gemini-3.5-flash-high; checkpoint=gemini-3.5-flash","score":77.25,"warning":null},{"id":"panel-bf109486b4ee154dd5bf538c","modelId":"gemini-3.5-flash-lite","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"gemini-3.5-flash-lite-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gemini-3.5-flash-lite-high; checkpoint=gemini-3.5-flash-lite","score":32.75,"warning":null},{"id":"panel-2fadbe78a18174dfa36798ad","modelId":"gemini-3.6-flash","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"gemini-3.6-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gemini-3.6-flash-high; checkpoint=gemini-3.6-flash","score":85.75,"warning":null},{"id":"panel-d40d3cee5878b364f2758bf1","modelId":"gemini-3.7-flash","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"gemini-3.7-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash","score":94.5,"warning":null},{"id":"panel-1705e80b84b9b5b17c4be595","modelId":"gemini-3.8-flash","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"gemini-3.8-flash-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gemini-3.8-flash-high; checkpoint=gemini-3.8-flash","score":98.25,"warning":null},{"id":"panel-cdd9ee7d07449e206cc9e3dc","modelId":"gpt-5.2","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"high","sourceLabel":"gpt-5.2-2025-12-11-high","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-5.2-2025-12-11-high; checkpoint=gpt-5.2","score":84,"warning":null},{"id":"panel-52b264b698e93d9c6004f43d","modelId":"gpt-5.4","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"gpt-5.4-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-5.4-xhigh; checkpoint=gpt-5.4","score":98,"warning":null},{"id":"panel-cf093414bb1c79faa8013d1c","modelId":"gpt-5.4-mini","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"gpt-5.4-mini-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-5.4-mini-xhigh; checkpoint=gpt-5.4-mini","score":60.372,"warning":null},{"id":"panel-31bd5c440bbe0254845c74b9","modelId":"gpt-5.4-nano","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"gpt-5.4-nano-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-5.4-nano-xhigh; checkpoint=gpt-5.4-nano","score":97.619,"warning":null},{"id":"panel-b6b4a2a1c5b5a3d4aa7ecec7","modelId":"gpt-5.5","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"gpt-5.5-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-5.5-xhigh; checkpoint=gpt-5.5","score":100,"warning":null},{"id":"panel-41dd83b36bf6c44b1f57ac1d","modelId":"gpt-5.6-luna","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"max","sourceLabel":"gpt-5.6-luna-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-5.6-luna-max; checkpoint=gpt-5.6-luna","score":93.5,"warning":null},{"id":"panel-2f9395d08746fc6829802981","modelId":"gpt-5.6-sol","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"max","sourceLabel":"gpt-5.6-sol-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-5.6-sol-max; checkpoint=gpt-5.6-sol","score":100,"warning":null},{"id":"panel-c3767e7e55780617f0ade91d","modelId":"gpt-5.6-terra","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"max","sourceLabel":"gpt-5.6-terra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-5.6-terra-max; checkpoint=gpt-5.6-terra","score":100,"warning":null},{"id":"panel-1ffa9572fdf497d938c73d9d","modelId":"gpt-6-astra","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"max","sourceLabel":"gpt-6-astra-max","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; gpt-6-astra-max; checkpoint=gpt-6-astra","score":100,"warning":null},{"id":"panel-3ca3b50afff257eb11c4cb04","modelId":"muse-spark-1.1","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"muse-spark-1.1-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1","score":96,"warning":null},{"id":"panel-5924987a533b33a47f789e7e","modelId":"muse-spark-1.2","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"muse-spark-1.2-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; muse-spark-1.2-xhigh; checkpoint=muse-spark-1.2","score":95.25,"warning":null},{"id":"panel-1a10629747e118f97cfc0f67","modelId":"muse-spark-1.3","benchmarkId":"livebench-2026-06-25-zebra_puzzle","level":"xhigh","sourceLabel":"muse-spark-1.3-xhigh","configuration":"LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; muse-spark-1.3-xhigh; checkpoint=muse-spark-1.3","score":98,"warning":null},{"id":"panel-eeaabbca375641a41f9d6033","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-08-tools","level":"high","sourceLabel":"gpt-5-2025-08-07-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-08-tools; gpt-5-2025-08-07-high; checkpoint=gpt-5","score":46.53846153846154,"warning":null},{"id":"panel-df1f433349e12b715f87b8ca","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-08-tools","level":"medium","sourceLabel":"gpt-5-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-08-tools; gpt-5-2025-08-07-medium; checkpoint=gpt-5","score":45.38461538461539,"warning":null},{"id":"panel-7aa0c89e21a5b4ba53c846fe","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-08-tools","level":"minimal","sourceLabel":"gpt-5-2025-08-07-minimal","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-08-tools; gpt-5-2025-08-07-minimal; checkpoint=gpt-5","score":33.46153846153846,"warning":null},{"id":"panel-8f5f1ae06f1007eabaadad12","modelId":"gpt-5-mini","benchmarkId":"swe-rebench-2025-08-tools","level":"medium","sourceLabel":"gpt-5-mini-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-08-tools; gpt-5-mini-2025-08-07-medium; checkpoint=gpt-5-mini","score":43.07692307692307,"warning":null},{"id":"panel-462303d94f9258ff82feec79","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-09-tools","level":"high","sourceLabel":"gpt-5-2025-08-07-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-09-tools; gpt-5-2025-08-07-high; checkpoint=gpt-5","score":36.3265306122449,"warning":null},{"id":"panel-6a5dad63f041041541673c1a","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-09-tools","level":"medium","sourceLabel":"gpt-5-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-09-tools; gpt-5-2025-08-07-medium; checkpoint=gpt-5","score":38.775510204081634,"warning":null},{"id":"panel-8613396169af318add6485b7","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-09-tools","level":"minimal","sourceLabel":"gpt-5-2025-08-07-minimal","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-09-tools; gpt-5-2025-08-07-minimal; checkpoint=gpt-5","score":30.612244897959183,"warning":null},{"id":"panel-4b776aced4fe63c3161c7bb8","modelId":"gpt-5-mini","benchmarkId":"swe-rebench-2025-09-tools","level":"medium","sourceLabel":"gpt-5-mini-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-09-tools; gpt-5-mini-2025-08-07-medium; checkpoint=gpt-5-mini","score":37.14285714285714,"warning":null},{"id":"panel-eeadcd73222785f2a270b0be","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-10-tools","level":"high","sourceLabel":"gpt-5-2025-08-07-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-10-tools; gpt-5-2025-08-07-high; checkpoint=gpt-5","score":38.82352941176471,"warning":null},{"id":"panel-128f7a0af9b7fa3967594c52","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-10-tools","level":"medium","sourceLabel":"gpt-5-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-10-tools; gpt-5-2025-08-07-medium; checkpoint=gpt-5","score":42.35294117647059,"warning":null},{"id":"panel-3e55e76525c8e98cf682c126","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-10-tools","level":"minimal","sourceLabel":"gpt-5-2025-08-07-minimal","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-10-tools; gpt-5-2025-08-07-minimal; checkpoint=gpt-5","score":25.968627450980396,"warning":null},{"id":"panel-7d9e8814bc198c5ebfeecf3a","modelId":"gpt-5-mini","benchmarkId":"swe-rebench-2025-10-tools","level":"medium","sourceLabel":"gpt-5-mini-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-10-tools; gpt-5-mini-2025-08-07-medium; checkpoint=gpt-5-mini","score":32.549019607843135,"warning":null},{"id":"panel-105cf9d397ba788c03ce8531","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-11-tools","level":"high","sourceLabel":"gpt-5-2025-08-07-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-11-tools; gpt-5-2025-08-07-high; checkpoint=gpt-5","score":55.74468085106383,"warning":null},{"id":"panel-5b22352026768409d27902f3","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-11-tools","level":"medium","sourceLabel":"gpt-5-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-11-tools; gpt-5-2025-08-07-medium; checkpoint=gpt-5","score":58.723404255319146,"warning":null},{"id":"panel-12e0ccd4a964c83e4b36650b","modelId":"gpt-5","benchmarkId":"swe-rebench-2025-11-tools","level":"minimal","sourceLabel":"gpt-5-2025-08-07-minimal","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-11-tools; gpt-5-2025-08-07-minimal; checkpoint=gpt-5","score":34.8936170212766,"warning":null},{"id":"panel-c89e195031cf4c7684a9a9b0","modelId":"gpt-5-mini","benchmarkId":"swe-rebench-2025-11-tools","level":"medium","sourceLabel":"gpt-5-mini-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-11-tools; gpt-5-mini-2025-08-07-medium; checkpoint=gpt-5-mini","score":44.255319148936174,"warning":null},{"id":"panel-b21a69a8ceeb7196e4fbdfc9","modelId":"gpt-5.2","benchmarkId":"swe-rebench-2025-11-tools","level":"medium","sourceLabel":"gpt-5.2-2025-12-11-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-11-tools; gpt-5.2-2025-12-11-medium; checkpoint=gpt-5.2","score":61.27659574468085,"warning":null},{"id":"panel-9d3595bc411ad8842b5f1eef","modelId":"gpt-5-mini","benchmarkId":"swe-rebench-2025-12-tools","level":"high","sourceLabel":"gpt-5-mini-2025-08-07-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-12-tools; gpt-5-mini-2025-08-07-high; checkpoint=gpt-5-mini","score":44.30851063829787,"warning":null},{"id":"panel-9f5fbd93e0f5873f7f2e34ad","modelId":"gpt-5-mini","benchmarkId":"swe-rebench-2025-12-tools","level":"medium","sourceLabel":"gpt-5-mini-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-12-tools; gpt-5-mini-2025-08-07-medium; checkpoint=gpt-5-mini","score":40.66489361702128,"warning":null},{"id":"panel-3158ebf36b887b27663bbccd","modelId":"gpt-5.2","benchmarkId":"swe-rebench-2025-12-tools","level":"medium","sourceLabel":"gpt-5.2-2025-12-11-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-12-tools; gpt-5.2-2025-12-11-medium; checkpoint=gpt-5.2","score":59.41489361702128,"warning":null},{"id":"panel-709e5e2b9100c29ff4ccf9e6","modelId":"gpt-5.2","benchmarkId":"swe-rebench-2025-12-tools","level":"xhigh","sourceLabel":"gpt-5.2-2025-12-11-xhigh","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-12-tools; gpt-5.2-2025-12-11-xhigh; checkpoint=gpt-5.2","score":61.48936170212765,"warning":null},{"id":"panel-46441b51f4e16452b66da4d8","modelId":"gpt-oss-120b","benchmarkId":"swe-rebench-2025-12-tools","level":"high","sourceLabel":"gpt-oss-120b-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2025-12-tools; gpt-oss-120b-high; checkpoint=gpt-oss-120b","score":36.959219858156025,"warning":null},{"id":"panel-439f39520f3958e5a7901ccc","modelId":"claude-opus-4-6","benchmarkId":"swe-rebench-2026-01-tools","level":"high","sourceLabel":"Claude Opus 4.6-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-01-tools; Claude Opus 4.6-high; checkpoint=claude-opus-4-6","score":51.666666666666686,"warning":null},{"id":"panel-882148776d6b6bf196c8e72f","modelId":"gpt-5-mini","benchmarkId":"swe-rebench-2026-01-tools","level":"high","sourceLabel":"gpt-5-mini-2025-08-07-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-01-tools; gpt-5-mini-2025-08-07-high; checkpoint=gpt-5-mini","score":35,"warning":null},{"id":"panel-c8b39cb9c7921b483f979a9c","modelId":"gpt-5-mini","benchmarkId":"swe-rebench-2026-01-tools","level":"medium","sourceLabel":"gpt-5-mini-2025-08-07-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-01-tools; gpt-5-mini-2025-08-07-medium; checkpoint=gpt-5-mini","score":30.83333333333333,"warning":null},{"id":"panel-8380ef3f8a50b6f89b396276","modelId":"gpt-5.2","benchmarkId":"swe-rebench-2026-01-tools","level":"medium","sourceLabel":"gpt-5.2-2025-12-11-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-01-tools; gpt-5.2-2025-12-11-medium; checkpoint=gpt-5.2","score":51.046099290780134,"warning":null},{"id":"panel-2a5f25442a3b5295bfa02259","modelId":"gpt-5.2","benchmarkId":"swe-rebench-2026-01-tools","level":"xhigh","sourceLabel":"gpt-5.2-2025-12-11-xhigh","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-01-tools; gpt-5.2-2025-12-11-xhigh; checkpoint=gpt-5.2","score":51.66666666666666,"warning":null},{"id":"panel-9cfedefbaaad4dfb46e7ab3e","modelId":"claude-opus-4-6","benchmarkId":"swe-rebench-2026-02-tools","level":"high","sourceLabel":"Claude Opus 4.6-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-02-tools; Claude Opus 4.6-high; checkpoint=claude-opus-4-6","score":65.26315789473685,"warning":null},{"id":"panel-31ec105465e7a26d35da4265","modelId":"gpt-5.2","benchmarkId":"swe-rebench-2026-02-tools","level":"medium","sourceLabel":"gpt-5.2-2025-12-11-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-02-tools; gpt-5.2-2025-12-11-medium; checkpoint=gpt-5.2","score":64.4172932330827,"warning":null},{"id":"panel-ca4f23c7585afe314456c6ee","modelId":"gpt-5.3-codex","benchmarkId":"swe-rebench-2026-02-tools","level":"xhigh","sourceLabel":"gpt-5.3-codex-xhigh","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-02-tools; gpt-5.3-codex-xhigh; checkpoint=gpt-5.3-codex","score":58.59649122807018,"warning":null},{"id":"panel-ef0926b5f5d004f8a5348da5","modelId":"gpt-5.4","benchmarkId":"swe-rebench-2026-02-tools","level":"medium","sourceLabel":"gpt-5.4-2026-03-05-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-02-tools; gpt-5.4-2026-03-05-medium; checkpoint=gpt-5.4","score":62.807017543859644,"warning":null},{"id":"panel-af6affc17d37d1ebceed5651","modelId":"claude-opus-4-6","benchmarkId":"swe-rebench-2026-03-tools","level":"high","sourceLabel":"Claude Opus 4.6-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; Claude Opus 4.6-high; checkpoint=claude-opus-4-6","score":51.304347826086946,"warning":null},{"id":"panel-582529e031a763a72cb0c962","modelId":"claude-opus-4-7","benchmarkId":"swe-rebench-2026-03-tools","level":"high","sourceLabel":"Claude Opus 4.7-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; Claude Opus 4.7-high; checkpoint=claude-opus-4-7","score":53.47826086956522,"warning":null},{"id":"panel-aa3ee5d91a696499570b9479","modelId":"claude-opus-4-8","benchmarkId":"swe-rebench-2026-03-tools","level":"xhigh","sourceLabel":"Claude Opus 4.8-xhigh","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; Claude Opus 4.8-xhigh; checkpoint=claude-opus-4-8","score":56.52173913043479,"warning":null},{"id":"panel-84d19d866a5f84d2e5157771","modelId":"deepseek-v4-pro-0424","benchmarkId":"swe-rebench-2026-03-tools","level":"high","sourceLabel":"DeepSeek-V4 Pro [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; DeepSeek-V4 Pro [high]; checkpoint=deepseek-v4-pro-0424","score":46.72463768115942,"warning":null},{"id":"panel-4e74e790b8c2ab2987cd3979","modelId":"glm-5.2","benchmarkId":"swe-rebench-2026-03-tools","level":"high","sourceLabel":"GLM-5.2 [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; GLM-5.2 [high]; checkpoint=glm-5.2","score":53.47826086956522,"warning":null},{"id":"panel-91308a65440d721514f94949","modelId":"gpt-5.4","benchmarkId":"swe-rebench-2026-03-tools","level":"medium","sourceLabel":"gpt-5.4-2026-03-05-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; gpt-5.4-2026-03-05-medium; checkpoint=gpt-5.4","score":57.826086956521735,"warning":null},{"id":"panel-082ec7a4e998253830c59d5e","modelId":"gpt-5.5","benchmarkId":"swe-rebench-2026-03-tools","level":"medium","sourceLabel":"gpt-5.5-2026-04-23-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; gpt-5.5-2026-04-23-medium; checkpoint=gpt-5.5","score":60.434782608695656,"warning":null},{"id":"panel-03a4267243f5da43f4f0f916","modelId":"gpt-5.5","benchmarkId":"swe-rebench-2026-03-tools","level":"xhigh","sourceLabel":"gpt-5.5-2026-04-23-xhigh","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-03-tools; gpt-5.5-2026-04-23-xhigh; checkpoint=gpt-5.5","score":63.04347826086957,"warning":null},{"id":"panel-c4a47cfea3565c4484c1c8b8","modelId":"claude-opus-4-6","benchmarkId":"swe-rebench-2026-04-tools","level":"high","sourceLabel":"Claude Opus 4.6-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; Claude Opus 4.6-high; checkpoint=claude-opus-4-6","score":43.72093023255814,"warning":null},{"id":"panel-d4309f168dc4babc6bc9d587","modelId":"claude-opus-4-7","benchmarkId":"swe-rebench-2026-04-tools","level":"high","sourceLabel":"Claude Opus 4.7-high","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; Claude Opus 4.7-high; checkpoint=claude-opus-4-7","score":57.67441860465116,"warning":null},{"id":"panel-59f0399257b1743a621e4448","modelId":"claude-opus-4-8","benchmarkId":"swe-rebench-2026-04-tools","level":"xhigh","sourceLabel":"Claude Opus 4.8-xhigh","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; Claude Opus 4.8-xhigh; checkpoint=claude-opus-4-8","score":57.674418604651166,"warning":null},{"id":"panel-2e61455480fb766893d98afe","modelId":"deepseek-v4-pro-0424","benchmarkId":"swe-rebench-2026-04-tools","level":"high","sourceLabel":"DeepSeek-V4 Pro [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; DeepSeek-V4 Pro [high]; checkpoint=deepseek-v4-pro-0424","score":41.58361018826135,"warning":null},{"id":"panel-7073ced98bba7f5b5d8c68cd","modelId":"glm-5.2","benchmarkId":"swe-rebench-2026-04-tools","level":"high","sourceLabel":"GLM-5.2 [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; GLM-5.2 [high]; checkpoint=glm-5.2","score":51.162790697674424,"warning":null},{"id":"panel-f0febcfcf5b14d5f6f8f1b5e","modelId":"gpt-5.4","benchmarkId":"swe-rebench-2026-04-tools","level":"medium","sourceLabel":"gpt-5.4-2026-03-05-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; gpt-5.4-2026-03-05-medium; checkpoint=gpt-5.4","score":49.76744186046512,"warning":null},{"id":"panel-1e3fa2d67e3e69ad184eb7a4","modelId":"gpt-5.5","benchmarkId":"swe-rebench-2026-04-tools","level":"medium","sourceLabel":"gpt-5.5-2026-04-23-medium","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; gpt-5.5-2026-04-23-medium; checkpoint=gpt-5.5","score":57.20930232558139,"warning":null},{"id":"panel-3f17e0eb43dae6ec089f2c0b","modelId":"gpt-5.5","benchmarkId":"swe-rebench-2026-04-tools","level":"xhigh","sourceLabel":"gpt-5.5-2026-04-23-xhigh","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-04-tools; gpt-5.5-2026-04-23-xhigh; checkpoint=gpt-5.5","score":60.46511627906976,"warning":null},{"id":"panel-5d62ab6fe9c2e7d1f8fda50c","modelId":"deepseek-v4-pro-0424","benchmarkId":"swe-rebench-2026-05-tools","level":"high","sourceLabel":"DeepSeek-V4 Pro [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-05-tools; DeepSeek-V4 Pro [high]; checkpoint=deepseek-v4-pro-0424","score":41.55555555555556,"warning":null},{"id":"panel-9b20aa7050ddddd133712208","modelId":"glm-5.2","benchmarkId":"swe-rebench-2026-05-tools","level":"high","sourceLabel":"GLM-5.2 [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-05-tools; GLM-5.2 [high]; checkpoint=glm-5.2","score":61.111111111111114,"warning":null},{"id":"panel-7227c50a2326d0f76441e35b","modelId":"claude-fable-5","benchmarkId":"swe-rebench-2026-06-tools","level":"high","sourceLabel":"Fable 5 [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; Fable 5 [high]; checkpoint=claude-fable-5","score":57.61904761904761,"warning":null},{"id":"panel-79497e6cca80d008679179a1","modelId":"claude-opus-5","benchmarkId":"swe-rebench-2026-06-tools","level":"high","sourceLabel":"Opus 5 [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; Opus 5 [high]; checkpoint=claude-opus-5","score":60,"warning":null},{"id":"panel-8ea63df7cd359367585d2968","modelId":"claude-sonnet-5","benchmarkId":"swe-rebench-2026-06-tools","level":"high","sourceLabel":"Sonnet 5 [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; Sonnet 5 [high]; checkpoint=claude-sonnet-5","score":52.85714285714285,"warning":null},{"id":"panel-17c093bae14aabe9e7a0ba93","modelId":"deepseek-v4-pro-0424","benchmarkId":"swe-rebench-2026-06-tools","level":"high","sourceLabel":"DeepSeek-V4 Pro [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; DeepSeek-V4 Pro [high]; checkpoint=deepseek-v4-pro-0424","score":35.238095238095234,"warning":null},{"id":"panel-9633b6cae80f96f07bdab378","modelId":"glm-5.2","benchmarkId":"swe-rebench-2026-06-tools","level":"high","sourceLabel":"GLM-5.2 [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; GLM-5.2 [high]; checkpoint=glm-5.2","score":58.0952380952381,"warning":null},{"id":"panel-af745c954411352e8ff6dfe1","modelId":"gpt-5.6-luna","benchmarkId":"swe-rebench-2026-06-tools","level":"medium","sourceLabel":"GPT-5.6 Luna [medium]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; GPT-5.6 Luna [medium]; checkpoint=gpt-5.6-luna","score":30.95238095238095,"warning":null},{"id":"panel-ed7429eba1da33d52494d3cd","modelId":"gpt-5.6-sol","benchmarkId":"swe-rebench-2026-06-tools","level":"medium","sourceLabel":"GPT-5.6 Sol [medium]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; GPT-5.6 Sol [medium]; checkpoint=gpt-5.6-sol","score":55.23809523809524,"warning":null},{"id":"panel-c9c71176cdf68d6328da3f8c","modelId":"grok-4.5","benchmarkId":"swe-rebench-2026-06-tools","level":"high","sourceLabel":"Grok 4.5 [high]","configuration":"SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; Grok 4.5 [high]; checkpoint=grok-4.5","score":55.714285714285715,"warning":null},{"id":"epoch-run-26q7yB8XHAcmxWgEMFPMHP","modelId":"nemotron-3-ultra","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"nemotron-3-ultra","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=nemotron-3-ultra; run=26q7yB8XHAcmxWgEMFPMHP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-272CatAfNpHUw44w7oJ2MM","modelId":"gemma-4-26b-a4b-it","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemma-4-26b-a4b-it_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-4-26b-a4b-it_minimal; run=272CatAfNpHUw44w7oJ2MM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":6,"warning":null},{"id":"epoch-run-2AxSH8gojpyyzADeWfuSqu","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-14B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=DeepSeek-R1-Distill-Qwen-14B; run=2AxSH8gojpyyzADeWfuSqu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1,"warning":null},{"id":"epoch-run-2c4rvmf5N7QXTugrFLMZ83","modelId":"claude-opus-4-7","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"xhigh","sourceLabel":"claude-opus-4-7_xhigh","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-opus-4-7_xhigh; run=2c4rvmf5N7QXTugrFLMZ83; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":51.7,"warning":null},{"id":"epoch-run-2CdomqtBVz2it7a2Zx2G2t","modelId":"gpt-5.5","benchmarkId":"epoch-gpqa-diamond-1-0-8-choice","level":"low","sourceLabel":"gpt-5.5_low","configuration":"Epoch AI Inspect; task 1.0.8; scorer choice; model=gpt-5.5_low; run=2CdomqtBVz2it7a2Zx2G2t; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.65656565656566,"warning":null},{"id":"epoch-run-2fQJP3brRApfBdQq7Zy3bm","modelId":"llama-3.1-405b-instruct","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"Llama-3.1-405B-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=Llama-3.1-405B-Instruct; run=2fQJP3brRApfBdQq7Zy3bm; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":9.722222222222223,"warning":null},{"id":"epoch-run-2gzNF2d53h2oCKDnojLtSP","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3-30b-a3b-thinking-2507","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-30b-a3b-thinking-2507; run=2gzNF2d53h2oCKDnojLtSP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":70.07575757575758,"warning":null},{"id":"epoch-run-2hbbp8z6PhB7c2T33os9q5","modelId":"claude-opus-4-6","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-opus-4-6_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-4-6_max; run=2hbbp8z6PhB7c2T33os9q5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26.82926829268293,"warning":null},{"id":"epoch-run-2jTRxz7rW3B66a8smtz7Ya","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"claude-opus-4-5-20251101","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-5-20251101; run=2jTRxz7rW3B66a8smtz7Ya; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4,"warning":null},{"id":"epoch-run-2xfFf6KZAp2gUWYhHGkFgs","modelId":"deepseek-v4-pro","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"deepseek-v4-pro-0813_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=deepseek-v4-pro-0813_max; run=2xfFf6KZAp2gUWYhHGkFgs; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":52.90581162324649,"warning":null},{"id":"epoch-run-2y5jXmHGjyEyZvGjNDtRZe","modelId":"qwen3.6-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"qwen3.6-flash","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.6-flash; run=2y5jXmHGjyEyZvGjNDtRZe; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-2z7kL9DpfvY44T9Wo99FYx","modelId":"gemini-2.5-pro","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"gemini-2.5-pro","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-2.5-pro; run=2z7kL9DpfvY44T9Wo99FYx; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-35hRAbkceJM3Dpb2pWXnx9","modelId":"kimi-k3","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"kimi-k3_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k3_max; run=35hRAbkceJM3Dpb2pWXnx9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":39,"warning":null},{"id":"epoch-run-37pJqPpXTE6ia9ikmmGPJ4","modelId":"claude-opus-4-8","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-5-model-extracted-exact-match","level":"max","sourceLabel":"claude-opus-4-8_max","configuration":"Epoch AI Inspect; task 1.1.5; scorer model_extracted_exact_match; model=claude-opus-4-8_max; run=37pJqPpXTE6ia9ikmmGPJ4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":98.33333333333333,"warning":null},{"id":"epoch-run-3asQZd87VuKoH95e4x5Yfg","modelId":"phi-3-mini-4k-instruct","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Phi-3-mini-4k-instruct","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Phi-3-mini-4k-instruct; run=3asQZd87VuKoH95e4x5Yfg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-3CGChL5vNDM6Df5C8Z8owN","modelId":"gemma-3-1b-it","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemma-3-1b-it","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-3-1b-it; run=3CGChL5vNDM6Df5C8Z8owN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1.1111111111111112,"warning":null},{"id":"epoch-run-3dXpsUjaVEbBN72dnw4Vzq","modelId":"claude-opus-5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"claude-opus-5_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-5_low; run=3dXpsUjaVEbBN72dnw4Vzq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-3h8STJpG2VzY9LiBUzwotv","modelId":"gpt-6-astra","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"gpt-6-astra_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-6-astra_max; run=3h8STJpG2VzY9LiBUzwotv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.77020202020202,"warning":null},{"id":"epoch-run-3iRQkf5v7Wu7YuZhxa76Gg","modelId":"grok-4.3","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"high","sourceLabel":"grok-4.3_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=grok-4.3_high; run=3iRQkf5v7Wu7YuZhxa76Gg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":14.634146341463413,"warning":null},{"id":"epoch-run-3L22tfAid5ZM42p92tqC73","modelId":"gemini-3.6-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"minimal","sourceLabel":"gemini-3.6-flash_minimal","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3.6-flash_minimal; run=3L22tfAid5ZM42p92tqC73; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25,"warning":null},{"id":"epoch-run-3mCgC7byPaZ3zzPM98bY5A","modelId":"qwen3-4b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3-4b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-4b_none; run=3mCgC7byPaZ3zzPM98bY5A; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1,"warning":null},{"id":"epoch-run-3n5KDcBaKqJh3WTg7qU2rs","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.6-35b-a3b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-35b-a3b; run=3n5KDcBaKqJh3WTg7qU2rs; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.66666666666667,"warning":null},{"id":"epoch-run-3QtkFWzSLzd4hgYGsNd5cL","modelId":"qwen3.6-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.6-flash_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.6-flash_none; run=3QtkFWzSLzd4hgYGsNd5cL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":18,"warning":null},{"id":"epoch-run-3UbYVQELDHAcQgu7sTTnRf","modelId":"magistral-small-2509","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"magistral-small-2509","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=magistral-small-2509; run=3UbYVQELDHAcQgu7sTTnRf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47.6010101010101,"warning":null},{"id":"epoch-run-3UzTUnn6wx79jU3XoP7VFA","modelId":"qwen3-1.7b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3-1.7b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-1.7b_none; run=3UzTUnn6wx79jU3XoP7VFA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-3y52KdaFo7gQZCccCQnNxp","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.6-35b-a3b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-35b-a3b; run=3y52KdaFo7gQZCccCQnNxp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26,"warning":null},{"id":"epoch-run-3ZnPtGRJkvqHk8wvWWRgCe","modelId":"claude-opus-4-8","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"xhigh","sourceLabel":"claude-opus-4-8_xhigh","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-opus-4-8_xhigh; run=3ZnPtGRJkvqHk8wvWWRgCe; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":31,"warning":null},{"id":"epoch-run-452pB5w5ea6uy92e2q2NMv","modelId":"qwen3.6-27b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.6-27b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-27b; run=452pB5w5ea6uy92e2q2NMv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.11111111111111,"warning":null},{"id":"epoch-run-4a3M8rRWUoPphCSr2dguXH","modelId":"gemini-3.1-pro","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"low","sourceLabel":"gemini-3.1-pro-preview_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3.1-pro-preview_low; run=4a3M8rRWUoPphCSr2dguXH; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.999999999999996,"warning":null},{"id":"epoch-run-4ACEC4x26HWRGiAepHGw43","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"Qwen3-235B-A22B-Thinking-2507","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=Qwen3-235B-A22B-Thinking-2507; run=4ACEC4x26HWRGiAepHGw43; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":40.44044044044044,"warning":null},{"id":"epoch-run-4bLcFNu5zF6YuZf3qVKoHE","modelId":"gpt-5.6-terra","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"gpt-5.6-terra_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-terra_max; run=4bLcFNu5zF6YuZf3qVKoHE; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.3080808080808,"warning":null},{"id":"epoch-run-4E5xGsuRMwMBhAfC4F2G4N","modelId":"kimi-k3","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"kimi-k3_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k3_high; run=4E5xGsuRMwMBhAfC4F2G4N; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.33333333333333,"warning":null},{"id":"epoch-run-4gZy2dAAT2EPZDGz5puD3H","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"minimal","sourceLabel":"gemini-3.1-flash-lite_minimal","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.1-flash-lite_minimal; run=4gZy2dAAT2EPZDGz5puD3H; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21.403508771929825,"warning":null},{"id":"epoch-run-4hmmfwG9tgZJvKhL78nKzL","modelId":"glm-5.1","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"glm-5.1_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.1_none; run=4hmmfwG9tgZJvKhL78nKzL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":24.912280701754387,"warning":null},{"id":"epoch-run-4HVvM9ZWKKPLQPcC8WYYMT","modelId":"deepseek-v4-pro","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"deepseek-v4-pro-0813_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=deepseek-v4-pro-0813_max; run=4HVvM9ZWKKPLQPcC8WYYMT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":98.61111111111111,"warning":null},{"id":"epoch-run-4LjmaK4MRrxuDXUiZsvA3o","modelId":"gemma-4-31b-it","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemma-4-31b-it_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-4-31b-it_minimal; run=4LjmaK4MRrxuDXUiZsvA3o; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":5,"warning":null},{"id":"epoch-run-4LWNorP8Fy8V8doxirNFcH","modelId":"qwen3.6-plus","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"qwen3.6-plus","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=qwen3.6-plus; run=4LWNorP8Fy8V8doxirNFcH; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":44.14414414414414,"warning":null},{"id":"epoch-run-4MWuvJB4YXGnGz27Y74cqW","modelId":"kimi-k2.6","benchmarkId":"epoch-chess-puzzles-1-1-4-model-extracted-exact-match","level":"unspecified","sourceLabel":"kimi-k2.6","configuration":"Epoch AI Inspect; task 1.1.4; scorer model_extracted_exact_match; model=kimi-k2.6; run=4MWuvJB4YXGnGz27Y74cqW; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26,"warning":null},{"id":"epoch-run-4mzBGLow3HkS8BmAYCzGTR","modelId":"gemini-3.1-pro","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.1-pro-preview_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.1-pro-preview_high; run=4mzBGLow3HkS8BmAYCzGTR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":49,"warning":null},{"id":"epoch-run-4oSbA2RKFsfuAfVayAMAww","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_48K (thinking 48k)","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-sonnet-4-5-20250929_48K; run=4oSbA2RKFsfuAfVayAMAww; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17,"warning":null},{"id":"epoch-run-4QfM9qyeWGqNc8YTcQNV76","modelId":"gemini-3.1-pro","benchmarkId":"epoch-chess-puzzles-1-0-2-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemini-3.1-pro-preview","configuration":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match; model=gemini-3.1-pro-preview; run=4QfM9qyeWGqNc8YTcQNV76; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":55.00000000000001,"warning":"Run-specific qualification requires review: In the initial run, 53 samples did not complete. These were rerun until 51 of them completed. The remaining samples are scored as incorrect."},{"id":"epoch-run-4S3ZrJDkwh4gmGrmJQdvzR","modelId":"glm-5.3","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"glm-5.3_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.3_max; run=4S3ZrJDkwh4gmGrmJQdvzR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":29.268292682926827,"warning":null},{"id":"epoch-run-4S4GXbkRhLz8wWP97jYG57","modelId":"deepseek-v4-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"deepseek-v4-flash-0731_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=deepseek-v4-flash-0731_max; run=4S4GXbkRhLz8wWP97jYG57; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34,"warning":null},{"id":"epoch-run-4uxDyWmq5f5azVYfWBGUHh","modelId":"gpt-5.6-sol","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"none","sourceLabel":"gpt-5.6-sol_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-sol_none; run=4uxDyWmq5f5azVYfWBGUHh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":33,"warning":null},{"id":"epoch-run-4vjzjypxWVWBVdAnwaDQYX","modelId":"qwen3.5-9b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-9B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-9B; run=4vjzjypxWVWBVdAnwaDQYX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":2,"warning":null},{"id":"epoch-run-58eQmyCfPa3FufhXJFvAL2","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-gpqa-diamond-1-0-6-choice","level":"thinking","sourceLabel":"claude-sonnet-4-6_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.6; scorer choice; model=claude-sonnet-4-6_32K; run=58eQmyCfPa3FufhXJFvAL2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.37373737373737,"warning":null},{"id":"epoch-run-58MQQiJ7vvgvP9e8LcG6eV","modelId":"gpt-oss-120b","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"medium","sourceLabel":"gpt-oss-120b_medium","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-oss-120b_medium; run=58MQQiJ7vvgvP9e8LcG6eV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":2,"warning":null},{"id":"epoch-run-5AijYw5bFJtSuahnbzNo6Z","modelId":"kimi-k2.7-code","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"kimi-k2.7-code","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=kimi-k2.7-code; run=5AijYw5bFJtSuahnbzNo6Z; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":36.5,"warning":null},{"id":"epoch-run-5Ax3kMh4Lmw8KsrJVWbXqn","modelId":"qwen3.7-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.7-flash","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-flash; run=5Ax3kMh4Lmw8KsrJVWbXqn; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":23,"warning":null},{"id":"epoch-run-5e4Jp9dxtNisWx2wbRRZxM","modelId":"qwen3.7-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"qwen3.7-flash","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.7-flash; run=5e4Jp9dxtNisWx2wbRRZxM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":15,"warning":null},{"id":"epoch-run-5FGXKvXQwGPtcCX2PNrLR5","modelId":"gpt-5.5","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"gpt-5.5_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.5_xhigh; run=5FGXKvXQwGPtcCX2PNrLR5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.26315789473684,"warning":null},{"id":"epoch-run-5FVmQUSS4uRd23f6nNgeRe","modelId":"qwen3.5-9b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-9B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-9B; run=5FVmQUSS4uRd23f6nNgeRe; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":42.77777777777778,"warning":null},{"id":"epoch-run-5kMRXeasRvtghXpDotCdgV","modelId":"gpt-5.6-sol","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"gpt-5.6-sol_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-sol_max; run=5kMRXeasRvtghXpDotCdgV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":57.99999999999999,"warning":null},{"id":"epoch-run-5mmrBSQb7hVSJ9VYtNm46i","modelId":"phi-4","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"phi-4","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=phi-4; run=5mmrBSQb7hVSJ9VYtNm46i; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":13.750000000000002,"warning":null},{"id":"epoch-run-5Q9RNC2JfEmmvNFFE5CQCf","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"claude-sonnet-4-6_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-4-6_high; run=5Q9RNC2JfEmmvNFFE5CQCf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":5,"warning":null},{"id":"epoch-run-5sNRWemuVwb4adBaSwrLFf","modelId":"gpt-6-astra","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"medium","sourceLabel":"gpt-6-astra_medium","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-6-astra_medium; run=5sNRWemuVwb4adBaSwrLFf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.5609756097561,"warning":null},{"id":"epoch-run-5u3LkMVq4Dy8CfiwA2EAVr","modelId":"claude-opus-4-8","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"claude-opus-4-8_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-8_low; run=5u3LkMVq4Dy8CfiwA2EAVr; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.999999999999996,"warning":null},{"id":"epoch-run-5yyuCCi2Dpfh6xLBMxqFyB","modelId":"gemini-3.8-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"high","sourceLabel":"gemini-3.8-flash_high","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gemini-3.8-flash_high; run=5yyuCCi2Dpfh6xLBMxqFyB; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47,"warning":null},{"id":"epoch-run-64rokFyL2L8Vd4SZVdayCy","modelId":"claude-opus-4-6","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"claude-opus-4-6_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-opus-4-6_max; run=64rokFyL2L8Vd4SZVdayCy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25,"warning":null},{"id":"epoch-run-6cmgkNAQZekBr6e6rVdLe9","modelId":"gpt-5.6-sol","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"gpt-5.6-sol_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-sol_low; run=6cmgkNAQZekBr6e6rVdLe9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":89.8989898989899,"warning":null},{"id":"epoch-run-6e3LDVuZwoZC4Sg7ushoVP","modelId":"grok-4.5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"grok-4.5_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.5_high; run=6e3LDVuZwoZC4Sg7ushoVP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":36,"warning":null},{"id":"epoch-run-6E989Xxeuw925T7cCV3XGB","modelId":"claude-fable-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"claude-fable-5_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5_low; run=6E989Xxeuw925T7cCV3XGB; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.77777777777777,"warning":null},{"id":"epoch-run-6iEkMa88YjLDgcde4bLm8B","modelId":"gemini-3.6-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gemini-3.6-flash_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.6-flash_low; run=6iEkMa88YjLDgcde4bLm8B; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.22222222222221,"warning":null},{"id":"epoch-run-6phXzd4aCbnBUSQmBsaywa","modelId":"glm-4.7","benchmarkId":"epoch-gpqa-diamond-1-0-4-choice","level":"unspecified","sourceLabel":"glm-4.7","configuration":"Epoch AI Inspect; task 1.0.4; scorer choice; model=glm-4.7; run=6phXzd4aCbnBUSQmBsaywa; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.33333333333334,"warning":null},{"id":"epoch-run-6pTYmQCw3EMbErvAqpivH5","modelId":"qwen3.7-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.7-flash","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.7-flash; run=6pTYmQCw3EMbErvAqpivH5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":19.298245614035086,"warning":null},{"id":"epoch-run-6qgxJVk8HHLppb7hPqz9Tv","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-chess-puzzles-1-0-0-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=claude-sonnet-4-5-20250929_32K; run=6qgxJVk8HHLppb7hPqz9Tv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-6rZFxNR3GjfhWey6DzEiYz","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-30b-a3b-thinking-2507","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-30b-a3b-thinking-2507; run=6rZFxNR3GjfhWey6DzEiYz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":70.27777777777777,"warning":null},{"id":"epoch-run-6XZAenohp9pCgQ3gVeUAi8","modelId":"qwen3.5-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.5-flash","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.5-flash; run=6XZAenohp9pCgQ3gVeUAi8; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":9.473684210526317,"warning":null},{"id":"epoch-run-6YAzFq89fwWiJ3uJdptCMr","modelId":"llama-3.1-8b-instruct","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Llama-3.1-8B-Instruct","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Llama-3.1-8B-Instruct; run=6YAzFq89fwWiJ3uJdptCMr; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1.6666666666666667,"warning":null},{"id":"epoch-run-72DQVwbYiQW5pjhshjBaGU","modelId":"gemini-3.5-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.5-flash_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.5-flash_high; run=72DQVwbYiQW5pjhshjBaGU; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":62.807017543859644,"warning":null},{"id":"epoch-run-79ZP6iwoBaF5t9a5VRqPnw","modelId":"minimax-m3","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"MiniMax-M3","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=MiniMax-M3; run=79ZP6iwoBaF5t9a5VRqPnw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":71.11111111111111,"warning":null},{"id":"epoch-run-7aAKcnsCXoSumfAu8mr2un","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"minimal","sourceLabel":"gemini-3.5-flash-lite_minimal","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.5-flash-lite_minimal; run=7aAKcnsCXoSumfAu8mr2un; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":74.24242424242425,"warning":null},{"id":"epoch-run-7cc6cDCXjsPjtKt36bbeMR","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"high","sourceLabel":"gemini-3-flash-preview_high","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gemini-3-flash-preview_high; run=7cc6cDCXjsPjtKt36bbeMR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.8,"warning":null},{"id":"epoch-run-7cL3BzoAaiHmdMNRCVLE6s","modelId":"gpt-5.6-sol","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-5.6-sol_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-sol_low; run=7cL3BzoAaiHmdMNRCVLE6s; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":27,"warning":null},{"id":"epoch-run-7crLvnfQc987dC6mr3iGbf","modelId":"grok-4.6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"xhigh","sourceLabel":"grok-4.6_xhigh","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.6_xhigh; run=7crLvnfQc987dC6mr3iGbf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":99.16666666666667,"warning":null},{"id":"epoch-run-7czodbcgEF5zN68ppPFzBN","modelId":"glm-5","benchmarkId":"epoch-chess-puzzles-1-0-2-model-extracted-exact-match","level":"unspecified","sourceLabel":"glm-5","configuration":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match; model=glm-5; run=7czodbcgEF5zN68ppPFzBN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":10,"warning":null},{"id":"epoch-run-7DQNxGG5q6i7VtnzF7vNxA","modelId":"glm-5.2","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"low","sourceLabel":"glm-5.2_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.2_low; run=7DQNxGG5q6i7VtnzF7vNxA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":19,"warning":null},{"id":"epoch-run-7GiYWM7UagUsHpNsdymd4z","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.6-35b-a3b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-35b-a3b_none; run=7GiYWM7UagUsHpNsdymd4z; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":68.88888888888889,"warning":null},{"id":"epoch-run-7HWW3sjRstKzb9JpcnvLaV","modelId":"grok-4.5","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"high","sourceLabel":"grok-4.5_high","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=grok-4.5_high; run=7HWW3sjRstKzb9JpcnvLaV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":48.3,"warning":null},{"id":"epoch-run-7iH4kjDYrjgRwQdKYgNACT","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"epoch-chess-puzzles-1-0-0-model-extracted-exact-match","level":"unspecified","sourceLabel":"Qwen3-235B-A22B-Thinking-2507","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=Qwen3-235B-A22B-Thinking-2507; run=7iH4kjDYrjgRwQdKYgNACT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":"Run-specific qualification requires review: Two samples did not complete, which is > than our 2% tolerance. As such, the score has been manually edited to grade them as incorrect."},{"id":"epoch-run-7oUkeLfwMK3MtkSNHX6QPu","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-sonnet-4-5-20250929_32K; run=7oUkeLfwMK3MtkSNHX6QPu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":23.859649122807017,"warning":null},{"id":"epoch-run-7QkPRbRPpRx8nJT2ZcqSx6","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_16K (thinking 16k)","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=claude-sonnet-4-5-20250929_16K; run=7QkPRbRPpRx8nJT2ZcqSx6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":71.11111111111111,"warning":null},{"id":"epoch-run-7RjsANKwwsePSstcZeSMhX","modelId":"gpt-5.6-sol","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"gpt-5.6-sol_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-sol_max; run=7RjsANKwwsePSstcZeSMhX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":100,"warning":null},{"id":"epoch-run-7vThbrtbczScg2UcsAYXtF","modelId":"grok-4.5","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"high","sourceLabel":"grok-4.5_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=grok-4.5_high; run=7vThbrtbczScg2UcsAYXtF; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":24.390243902439025,"warning":null},{"id":"epoch-run-84ARuGyhQsjgh8umRmBvas","modelId":"gemini-3.7-flash","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"high","sourceLabel":"gemini-3.7-flash_high","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gemini-3.7-flash_high; run=84ARuGyhQsjgh8umRmBvas; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":69.19999999999999,"warning":null},{"id":"epoch-run-85fhMxLaebWtLoi6oLpTbi","modelId":"claude-opus-4-6","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"claude-opus-4-6_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-opus-4-6_max; run=85fhMxLaebWtLoi6oLpTbi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47,"warning":null},{"id":"epoch-run-86SY5JbPB49xXhHFQW6tHu","modelId":"gemini-3.6-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"gemini-3.6-flash_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.6-flash_high; run=86SY5JbPB49xXhHFQW6tHu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.12878787878788,"warning":null},{"id":"epoch-run-89zcekqEYnE8zhwG4pR5Nu","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Llama-70B","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=DeepSeek-R1-Distill-Llama-70B; run=89zcekqEYnE8zhwG4pR5Nu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":51.388888888888886,"warning":null},{"id":"epoch-run-8grv57UmR89LXkEYhyssr9","modelId":"gpt-5.6-terra","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"none","sourceLabel":"gpt-5.6-terra_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-terra_none; run=8grv57UmR89LXkEYhyssr9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":14.000000000000002,"warning":null},{"id":"epoch-run-8iiRQiAoCepDELQfUv3VDq","modelId":"kimi-k2.6","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"kimi-k2.6_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=kimi-k2.6_none; run=8iiRQiAoCepDELQfUv3VDq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-8o2J9uQLKDCTiCFwYdkJRK","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.5-flash-lite_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.5-flash-lite_high; run=8o2J9uQLKDCTiCFwYdkJRK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25.964912280701753,"warning":null},{"id":"epoch-run-8qwT2CF9U5zV99PFirnVsp","modelId":"llama-3.2-1b-instruct","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Llama-3.2-1B-Instruct","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Llama-3.2-1B-Instruct; run=8qwT2CF9U5zV99PFirnVsp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0.5555555555555556,"warning":null},{"id":"epoch-run-8UqaLobhmNJLuPGTTpeaCw","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-14B","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=DeepSeek-R1-Distill-Qwen-14B; run=8UqaLobhmNJLuPGTTpeaCw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":44.696969696969695,"warning":null},{"id":"epoch-run-97t77hRrNae6Va8fBqBhPy","modelId":"minimax-m3","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"MiniMax-M3_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=MiniMax-M3_none; run=97t77hRrNae6Va8fBqBhPy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26.666666666666668,"warning":null},{"id":"epoch-run-99ys2jgQiPQ5UwrqnazfqA","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"gemini-3.1-flash-lite_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.1-flash-lite_low; run=99ys2jgQiPQ5UwrqnazfqA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":74.24242424242425,"warning":null},{"id":"epoch-run-9cXtChGrowgGDwa9AcAecB","modelId":"grok-4.6","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"xhigh","sourceLabel":"grok-4.6_xhigh","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=grok-4.6_xhigh; run=9cXtChGrowgGDwa9AcAecB; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34,"warning":null},{"id":"epoch-run-9ekki5tJhyjmA7ZMLoUxzo","modelId":"glm-4.7-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"glm-4.7-flash","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-4.7-flash; run=9ekki5tJhyjmA7ZMLoUxzo; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":58.333333333333336,"warning":null},{"id":"epoch-run-9F6GMXWPSzWo3evzcpAkTd","modelId":"gpt-oss-20b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"medium","sourceLabel":"gpt-oss-20b_medium","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-oss-20b_medium; run=9F6GMXWPSzWo3evzcpAkTd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4,"warning":null},{"id":"epoch-run-9kErpmgQ42wTvgJaFn478v","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3.6-35b-a3b_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.6-35b-a3b_none; run=9kErpmgQ42wTvgJaFn478v; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84.84848484848484,"warning":null},{"id":"epoch-run-9kSgmUd9vh4CBXz3tJhctN","modelId":"grok-4.5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"grok-4.5_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=grok-4.5_high; run=9kSgmUd9vh4CBXz3tJhctN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.43434343434343,"warning":null},{"id":"epoch-run-9LWdzVN5w4ihNvncsaCWMu","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-5-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-sonnet-4-6_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.5; scorer model_extracted_exact_match; model=claude-sonnet-4-6_32K; run=9LWdzVN5w4ihNvncsaCWMu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.7936507936508,"warning":null},{"id":"epoch-run-9RfS3yHmzmP3azirghceFL","modelId":"glm-5.3","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"glm-5.3_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.3_max; run=9RfS3yHmzmP3azirghceFL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21,"warning":null},{"id":"epoch-run-9SSHEP95FYVZvHDdoHSRy3","modelId":"llama-3.2-90b-vision-instruct","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"Llama-3.2-90B-Vision-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=Llama-3.2-90B-Vision-Instruct; run=9SSHEP95FYVZvHDdoHSRy3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":41.035353535353536,"warning":null},{"id":"epoch-run-9uKmMPn6eiRPsfcLKod7M7","modelId":"glm-5.2","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"glm-5.2_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_low; run=9uKmMPn6eiRPsfcLKod7M7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":75.55555555555556,"warning":null},{"id":"epoch-run-9WS6kHXT8XFtJWtE2wWLAo","modelId":"qwen3.5-35b-a3b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-35b-a3b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-35b-a3b; run=9WS6kHXT8XFtJWtE2wWLAo; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":54.44444444444444,"warning":null},{"id":"epoch-run-9YJf2nviwjM6WVhw8qeJta","modelId":"grok-4.6","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"xhigh","sourceLabel":"grok-4.6_xhigh","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=grok-4.6_xhigh; run=9YJf2nviwjM6WVhw8qeJta; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.18181818181817,"warning":null},{"id":"epoch-run-9zx2EXPTvPmxsL9qFCjP3x","modelId":"qwen3.6-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.6-flash","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-flash; run=9zx2EXPTvPmxsL9qFCjP3x; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84.44444444444444,"warning":null},{"id":"epoch-run-A33om9MTYMC7xYeLv9X7Ha","modelId":"kimi-k3","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"kimi-k3_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k3_max; run=A33om9MTYMC7xYeLv9X7Ha; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.22222222222221,"warning":null},{"id":"epoch-run-a4uE6KgMhGSUjcnemRnbkA","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3-flash-preview_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3-flash-preview_high; run=a4uE6KgMhGSUjcnemRnbkA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.55555555555556,"warning":null},{"id":"epoch-run-a4uV8HMMBAcHXLVSmZfBgX","modelId":"deepseek-v4-pro","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"deepseek-v4-pro-0813_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=deepseek-v4-pro-0813_max; run=a4uV8HMMBAcHXLVSmZfBgX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26.82926829268293,"warning":null},{"id":"epoch-run-A4yUA9PfzRr92JAqDDo9ro","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"qwen3.5-397b-a17b_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.5-397b-a17b_none; run=A4yUA9PfzRr92JAqDDo9ro; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":31.2280701754386,"warning":null},{"id":"epoch-run-a5qR5FNnftfR8pk9HJ3JUz","modelId":"qwen3.7-plus","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.7-plus_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.7-plus_none; run=a5qR5FNnftfR8pk9HJ3JUz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17,"warning":null},{"id":"epoch-run-a5YYZ3NSBGCUuALngGHhfZ","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-1.5B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=DeepSeek-R1-Distill-Qwen-1.5B; run=a5YYZ3NSBGCUuALngGHhfZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-ABT89ieSWGnGj4RYMduHiG","modelId":"qwen-3.8-max","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"qwen3.8-max_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.8-max_xhigh; run=ABT89ieSWGnGj4RYMduHiG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":74.73684210526315,"warning":null},{"id":"epoch-run-AczFCvkWR5SmdbV7eXruqj","modelId":"qwen3.5-9b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3.5-9B_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.5-9B_none; run=AczFCvkWR5SmdbV7eXruqj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":78.91414141414141,"warning":null},{"id":"epoch-run-adGE8rXdNuUFs96ioppbc5","modelId":"claude-opus-4-8","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"claude-opus-4-8_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-8_none; run=adGE8rXdNuUFs96ioppbc5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84.44444444444444,"warning":null},{"id":"epoch-run-aekViWbdqVVeXpEG5hrSbQ","modelId":"glm-5.2","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"minimal","sourceLabel":"glm-5.2_minimal","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.2_minimal; run=aekViWbdqVVeXpEG5hrSbQ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":18,"warning":null},{"id":"epoch-run-AfKJ2DGMhkjZmeFZxGoY3w","modelId":"gpt-6-astra","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"gpt-6-astra_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-6-astra_xhigh; run=AfKJ2DGMhkjZmeFZxGoY3w; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.6,"warning":null},{"id":"epoch-run-aftzew4ra4iax5D4R4vvfF","modelId":"claude-fable-5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"claude-fable-5_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5_low; run=aftzew4ra4iax5D4R4vvfF; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.000000000000004,"warning":null},{"id":"epoch-run-afxoicJc4C6caVDwUpsiME","modelId":"qwen3.5-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"qwen3.5-flash_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.5-flash_none; run=afxoicJc4C6caVDwUpsiME; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":18.24561403508772,"warning":null},{"id":"epoch-run-agebmxGseTvmvN4AHN8i4m","modelId":"qwen3-235b-a22b","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"qwen3-235b-a22b","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=qwen3-235b-a22b; run=agebmxGseTvmvN4AHN8i4m; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":70.70707070707071,"warning":null},{"id":"epoch-run-aGRKHaq9uSawfYVpC565zU","modelId":"qwen-3.8-max","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"xhigh","sourceLabel":"qwen3.8-max_xhigh","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.8-max_xhigh; run=aGRKHaq9uSawfYVpC565zU; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":99.44444444444444,"warning":null},{"id":"epoch-run-AhtQ5ggs4pTfLDqHFjueGy","modelId":"gpt-5.6-luna","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"gpt-5.6-luna_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-luna_max; run=AhtQ5ggs4pTfLDqHFjueGy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":98.33333333333333,"warning":null},{"id":"epoch-run-ajQFZGMjvyMTH2ULDZhwtz","modelId":"gemini-3.6-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.6-flash_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.6-flash_high; run=ajQFZGMjvyMTH2ULDZhwtz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.16666666666667,"warning":null},{"id":"epoch-run-amkBg66TZcYjF26HaRAXfs","modelId":"claude-opus-4-6","benchmarkId":"epoch-chess-puzzles-1-0-1-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-opus-4-6_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.1; scorer model_extracted_exact_match; model=claude-opus-4-6_32K; run=amkBg66TZcYjF26HaRAXfs; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17,"warning":null},{"id":"epoch-run-aMtSkxyLZPdf6o6f5zLP6A","modelId":"gemini-3.6-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.6-flash_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.6-flash_high; run=aMtSkxyLZPdf6o6f5zLP6A; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":40,"warning":null},{"id":"epoch-run-AoAD5uVtgVDnXmwA7STuno","modelId":"kimi-k3","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"kimi-k3_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=kimi-k3_high; run=AoAD5uVtgVDnXmwA7STuno; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.91919191919192,"warning":null},{"id":"epoch-run-AoYLH4gxsYmhLYi9gyduiM","modelId":"qwen3-30b-a3b-thinking-2507","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-30b-a3b-thinking-2507","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-30b-a3b-thinking-2507; run=AoYLH4gxsYmhLYi9gyduiM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":8,"warning":null},{"id":"epoch-run-aPmR8fV49N98a6NVKpASAf","modelId":"gemini-3.6-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"minimal","sourceLabel":"gemini-3.6-flash_minimal","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.6-flash_minimal; run=aPmR8fV49N98a6NVKpASAf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.85858585858585,"warning":null},{"id":"epoch-run-ASLdzByzxxMxFeLc7dwTPi","modelId":"qwen3-8b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3-8b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-8b_none; run=ASLdzByzxxMxFeLc7dwTPi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22.22222222222222,"warning":null},{"id":"epoch-run-awDKyKbPXRzBVZzfdQucef","modelId":"qwen3.5-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-flash","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-flash; run=awDKyKbPXRzBVZzfdQucef; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84.44444444444444,"warning":null},{"id":"epoch-run-axMdgNDC8UYYLnZYLHZpF5","modelId":"gemini-3.7-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.7-flash_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.7-flash_high; run=axMdgNDC8UYYLnZYLHZpF5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":71.57894736842105,"warning":null},{"id":"epoch-run-aYau6EG7CCaWVSyVq3vvQc","modelId":"glm-4.7","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"glm-4.7","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=glm-4.7; run=aYau6EG7CCaWVSyVq3vvQc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":32.2,"warning":null},{"id":"epoch-run-AZHoMLTNQEcKLwtv7QzBLZ","modelId":"claude-sonnet-5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"unspecified","sourceLabel":"claude-sonnet-5","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=claude-sonnet-5; run=AZHoMLTNQEcKLwtv7QzBLZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":16,"warning":null},{"id":"epoch-run-azk4theXxAsizmoi2HDD49","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-4-5-20251101_32K; run=azk4theXxAsizmoi2HDD49; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4.878048780487805,"warning":null},{"id":"epoch-run-b3cBsiDi4D7NtisdffQqxV","modelId":"glm-5.3-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"glm-5.3-flash_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.3-flash_max; run=b3cBsiDi4D7NtisdffQqxV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":14.000000000000002,"warning":null},{"id":"epoch-run-B3Kno3buYWRYbZxU33STiX","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gemini-3.5-flash-lite_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash-lite_low; run=B3Kno3buYWRYbZxU33STiX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":60,"warning":null},{"id":"epoch-run-b6yWmeFgsWeEiG9Qzs3NSf","modelId":"deepseek-v4-pro","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"deepseek-v4-pro-0813_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=deepseek-v4-pro-0813_max; run=b6yWmeFgsWeEiG9Qzs3NSf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":64.56140350877193,"warning":null},{"id":"epoch-run-b7Lw9ExxAhVY3hdExoh4MP","modelId":"glm-5.1","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"glm-5.1","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.1; run=b7Lw9ExxAhVY3hdExoh4MP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.33333333333333,"warning":null},{"id":"epoch-run-B8MaPUe3EYwUZASsNqE7C9","modelId":"kimi-k3","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"kimi-k3_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=kimi-k3_max; run=B8MaPUe3EYwUZASsNqE7C9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.11868686868688,"warning":null},{"id":"epoch-run-b9csPZ2c9CAsRXmzzfVoEW","modelId":"qwen3.5-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"qwen3.5-flash","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.5-flash; run=b9csPZ2c9CAsRXmzzfVoEW; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-BAi4jidcT3F6reBkSXDJKv","modelId":"qwen3-32b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Qwen3-32B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Qwen3-32B; run=BAi4jidcT3F6reBkSXDJKv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.94444444444444,"warning":null},{"id":"epoch-run-bAR85KQmEATQP8j764jpBA","modelId":"claude-fable-5","benchmarkId":"epoch-chess-puzzles-1-1-5-model-extracted-exact-match","level":"max","sourceLabel":"claude-fable-5_max","configuration":"Epoch AI Inspect; task 1.1.5; scorer model_extracted_exact_match; model=claude-fable-5_max; run=bAR85KQmEATQP8j764jpBA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":41,"warning":null},{"id":"epoch-run-BbM4xbJcS5sjrzZABGg8K7","modelId":"claude-opus-4-6","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"unspecified","sourceLabel":"claude-opus-4-6","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=claude-opus-4-6; run=BbM4xbJcS5sjrzZABGg8K7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":15,"warning":null},{"id":"epoch-run-bbqokudairnKtbyjBjuWCx","modelId":"qwen3-1.7b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3-1.7b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-1.7b_none; run=bbqokudairnKtbyjBjuWCx; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":8.055555555555555,"warning":null},{"id":"epoch-run-bBV5wCrrZtihrgxEsg9jPD","modelId":"deepseek-r1-0528","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"DeepSeek-R1-0528","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=DeepSeek-R1-0528; run=bBV5wCrrZtihrgxEsg9jPD; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.38888888888889,"warning":null},{"id":"epoch-run-BCCBjMXW674jF57sP4jf2h","modelId":"gemini-3.8-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.8-flash_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.8-flash_high; run=BCCBjMXW674jF57sP4jf2h; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":61,"warning":null},{"id":"epoch-run-bCdwpRXgZtvQLYC4wA9JXr","modelId":"muse-spark-1.1","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"muse-spark-1.1","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=muse-spark-1.1; run=bCdwpRXgZtvQLYC4wA9JXr; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":57.78894472361809,"warning":null},{"id":"epoch-run-bcntamvGsSH6QgETdoaSph","modelId":"kimi-k3","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"kimi-k3_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k3_max; run=bcntamvGsSH6QgETdoaSph; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":72.1830985915493,"warning":null},{"id":"epoch-run-bDKKx7zTdW5WwMCfwqsLi4","modelId":"gpt-5.6-luna","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"none","sourceLabel":"gpt-5.6-luna_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-luna_none; run=bDKKx7zTdW5WwMCfwqsLi4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":63.63636363636363,"warning":null},{"id":"epoch-run-bDS2AGEf3AywbVcdDyAKZK","modelId":"phi-3-medium-128k-instruct","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"Phi-3-medium-128k-instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=Phi-3-medium-128k-instruct; run=bDS2AGEf3AywbVcdDyAKZK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":27.58838383838384,"warning":null},{"id":"epoch-run-bdsZjrG4ayzP8NAJg5q586","modelId":"grok-4.3","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"high","sourceLabel":"grok-4.3_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=grok-4.3_high; run=bdsZjrG4ayzP8NAJg5q586; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":42.80701754385965,"warning":null},{"id":"epoch-run-beRGgJXTJggTi8PPEZNoZ5","modelId":"mistral-large-2411","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"mistral-large-2411","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=mistral-large-2411; run=beRGgJXTJggTi8PPEZNoZ5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":7.777777777777778,"warning":null},{"id":"epoch-run-bfftd5EzUK9yAekafEofvK","modelId":"qwen-3.8-max","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"xhigh","sourceLabel":"qwen3.8-max_xhigh","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=qwen3.8-max_xhigh; run=bfftd5EzUK9yAekafEofvK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":45.800000000000004,"warning":null},{"id":"epoch-run-bg3JRdd33iWfvRoGSvyXXE","modelId":"grok-4.6","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"grok-4.6_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=grok-4.6_xhigh; run=bg3JRdd33iWfvRoGSvyXXE; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":31.70731707317073,"warning":null},{"id":"epoch-run-bggkB6SQyMaVNvB2Txr9Nd","modelId":"seed-oss-36b-instruct","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"seed-oss-36b-instruct","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=seed-oss-36b-instruct; run=bggkB6SQyMaVNvB2Txr9Nd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":13,"warning":null},{"id":"epoch-run-BgmrBFsbsaD8rNpebv49Da","modelId":"gemini-3.1-pro","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"gemini-3.1-pro-preview_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.1-pro-preview_high; run=BgmrBFsbsaD8rNpebv49Da; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.44444444444444,"warning":null},{"id":"epoch-run-BiaKGj9CUTKhhNwW9SM4qt","modelId":"claude-opus-5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-opus-5_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-5_max; run=BiaKGj9CUTKhhNwW9SM4qt; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":42,"warning":null},{"id":"epoch-run-BJiQ8aRjMyCGPTBGYfBhyj","modelId":"gpt-5.6-luna","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"gpt-5.6-luna_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-luna_max; run=BJiQ8aRjMyCGPTBGYfBhyj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":40,"warning":null},{"id":"epoch-run-bJV4D8SEo9zMJPEYTTXJNZ","modelId":"ministral-3b-2410","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"ministral-3b-2410","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=ministral-3b-2410; run=bJV4D8SEo9zMJPEYTTXJNZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25.252525252525253,"warning":null},{"id":"epoch-run-BLjXudxuEyLbZiKBSZz326","modelId":"glm-5.2","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"glm-5.2_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.2_none; run=BLjXudxuEyLbZiKBSZz326; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":18,"warning":null},{"id":"epoch-run-BnqWATgxsPzSF7ojBEMoG3","modelId":"gemini-3.7-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.7-flash_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.7-flash_high; run=BnqWATgxsPzSF7ojBEMoG3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47,"warning":null},{"id":"epoch-run-BnX67AoZzgVbHgaM8F8Brz","modelId":"qwen3-30b-a3b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"Qwen3-30B-A3B","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=Qwen3-30B-A3B; run=BnX67AoZzgVbHgaM8F8Brz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":61.67929292929293,"warning":null},{"id":"epoch-run-BP3KYD8rYyFg3LviNGtjLL","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"Qwen3-235B-A22B-Thinking-2507","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=Qwen3-235B-A22B-Thinking-2507; run=BP3KYD8rYyFg3LviNGtjLL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":9,"warning":null},{"id":"epoch-run-bpZy8tAbh7UV6A6U7XZtBg","modelId":"nemotron-3-ultra","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"nemotron-3-ultra","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=nemotron-3-ultra; run=bpZy8tAbh7UV6A6U7XZtBg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.35353535353535,"warning":null},{"id":"epoch-run-bqiVinHXFcgyFGPstJwXJN","modelId":"claude-sonnet-5","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-sonnet-5_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-sonnet-5_max; run=bqiVinHXFcgyFGPstJwXJN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":29.268292682926827,"warning":null},{"id":"epoch-run-Br3mjs2GrYcCwX9AMwcihU","modelId":"gemini-3.8-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"gemini-3.8-flash_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.8-flash_high; run=Br3mjs2GrYcCwX9AMwcihU; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.39141414141415,"warning":null},{"id":"epoch-run-BSSNShjap29bDUHz4gA9oh","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.5-flash-lite_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash-lite_high; run=BSSNShjap29bDUHz4gA9oh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22,"warning":null},{"id":"epoch-run-BTeRdhgt6TFBj6QkGX2j6P","modelId":"kimi-k2.6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-3-model-extracted-exact-match","level":"unspecified","sourceLabel":"kimi-k2.6","configuration":"Epoch AI Inspect; task 1.1.3; scorer model_extracted_exact_match; model=kimi-k2.6; run=BTeRdhgt6TFBj6QkGX2j6P; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":96.11111111111111,"warning":null},{"id":"epoch-run-bUATynSWVG53pxLCE2zeAD","modelId":"qwen3-8b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3-8b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-8b_none; run=bUATynSWVG53pxLCE2zeAD; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-BUBiYK8WB8XDb9u7s9kTDf","modelId":"kimi-k3","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"kimi-k3_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k3_low; run=BUBiYK8WB8XDb9u7s9kTDf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-buLf8Ne29xmzMZBRQkvrQG","modelId":"qwen3.6-27b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.6-27b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.6-27b; run=buLf8Ne29xmzMZBRQkvrQG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.85858585858585,"warning":null},{"id":"epoch-run-BVat526nF6NUGoVaLCp7DT","modelId":"seed-oss-36b-instruct","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"seed-oss-36b-instruct","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=seed-oss-36b-instruct; run=BVat526nF6NUGoVaLCp7DT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":71.52777777777779,"warning":null},{"id":"epoch-run-BvShPsULJMkwxxf8vBSNfu","modelId":"gpt-5.6-luna","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"medium","sourceLabel":"gpt-5.6-luna_medium","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-luna_medium; run=BvShPsULJMkwxxf8vBSNfu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-bwak5Cq3LBthfoboicGZUo","modelId":"claude-opus-4-8","benchmarkId":"epoch-chess-puzzles-1-1-4-model-extracted-exact-match","level":"max","sourceLabel":"claude-opus-4-8_max","configuration":"Epoch AI Inspect; task 1.1.4; scorer model_extracted_exact_match; model=claude-opus-4-8_max; run=bwak5Cq3LBthfoboicGZUo; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34,"warning":null},{"id":"epoch-run-bWnggCv6to2QKSjngrtuos","modelId":"claude-opus-5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"unspecified","sourceLabel":"claude-opus-5","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=claude-opus-5; run=bWnggCv6to2QKSjngrtuos; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":37,"warning":null},{"id":"epoch-run-BWz8uig4QyqPtke59pM88z","modelId":"qwen3.7-plus","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3.7-plus_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.7-plus_none; run=BWz8uig4QyqPtke59pM88z; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":81.81818181818183,"warning":null},{"id":"epoch-run-bXgZZgzRE3wXoSRUgrbsVf","modelId":"gemini-3.1-pro","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-5-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemini-3.1-pro-preview","configuration":"Epoch AI Inspect; task 1.0.5; scorer model_extracted_exact_match; model=gemini-3.1-pro-preview; run=bXgZZgzRE3wXoSRUgrbsVf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.6,"warning":"Run-specific qualification requires review: In the initial run, no epochs completed for 2/45 samples. Despite several re-runs of these two samples, no epochs completed. All epochs for the other 43/45 samples were correct. The model's score was edited to be 43/45."},{"id":"epoch-run-bXrmQqzF9sXbuZfRrSc7NP","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3.5-397b-a17b_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.5-397b-a17b_none; run=bXrmQqzF9sXbuZfRrSc7NP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.36363636363636,"warning":null},{"id":"epoch-run-BxrNfyMffkVUq4n7U5eK3Q","modelId":"kimi-k2.6","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"kimi-k2.6","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k2.6; run=BxrNfyMffkVUq4n7U5eK3Q; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":57.19298245614035,"warning":null},{"id":"epoch-run-bzuVVvmLtPCgofXqY7mTVR","modelId":"glm-4.7","benchmarkId":"epoch-chess-puzzles-1-0-1-model-extracted-exact-match","level":"unspecified","sourceLabel":"glm-4.7","configuration":"Epoch AI Inspect; task 1.0.1; scorer model_extracted_exact_match; model=glm-4.7; run=bzuVVvmLtPCgofXqY7mTVR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":6,"warning":null},{"id":"epoch-run-c2KVkMCWnpo6BbnMWgdaDH","modelId":"deepseek-v4-pro","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"deepseek-v4-pro-0813_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=deepseek-v4-pro-0813_max; run=c2KVkMCWnpo6BbnMWgdaDH; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":43,"warning":null},{"id":"epoch-run-c2YLifDU4zYCX5Jbi9HLL7","modelId":"qwen-3.8-max","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"xhigh","sourceLabel":"qwen3.8-max_xhigh","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.8-max_xhigh; run=c2YLifDU4zYCX5Jbi9HLL7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":38,"warning":null},{"id":"epoch-run-c5kpB4axzmygRywWqBKFmv","modelId":"glm-5.2","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"glm-5.2_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.2_max; run=c5kpB4axzmygRywWqBKFmv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.85606060606061,"warning":null},{"id":"epoch-run-CA5LW4phRnHSsZUGXEm8H6","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-opus-4-5-20251101_32K; run=CA5LW4phRnHSsZUGXEm8H6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":45.7,"warning":null},{"id":"epoch-run-CAoLSNkdR27AmHb84fnr8B","modelId":"kimi-k3","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"low","sourceLabel":"kimi-k3_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=kimi-k3_low; run=CAoLSNkdR27AmHb84fnr8B; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-CAyLyhDHZiMQBZDB3qd8tG","modelId":"gemma-3-12b-it","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemma-3-12b-it","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-3-12b-it; run=CAyLyhDHZiMQBZDB3qd8tG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":16.666666666666664,"warning":null},{"id":"epoch-run-CBbeMKRRSeRsXnvSfn7Png","modelId":"glm-5.1","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"glm-5.1","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.1; run=CBbeMKRRSeRsXnvSfn7Png; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":89.8989898989899,"warning":null},{"id":"epoch-run-ccbx7KQY9bTD563vzBXwSg","modelId":"glm-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-5-model-extracted-exact-match","level":"unspecified","sourceLabel":"glm-5","configuration":"Epoch AI Inspect; task 1.0.5; scorer model_extracted_exact_match; model=glm-5; run=ccbx7KQY9bTD563vzBXwSg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80,"warning":"Run-specific qualification requires review: Two samples did not complete, which is greater than our 2% error tolerance setting. As such, the score has been manually edited to grade them as incorrect."},{"id":"epoch-run-CdmtwZ8NR8YeTXWiLVTRDJ","modelId":"gpt-5.5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-5.5_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.5_low; run=CdmtwZ8NR8YeTXWiLVTRDJ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84.44444444444444,"warning":null},{"id":"epoch-run-CeDghdBk8CqtiFSbUzxNH5","modelId":"gpt-5.6-luna","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"max","sourceLabel":"gpt-5.6-luna_max","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=gpt-5.6-luna_max; run=CeDghdBk8CqtiFSbUzxNH5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":41,"warning":null},{"id":"epoch-run-cF97JqHbFxxp7ePjYVK9HV","modelId":"gemini-3.6-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemini-3.6-flash_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.6-flash_minimal; run=cF97JqHbFxxp7ePjYVK9HV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80,"warning":null},{"id":"epoch-run-CFBCC2QrkCAFBAvFj5pqPF","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gemini-3.1-flash-lite_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.1-flash-lite_low; run=CFBCC2QrkCAFBAvFj5pqPF; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":44.44444444444444,"warning":null},{"id":"epoch-run-cFbntXuxUtfreULvt7vEt7","modelId":"qwen3.5-plus","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-plus","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-plus; run=cFbntXuxUtfreULvt7vEt7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.66666666666667,"warning":null},{"id":"epoch-run-CfmvbqzjpF6cCJQfzqdD4w","modelId":"qwen3-32b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"Qwen3-32B_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Qwen3-32B_none; run=CfmvbqzjpF6cCJQfzqdD4w; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":23.055555555555557,"warning":null},{"id":"epoch-run-CGac6TZg5qVdxNGULzfR6R","modelId":"qwen3.6-27b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.6-27b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-27b_none; run=CGac6TZg5qVdxNGULzfR6R; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":9,"warning":null},{"id":"epoch-run-cgnopvpB6mzsfb9yGnYK2z","modelId":"claude-haiku-4-5-20251001","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"claude-haiku-4-5-20251001","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=claude-haiku-4-5-20251001; run=cgnopvpB6mzsfb9yGnYK2z; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":60.47979797979798,"warning":null},{"id":"epoch-run-chbh6XstiqtUa5W9zuyfjS","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"gemini-3.5-flash-lite_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.5-flash-lite_high; run=chbh6XstiqtUa5W9zuyfjS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.33333333333334,"warning":null},{"id":"epoch-run-cjUVqF2qQJ4qhFKBU5BQpW","modelId":"gpt-5.6-terra","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"none","sourceLabel":"gpt-5.6-terra_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-terra_none; run=cjUVqF2qQJ4qhFKBU5BQpW; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":53.333333333333336,"warning":null},{"id":"epoch-run-ckbZdkrXPwbFdjn6bmUQsi","modelId":"claude-opus-4-8","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"claude-opus-4-8_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-opus-4-8_none; run=ckbZdkrXPwbFdjn6bmUQsi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.35353535353535,"warning":null},{"id":"epoch-run-CmHy8cVECGkvQTwakfjRo2","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"minimal","sourceLabel":"gemini-3.1-flash-lite_minimal","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.1-flash-lite_minimal; run=CmHy8cVECGkvQTwakfjRo2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":73.73737373737373,"warning":null},{"id":"epoch-run-cMwETYmC6b4yKupyJfEHv2","modelId":"gpt-oss-20b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-oss-20b_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-oss-20b_low; run=cMwETYmC6b4yKupyJfEHv2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":40.27777777777778,"warning":null},{"id":"epoch-run-coxYk5vK5cBhQ7iZohMtA5","modelId":"claude-opus-4-6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-opus-4-6_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-6_max; run=coxYk5vK5cBhQ7iZohMtA5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.11111111111111,"warning":null},{"id":"epoch-run-CQhcUcXfPPJKuyt57AHZw5","modelId":"gpt-5.6-terra","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"gpt-5.6-terra_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-terra_max; run=CQhcUcXfPPJKuyt57AHZw5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":54,"warning":null},{"id":"epoch-run-cqUZ6gcq2HBnShFRWvKjGr","modelId":"gemini-2.5-pro","benchmarkId":"epoch-gpqa-diamond-1-0-1-choice","level":"unspecified","sourceLabel":"gemini-2.5-pro","configuration":"Epoch AI Inspect; task 1.0.1; scorer choice; model=gemini-2.5-pro; run=cqUZ6gcq2HBnShFRWvKjGr; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.29040404040404,"warning":null},{"id":"epoch-run-csK2fe5T8p2R7WgoJUu6bZ","modelId":"gpt-6-astra","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"gpt-6-astra_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-6-astra_max; run=csK2fe5T8p2R7WgoJUu6bZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.6842105263158,"warning":null},{"id":"epoch-run-cSTYZ3FKp5Mbs3xopn68NK","modelId":"magistral-small-2509","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"magistral-small-2509","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=magistral-small-2509; run=cSTYZ3FKp5Mbs3xopn68NK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.055555555555557,"warning":null},{"id":"epoch-run-cUim7Aqc8ifJMM69uXSeSn","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-32B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=DeepSeek-R1-Distill-Qwen-32B; run=cUim7Aqc8ifJMM69uXSeSn; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1,"warning":null},{"id":"epoch-run-CVuujQbCY38ZStXnBcFex9","modelId":"gpt-5.6-sol","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"gpt-5.6-sol_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-sol_max; run=CVuujQbCY38ZStXnBcFex9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":55.00000000000001,"warning":null},{"id":"epoch-run-cXkPywkhy3NnW992ri73yG","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-gpqa-diamond-1-0-2-choice","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_16K (thinking 16k)","configuration":"Epoch AI Inspect; task 1.0.2; scorer choice; model=claude-opus-4-5-20251101_16K; run=cXkPywkhy3NnW992ri73yG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.47979797979798,"warning":null},{"id":"epoch-run-cXn5zzns6VFwbTgotDwZjV","modelId":"gemini-3.5-flash","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.5-flash_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.5-flash_high; run=cXn5zzns6VFwbTgotDwZjV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26.82926829268293,"warning":null},{"id":"epoch-run-czNLsHc7tBqBWtWaoTSLXh","modelId":"claude-sonnet-5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-sonnet-5_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-5_max; run=czNLsHc7tBqBWtWaoTSLXh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":16,"warning":null},{"id":"epoch-run-d23hYvSNGFo7rniLFyBWiu","modelId":"claude-fable-5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"claude-fable-5_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-fable-5_high; run=d23hYvSNGFo7rniLFyBWiu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.33333333333334,"warning":null},{"id":"epoch-run-d3m9Xip8cof4s77z6LKkEh","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-sonnet-4-5-20250929_32K; run=d3m9Xip8cof4s77z6LKkEh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":2.4390243902439024,"warning":null},{"id":"epoch-run-D3mtasTumfvjR4fjmnHWRy","modelId":"claude-opus-5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"claude-opus-5_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-opus-5_max; run=D3mtasTumfvjR4fjmnHWRy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.87626262626263,"warning":null},{"id":"epoch-run-D3YDUZSfEUDsS4frLbEKDu","modelId":"qwen3.7-max","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.7-max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-max; run=D3YDUZSfEUDsS4frLbEKDu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.55555555555556,"warning":null},{"id":"epoch-run-D5cbXacPnJ8akq2jAtifEQ","modelId":"gemma-4-31b-it","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"gemma-4-31b-it","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gemma-4-31b-it; run=D5cbXacPnJ8akq2jAtifEQ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":10.4,"warning":null},{"id":"epoch-run-D7WDyCr24AVdzr4eKAreJu","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.5-397b-a17b_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.5-397b-a17b_none; run=D7WDyCr24AVdzr4eKAreJu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":18,"warning":null},{"id":"epoch-run-d8egYFK9XNSEHWvv4JFxWx","modelId":"kimi-k3","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"kimi-k3_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k3_high; run=d8egYFK9XNSEHWvv4JFxWx; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25,"warning":null},{"id":"epoch-run-d9jMGFp8BwebW7sufdxbnC","modelId":"gpt-5.6-luna","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"none","sourceLabel":"gpt-5.6-luna_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-luna_none; run=d9jMGFp8BwebW7sufdxbnC; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":2,"warning":null},{"id":"epoch-run-dagNWyu57ksu7gB7Q86eCx","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-397b-a17b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-397b-a17b; run=dagNWyu57ksu7gB7Q86eCx; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-DAyGUk5kLRdwNkSPZgqmos","modelId":"claude-sonnet-5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"xhigh","sourceLabel":"claude-sonnet-5_xhigh","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-5_xhigh; run=DAyGUk5kLRdwNkSPZgqmos; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":35,"warning":null},{"id":"epoch-run-DB8ja6pEZWGocQbdciyisL","modelId":"gpt-oss-20b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"medium","sourceLabel":"gpt-oss-20b_medium","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-oss-20b_medium; run=DB8ja6pEZWGocQbdciyisL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":65.27777777777779,"warning":null},{"id":"epoch-run-dBHxnnTzLGz3nHis5LET6t","modelId":"claude-fable-5-1","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"claude-fable-5-1_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-fable-5-1_max; run=dBHxnnTzLGz3nHis5LET6t; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":57.99999999999999,"warning":null},{"id":"epoch-run-DCJQMqipndGxwMXe8BDGeg","modelId":"gpt-oss-20b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"gpt-oss-20b_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-oss-20b_low; run=DCJQMqipndGxwMXe8BDGeg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":53.15656565656566,"warning":null},{"id":"epoch-run-DDfYPyKQW7vgDtGgkwcKSi","modelId":"gpt-5.6-sol","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"none","sourceLabel":"gpt-5.6-sol_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-sol_none; run=DDfYPyKQW7vgDtGgkwcKSi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.82828282828282,"warning":null},{"id":"epoch-run-DGEzZA6nvTne4MEGSuo3Tm","modelId":"ministral-8b-2410","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"ministral-8b-2410","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=ministral-8b-2410; run=DGEzZA6nvTne4MEGSuo3Tm; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":27.146464646464647,"warning":null},{"id":"epoch-run-dgSJTFQ4UtuQKEhB9ss6K7","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"gemini-3.5-flash-lite_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.5-flash-lite_low; run=dgSJTFQ4UtuQKEhB9ss6K7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":75.75757575757575,"warning":null},{"id":"epoch-run-DGSmhVxWsi7chsuKS64VLg","modelId":"qwen3-30b-a3b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"Qwen3-30B-A3B_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=Qwen3-30B-A3B_none; run=DGSmhVxWsi7chsuKS64VLg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":50.378787878787875,"warning":null},{"id":"epoch-run-DhJ248BX3ZPBHXvkRG4Qsz","modelId":"gemma-3-27b-it","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemma-3-27b-it","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-3-27b-it; run=DhJ248BX3ZPBHXvkRG4Qsz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22.5,"warning":null},{"id":"epoch-run-DienatPbgfgn3EzM7Gvzxr","modelId":"gpt-5.6-terra","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"max","sourceLabel":"gpt-5.6-terra_max","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=gpt-5.6-terra_max; run=DienatPbgfgn3EzM7Gvzxr; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":43.2,"warning":null},{"id":"epoch-run-DiXCMhdfhcjaCUSzYWgACy","modelId":"claude-opus-4-6","benchmarkId":"epoch-gpqa-diamond-1-0-4-choice","level":"thinking","sourceLabel":"claude-opus-4-6_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.4; scorer choice; model=claude-opus-4-6_32K; run=DiXCMhdfhcjaCUSzYWgACy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.53030303030303,"warning":null},{"id":"epoch-run-djbbEqvBW9qux3pZwcZN2i","modelId":"grok-4.5","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"high","sourceLabel":"grok-4.5_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=grok-4.5_high; run=djbbEqvBW9qux3pZwcZN2i; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":57.19298245614035,"warning":null},{"id":"epoch-run-DjFkVt62QwqQ4xXwzYR5Ng","modelId":"qwen3.5-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.5-flash_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.5-flash_none; run=DjFkVt62QwqQ4xXwzYR5Ng; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":16,"warning":null},{"id":"epoch-run-dKCWFaoGCWJTnD5CPWQGru","modelId":"grok-4.6","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"xhigh","sourceLabel":"grok-4.6_xhigh","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=grok-4.6_xhigh; run=dKCWFaoGCWJTnD5CPWQGru; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":48.9,"warning":null},{"id":"epoch-run-dKZDn279PKuc2Kxm68D4r2","modelId":"qwen3.6-27b","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.6-27b_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.6-27b_none; run=dKZDn279PKuc2Kxm68D4r2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":7.000000000000001,"warning":null},{"id":"epoch-run-dLDBahYBTGRNjbsXA5pyr3","modelId":"glm-5.3","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"glm-5.3_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.3_max; run=dLDBahYBTGRNjbsXA5pyr3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.9090909090909,"warning":null},{"id":"epoch-run-DLvSYBHHLcHECeL5SpNgVK","modelId":"gemini-3.6-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gemini-3.6-flash_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.6-flash_low; run=DLvSYBHHLcHECeL5SpNgVK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":43,"warning":null},{"id":"epoch-run-DmdKPD9Z9RXwYyATAoG4Uw","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"claude-sonnet-4-6_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-sonnet-4-6_high; run=DmdKPD9Z9RXwYyATAoG4Uw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.33333333333334,"warning":null},{"id":"epoch-run-DMei2tkTbCqecGNjYCYYoW","modelId":"grok-4.20-0309-reasoning","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"grok-4.20-0309-reasoning","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.20-0309-reasoning; run=DMei2tkTbCqecGNjYCYYoW; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":24,"warning":null},{"id":"epoch-run-DMjUrG6eZEqwcQ4SqUoViu","modelId":"qwen3.7-max","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"qwen3.7-max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=qwen3.7-max; run=DMjUrG6eZEqwcQ4SqUoViu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":55.76730190571715,"warning":null},{"id":"epoch-run-DmptTSPXx5uM5TYZoV59JT","modelId":"qwen3.7-plus","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"qwen3.7-plus","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.7-plus; run=DmptTSPXx5uM5TYZoV59JT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17,"warning":null},{"id":"epoch-run-doNrgGQY5SytQV22WRqw5L","modelId":"qwen3.7-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"qwen3.7-flash_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.7-flash_none; run=doNrgGQY5SytQV22WRqw5L; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":19.298245614035086,"warning":null},{"id":"epoch-run-doo2bL7TEHLCNNMwf7NbYN","modelId":"qwen3-14b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-14b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-14b; run=doo2bL7TEHLCNNMwf7NbYN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4,"warning":null},{"id":"epoch-run-DPwt4tRRKyqEjPE8Jc2Co9","modelId":"qwen3-8b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-8b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-8b; run=DPwt4tRRKyqEjPE8Jc2Co9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":5,"warning":null},{"id":"epoch-run-dqgqP2uEPswfECCVj2Kbr9","modelId":"claude-opus-4-8","benchmarkId":"epoch-gpqa-diamond-1-0-10-choice","level":"max","sourceLabel":"claude-opus-4-8_max","configuration":"Epoch AI Inspect; task 1.0.10; scorer choice; model=claude-opus-4-8_max; run=dqgqP2uEPswfECCVj2Kbr9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.03535353535354,"warning":null},{"id":"epoch-run-dQhoYvW3Wz2eZSZ89K6igd","modelId":"gemini-3.5-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gemini-3.5-flash_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash_low; run=dQhoYvW3Wz2eZSZ89K6igd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":45,"warning":null},{"id":"epoch-run-dszRh7ELyCEukWnwYnUxMp","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"deepseek-r1-0528-qwen3-8b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=deepseek-r1-0528-qwen3-8b; run=dszRh7ELyCEukWnwYnUxMp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":9.280303030303031,"warning":null},{"id":"epoch-run-dWG8tET6WnzXeT2WjcjWvT","modelId":"gemma-3-27b-it","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemma-3-27b-it","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-3-27b-it; run=dWG8tET6WnzXeT2WjcjWvT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-dWndu92zERWxzbpNa4BdJy","modelId":"qwen3.5-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-flash","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-flash; run=dWndu92zERWxzbpNa4BdJy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21,"warning":null},{"id":"epoch-run-dwyb2yzFewGT6w6oFdVMAc","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-32B","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=DeepSeek-R1-Distill-Qwen-32B; run=dwyb2yzFewGT6w6oFdVMAc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":64.14141414141415,"warning":null},{"id":"epoch-run-dYYtcwENFRtm9jZTDA2p9C","modelId":"gemini-3.5-flash","benchmarkId":"epoch-gpqa-diamond-1-0-9-choice","level":"high","sourceLabel":"gemini-3.5-flash_high","configuration":"Epoch AI Inspect; task 1.0.9; scorer choice; model=gemini-3.5-flash_high; run=dYYtcwENFRtm9jZTDA2p9C; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":92.8030303030303,"warning":null},{"id":"epoch-run-E28uZiJvrPgKtawbJpoZQ8","modelId":"claude-fable-5","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-fable-5_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-fable-5_max; run=E28uZiJvrPgKtawbJpoZQ8; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.01754385964912,"warning":null},{"id":"epoch-run-e8MXnAM8HMF8eEzYtYA7xv","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"medium","sourceLabel":"claude-sonnet-4-6_medium","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-sonnet-4-6_medium; run=e8MXnAM8HMF8eEzYtYA7xv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.33333333333334,"warning":null},{"id":"epoch-run-EatRQnSaUpUwKzdtjYnQHo","modelId":"gpt-5.5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"xhigh","sourceLabel":"gpt-5.5_xhigh","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.5_xhigh; run=EatRQnSaUpUwKzdtjYnQHo; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":56.00000000000001,"warning":null},{"id":"epoch-run-eB9e2mtd5nRwqdFyLEsz6k","modelId":"claude-opus-4-6","benchmarkId":"epoch-gpqa-diamond-1-0-4-choice","level":"thinking","sourceLabel":"claude-opus-4-6_64K (thinking 64k)","configuration":"Epoch AI Inspect; task 1.0.4; scorer choice; model=claude-opus-4-6_64K; run=eB9e2mtd5nRwqdFyLEsz6k; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.76262626262627,"warning":null},{"id":"epoch-run-ECdG3m8n5ABfWVZ55rPFmT","modelId":"glm-5.2","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"glm-5.2_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.2_none; run=ECdG3m8n5ABfWVZ55rPFmT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":42.45614035087719,"warning":null},{"id":"epoch-run-EceR3NeHzSxacdmAmfRxgT","modelId":"deepseek-r1-distill-qwen-14b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-14B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=DeepSeek-R1-Distill-Qwen-14B; run=EceR3NeHzSxacdmAmfRxgT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":50.55555555555556,"warning":null},{"id":"epoch-run-eCq63CuekohAswYftWXJVj","modelId":"kimi-k3","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"kimi-k3_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=kimi-k3_max; run=eCq63CuekohAswYftWXJVj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26,"warning":null},{"id":"epoch-run-EDFusDaaFkh5n2MqKNxMBD","modelId":"deepseek-v4-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"deepseek-v4-flash-0731_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=deepseek-v4-flash-0731_max; run=EDFusDaaFkh5n2MqKNxMBD; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.03535353535354,"warning":null},{"id":"epoch-run-EEGf5SDiF8jXB6NX7eR6Sa","modelId":"claude-fable-5-1","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-fable-5-1_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5-1_max; run=EEGf5SDiF8jXB6NX7eR6Sa; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47,"warning":null},{"id":"epoch-run-eiLEpRUvK48wUKDh4sYkzV","modelId":"claude-fable-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-5-model-extracted-exact-match","level":"max","sourceLabel":"claude-fable-5_max","configuration":"Epoch AI Inspect; task 1.1.5; scorer model_extracted_exact_match; model=claude-fable-5_max; run=eiLEpRUvK48wUKDh4sYkzV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":99.72222222222223,"warning":null},{"id":"epoch-run-eiTYduCDNq3HgwTg4ZhEw6","modelId":"gemini-3.5-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"gemini-3.5-flash_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.5-flash_low; run=eiTYduCDNq3HgwTg4ZhEw6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.88888888888889,"warning":null},{"id":"epoch-run-eJBzZyT5ohb8ieaJCum5rK","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"medium","sourceLabel":"claude-sonnet-4-6_medium","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-4-6_medium; run=eJBzZyT5ohb8ieaJCum5rK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":8,"warning":null},{"id":"epoch-run-eJvV6RezECZwh3b4ekg4pm","modelId":"seed-oss-36b-instruct","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"seed-oss-36b-instruct","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=seed-oss-36b-instruct; run=eJvV6RezECZwh3b4ekg4pm; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":67.5,"warning":null},{"id":"epoch-run-EnbN27oUrNyfbxuPwtZey2","modelId":"gpt-5.5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-5.5_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.5_low; run=EnbN27oUrNyfbxuPwtZey2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26,"warning":null},{"id":"epoch-run-ENc5ZM5TpBYNKkTWN4xyQM","modelId":"kimi-k2.7-code","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"kimi-k2.7-code","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k2.7-code; run=ENc5ZM5TpBYNKkTWN4xyQM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.55555555555556,"warning":null},{"id":"epoch-run-ENh7ZPQj7ihBePjsC8a7HV","modelId":"qwen3.7-max","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.7-max_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.7-max_none; run=ENh7ZPQj7ihBePjsC8a7HV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26,"warning":null},{"id":"epoch-run-enhRcQmfN6RFB2zu7R3Uxr","modelId":"gpt-3.5-turbo-1106","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"gpt-3.5-turbo-1106","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=gpt-3.5-turbo-1106; run=enhRcQmfN6RFB2zu7R3Uxr; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.030303030303028,"warning":null},{"id":"epoch-run-Eo5cAQJK28CHpKDfCSDYG4","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-30b-a3b-instruct-2507","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-30b-a3b-instruct-2507; run=Eo5cAQJK28CHpKDfCSDYG4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":62.22222222222222,"warning":null},{"id":"epoch-run-EoSFpgFhJB7iDPLcMNuLH4","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemini-3.1-flash-lite_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.1-flash-lite_minimal; run=EoSFpgFhJB7iDPLcMNuLH4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":37.77777777777778,"warning":null},{"id":"epoch-run-Epg7eNLwwGPXtX3sSAwPf8","modelId":"gpt-5.6-luna","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"gpt-5.6-luna_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-luna_max; run=Epg7eNLwwGPXtX3sSAwPf8; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21,"warning":null},{"id":"epoch-run-ESnXA8LqMqhjcsoWQaMLVQ","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-1.5B","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=DeepSeek-R1-Distill-Qwen-1.5B; run=ESnXA8LqMqhjcsoWQaMLVQ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":33.58585858585859,"warning":null},{"id":"epoch-run-EtgrDq6ei6kZe8K7QbXUe3","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"gemini-3-flash-preview","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3-flash-preview; run=EtgrDq6ei6kZe8K7QbXUe3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":51.2280701754386,"warning":null},{"id":"epoch-run-EUknGXXh3f2mHtv3dTufLg","modelId":"claude-opus-4-6","benchmarkId":"epoch-chess-puzzles-1-0-2-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-opus-4-6_120K (thinking 120k)","configuration":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match; model=claude-opus-4-6_120K; run=EUknGXXh3f2mHtv3dTufLg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":13,"warning":null},{"id":"epoch-run-eVKA2eavdRAbSN6AnzyBxA","modelId":"kimi-k2.6","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"kimi-k2.6","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k2.6; run=eVKA2eavdRAbSN6AnzyBxA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25.64102564102564,"warning":null},{"id":"epoch-run-EWAyxFsRUvuu4NpmmLqWkn","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.6-35b-a3b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.6-35b-a3b; run=EWAyxFsRUvuu4NpmmLqWkn; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.83838383838383,"warning":null},{"id":"epoch-run-EXpHB6kFqDjRfG9A5LsDf6","modelId":"qwen3-32b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"Qwen3-32B_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=Qwen3-32B_none; run=EXpHB6kFqDjRfG9A5LsDf6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":54.10353535353535,"warning":null},{"id":"epoch-run-eXVWr3RBeSsWy5DAU8ed46","modelId":"gemini-3.1-pro","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"gemini-3.1-pro-preview","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.1-pro-preview; run=eXVWr3RBeSsWy5DAU8ed46; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26.82926829268293,"warning":null},{"id":"epoch-run-ExyL3GN8s34tizrXV3VmS3","modelId":"claude-fable-5-1","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"claude-fable-5-1_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-fable-5-1_max; run=ExyL3GN8s34tizrXV3VmS3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":70.8,"warning":null},{"id":"epoch-run-EyKecrMhk7Yx25e5HGW43i","modelId":"deepseek-v4-pro","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"deepseek-v4-pro-0813_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=deepseek-v4-pro-0813_max; run=EyKecrMhk7Yx25e5HGW43i; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47,"warning":null},{"id":"epoch-run-eYmgjYJfM7Utm46nfoRfZ6","modelId":"gemini-3.5-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-4-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.5-flash_high","configuration":"Epoch AI Inspect; task 1.1.4; scorer model_extracted_exact_match; model=gemini-3.5-flash_high; run=eYmgjYJfM7Utm46nfoRfZ6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.55555555555556,"warning":null},{"id":"epoch-run-EzMaDdXs4YQTMLgppBGxAb","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.5-397b-a17b","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.5-397b-a17b; run=EzMaDdXs4YQTMLgppBGxAb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":29.47368421052631,"warning":null},{"id":"epoch-run-F3CtjUceBrMi9iYmjULx7J","modelId":"qwen3-1.7b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3-1.7b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-1.7b; run=F3CtjUceBrMi9iYmjULx7J; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":38.005050505050505,"warning":null},{"id":"epoch-run-f46NQY9jSxyKqo9qzrmk6F","modelId":"gpt-6-astra","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"high","sourceLabel":"gpt-6-astra_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-6-astra_high; run=f46NQY9jSxyKqo9qzrmk6F; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.6,"warning":null},{"id":"epoch-run-f6pnAATjxmrFJS353EjQKi","modelId":"deepseek-r1-distill-llama-70b","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Llama-70B","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=DeepSeek-R1-Distill-Llama-70B; run=f6pnAATjxmrFJS353EjQKi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":55.744949494949495,"warning":null},{"id":"epoch-run-f6ZdMtRpdfskGbrBCzrKSn","modelId":"qwen3.6-plus","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.6-plus","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.6-plus; run=f6ZdMtRpdfskGbrBCzrKSn; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.38383838383838,"warning":null},{"id":"epoch-run-f7BCT27LzcAtaLDP2tcrWF","modelId":"gpt-6-astra","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"gpt-6-astra_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-6-astra_max; run=f7BCT27LzcAtaLDP2tcrWF; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.6,"warning":null},{"id":"epoch-run-f7dotY9NheKNKK2zz6bfKZ","modelId":"qwen3.7-max","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"qwen3.7-max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.7-max; run=f7dotY9NheKNKK2zz6bfKZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":32,"warning":null},{"id":"epoch-run-F7v3JtKFb27j2YVmsndLM5","modelId":"gpt-5.6-terra","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"none","sourceLabel":"gpt-5.6-terra_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-terra_none; run=F7v3JtKFb27j2YVmsndLM5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":77.27272727272727,"warning":null},{"id":"epoch-run-F83pa7Gfsb4UNVttTnS5Hk","modelId":"gemini-3.6-flash","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"high","sourceLabel":"gemini-3.6-flash_high","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gemini-3.6-flash_high; run=F83pa7Gfsb4UNVttTnS5Hk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.2,"warning":null},{"id":"epoch-run-f8Pac6hqib4t7x2s4HCRoT","modelId":"grok-4.5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"grok-4.5_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.5_high; run=f8Pac6hqib4t7x2s4HCRoT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.77777777777777,"warning":null},{"id":"epoch-run-FA7pM9hKdkgTXmGHptcno7","modelId":"gpt-6-astra","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"gpt-6-astra_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-6-astra_max; run=FA7pM9hKdkgTXmGHptcno7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84,"warning":null},{"id":"epoch-run-ff7GeS7rdperjxSBZ7MHZY","modelId":"claude-opus-5","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-opus-5_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-5_max; run=ff7GeS7rdperjxSBZ7MHZY; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.6140350877193,"warning":null},{"id":"epoch-run-FF8iU7vP5ecg6PdvDyE7XG","modelId":"claude-opus-4-6","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-opus-4-6_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-6_max; run=FF8iU7vP5ecg6PdvDyE7XG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":14.000000000000002,"warning":null},{"id":"epoch-run-FfAvNS5H9bMDSBF4JNNiDz","modelId":"claude-opus-5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"claude-opus-5_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-opus-5_max; run=FfAvNS5H9bMDSBF4JNNiDz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":59,"warning":null},{"id":"epoch-run-Ffoxqm7YsZr3FimCGsGAJv","modelId":"qwen3-32b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"Qwen3-32B","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=Qwen3-32B; run=Ffoxqm7YsZr3FimCGsGAJv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":65.71969696969697,"warning":null},{"id":"epoch-run-FGEsLTxzZ7fE9aq7DhdqZb","modelId":"llama-3.2-1b-instruct","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"Llama-3.2-1B-Instruct","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=Llama-3.2-1B-Instruct; run=FGEsLTxzZ7fE9aq7DhdqZb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":23.92676767676768,"warning":null},{"id":"epoch-run-FHZCKbtfvpKGXU99vZFnXN","modelId":"qwen3.7-max","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.7-max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.7-max; run=FHZCKbtfvpKGXU99vZFnXN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34.146341463414636,"warning":null},{"id":"epoch-run-fjgo9DvKNgVAGtitPvgpY7","modelId":"gpt-oss-20b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gpt-oss-20b_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-oss-20b_high; run=fjgo9DvKNgVAGtitPvgpY7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-fJKhFRm5dn9wzbXojee7uj","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"minimal","sourceLabel":"gemini-3.5-flash-lite_minimal","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3.5-flash-lite_minimal; run=fJKhFRm5dn9wzbXojee7uj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-FkywQ2KS4AkLPzjSPmhHcS","modelId":"gemini-2.5-pro","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"gemini-2.5-pro","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-2.5-pro; run=FkywQ2KS4AkLPzjSPmhHcS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":24.561403508771928,"warning":null},{"id":"epoch-run-FLDt53waLTeshC7PK9uVy2","modelId":"grok-4.20-0309-reasoning","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"grok-4.20-0309-reasoning","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=grok-4.20-0309-reasoning; run=FLDt53waLTeshC7PK9uVy2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":44.91228070175438,"warning":null},{"id":"epoch-run-FNMbfvEEm9PRnrJnrqk2PH","modelId":"mistral-medium-2505","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"mistral-medium-2505","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=mistral-medium-2505; run=FNMbfvEEm9PRnrJnrqk2PH; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":59.53282828282829,"warning":null},{"id":"epoch-run-FNMFJuzKKuNsWx9gQoLerW","modelId":"llama-3.2-1b-instruct","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Llama-3.2-1B-Instruct","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Llama-3.2-1B-Instruct; run=FNMFJuzKKuNsWx9gQoLerW; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-FNXAt76ZUS3sWhQDFMga7U","modelId":"claude-sonnet-5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"claude-sonnet-5_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-sonnet-5_max; run=FNXAt76ZUS3sWhQDFMga7U; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80.3030303030303,"warning":null},{"id":"epoch-run-FoMSS4FmH3VxpsvZiUJPCv","modelId":"qwen3.6-flash","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"qwen3.6-flash","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=qwen3.6-flash; run=FoMSS4FmH3VxpsvZiUJPCv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":15.915915915915916,"warning":null},{"id":"epoch-run-fPE4Zajhq5WfccSxEYXXR7","modelId":"glm-4.7-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"glm-4.7-flash_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-4.7-flash_none; run=fPE4Zajhq5WfccSxEYXXR7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25,"warning":null},{"id":"epoch-run-FQ3Suh2vKacz7UNqJybTWk","modelId":"deepseek-v4-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"deepseek-v4-flash-0731_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=deepseek-v4-flash-0731_max; run=FQ3Suh2vKacz7UNqJybTWk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.44444444444444,"warning":null},{"id":"epoch-run-fQjoHKyUEPAuwdrBGfL8SG","modelId":"gemma-2-9b-it","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"gemma-2-9b-it","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=gemma-2-9b-it; run=fQjoHKyUEPAuwdrBGfL8SG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":27.46212121212121,"warning":null},{"id":"epoch-run-frszScNxpHXXjSHawCt9Zb","modelId":"kimi-k3","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"kimi-k3_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k3_low; run=frszScNxpHXXjSHawCt9Zb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":68.88888888888889,"warning":null},{"id":"epoch-run-fsZmzw8jjyUgMQGwxodBwN","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"claude-sonnet-4-5-20250929","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=claude-sonnet-4-5-20250929; run=fsZmzw8jjyUgMQGwxodBwN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":73.73737373737373,"warning":null},{"id":"epoch-run-fubPj2m5aKLCeXZAwb3xeD","modelId":"phi-4","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"phi-4","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=phi-4; run=fubPj2m5aKLCeXZAwb3xeD; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1,"warning":null},{"id":"epoch-run-FUE7jUup3RsXiXpYTjMKb5","modelId":"glm-5.2","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"glm-5.2_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_low; run=FUE7jUup3RsXiXpYTjMKb5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":14.000000000000002,"warning":null},{"id":"epoch-run-fxwRTtt8bLV4DNutwtMEox","modelId":"llama-3.1-8b-instruct","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"Llama-3.1-8B-Instruct","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=Llama-3.1-8B-Instruct; run=fxwRTtt8bLV4DNutwtMEox; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26.957070707070706,"warning":null},{"id":"epoch-run-fzoUFmy77NpEDtXyA6w6ap","modelId":"grok-4.3","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"grok-4.3_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.3_high; run=fzoUFmy77NpEDtXyA6w6ap; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.33333333333333,"warning":null},{"id":"epoch-run-G3dinPvwrci2Nu3m9pby2i","modelId":"qwen3-4b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3-4b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-4b; run=G3dinPvwrci2Nu3m9pby2i; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":52.33585858585859,"warning":null},{"id":"epoch-run-g4bbCaiFDqw2YYNDAcmn2a","modelId":"gemini-3.1-pro","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"high","sourceLabel":"gemini-3.1-pro-preview_high","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gemini-3.1-pro-preview_high; run=g4bbCaiFDqw2YYNDAcmn2a; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34,"warning":null},{"id":"epoch-run-g4iGoqwjeF5vqkdvtyytx5","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.6-35b-a3b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-35b-a3b_none; run=g4iGoqwjeF5vqkdvtyytx5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4,"warning":null},{"id":"epoch-run-g64kPFtWB7Adto8Y8Hi3XE","modelId":"qwen3.6-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.6-flash","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-flash; run=g64kPFtWB7Adto8Y8Hi3XE; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-g7czyLHudHegzP9yRD939X","modelId":"gpt-5.6-sol","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"none","sourceLabel":"gpt-5.6-sol_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-sol_none; run=g7czyLHudHegzP9yRD939X; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":68.88888888888889,"warning":null},{"id":"epoch-run-g7dXwZH2tWvqLg3X5idGs2","modelId":"claude-fable-5-1","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-fable-5-1_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-fable-5-1_max; run=g7dXwZH2tWvqLg3X5idGs2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.17543859649123,"warning":null},{"id":"epoch-run-G8hwpomZQaMniWH5XUzTRe","modelId":"glm-5.2","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"glm-5.2_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_max; run=G8hwpomZQaMniWH5XUzTRe; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21,"warning":null},{"id":"epoch-run-GbQrTQyihBUsb9sxbqT8pT","modelId":"gpt-oss-120b","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"high","sourceLabel":"gpt-oss-120b_high","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-oss-120b_high; run=GbQrTQyihBUsb9sxbqT8pT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-GdfzaHmiZht2DKPZDtQAET","modelId":"qwen3-1.7b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3-1.7b_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-1.7b_none; run=GdfzaHmiZht2DKPZDtQAET; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":30.61868686868687,"warning":null},{"id":"epoch-run-GEaAdb9UmoUFbEtBx7WzAR","modelId":"claude-haiku-4-5-20251001","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"thinking","sourceLabel":"claude-haiku-4-5-20251001_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=claude-haiku-4-5-20251001_32K; run=GEaAdb9UmoUFbEtBx7WzAR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":71.21212121212122,"warning":null},{"id":"epoch-run-GEwyLqZT93Hp55fdtHrJhm","modelId":"gpt-oss-20b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"medium","sourceLabel":"gpt-oss-20b_medium","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-oss-20b_medium; run=GEwyLqZT93Hp55fdtHrJhm; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":60.79545454545454,"warning":null},{"id":"epoch-run-gG2B6fLUDBy5jRraxL2pz8","modelId":"qwen3-8b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-8b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-8b; run=gG2B6fLUDBy5jRraxL2pz8; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":56.111111111111114,"warning":null},{"id":"epoch-run-ggG3n6WVPZn7Gu2RNyfQbK","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.6-35b-a3b","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-35b-a3b; run=ggG3n6WVPZn7Gu2RNyfQbK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17.543859649122805,"warning":null},{"id":"epoch-run-GGpgwGRFVATVJdQr8TgRc9","modelId":"minimax-m3","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"MiniMax-M3","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=MiniMax-M3; run=GGpgwGRFVATVJdQr8TgRc9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":7.000000000000001,"warning":null},{"id":"epoch-run-GJ6YsSuzyRD9YXe6SBwvsu","modelId":"gemini-3.5-flash","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"high","sourceLabel":"gemini-3.5-flash_high","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gemini-3.5-flash_high; run=GJ6YsSuzyRD9YXe6SBwvsu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.2,"warning":null},{"id":"epoch-run-GL7htq7XRnbzqpAVK5f862","modelId":"glm-4.7-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"glm-4.7-flash","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-4.7-flash; run=GL7htq7XRnbzqpAVK5f862; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":60.542929292929294,"warning":null},{"id":"epoch-run-GMngscbSmqoPbGZWNv2Jvw","modelId":"gpt-oss-20b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gpt-oss-20b_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-oss-20b_high; run=GMngscbSmqoPbGZWNv2Jvw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":50.83333333333333,"warning":null},{"id":"epoch-run-goZR5yGxZic9TZ23ezCL3w","modelId":"glm-5.3","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"glm-5.3_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.3_max; run=goZR5yGxZic9TZ23ezCL3w; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.11111111111111,"warning":null},{"id":"epoch-run-GQKsxFbdBWB546zE8ci49f","modelId":"gemini-3.5-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"high","sourceLabel":"gemini-3.5-flash_high","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gemini-3.5-flash_high; run=GQKsxFbdBWB546zE8ci49f; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":32,"warning":null},{"id":"epoch-run-GRQV9Q8gHoHnSEPWofiQuq","modelId":"qwen3-14b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3-14b_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-14b_none; run=GRQV9Q8gHoHnSEPWofiQuq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":53.40909090909091,"warning":null},{"id":"epoch-run-gRRQHECkYhz5UaYsRKDh2F","modelId":"qwen3-14b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-14b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-14b; run=gRRQHECkYhz5UaYsRKDh2F; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.38888888888889,"warning":null},{"id":"epoch-run-Gs234P3jzGiLm68KjyzYZL","modelId":"deepseek-r1-distill-qwen-1.5b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-1.5B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=DeepSeek-R1-Distill-Qwen-1.5B; run=Gs234P3jzGiLm68KjyzYZL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21.38888888888889,"warning":null},{"id":"epoch-run-gsBidnvEcmCfLnn5sxePtk","modelId":"claude-opus-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"claude-opus-5","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-5; run=gsBidnvEcmCfLnn5sxePtk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.77777777777777,"warning":null},{"id":"epoch-run-GSde7u2Mb6GZGpubJjjPam","modelId":"glm-4.7-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"glm-4.7-flash_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-4.7-flash_none; run=GSde7u2Mb6GZGpubJjjPam; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":45.13888888888889,"warning":null},{"id":"epoch-run-GThtce6GAmRAS8srQyGQoA","modelId":"claude-opus-4-8","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"claude-opus-4-8_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-opus-4-8_low; run=GThtce6GAmRAS8srQyGQoA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.38383838383838,"warning":null},{"id":"epoch-run-gu39ndv9QxWP3NRxSUJRaX","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"epoch-gpqa-diamond-1-0-3-choice","level":"unspecified","sourceLabel":"Qwen3-235B-A22B-Thinking-2507","configuration":"Epoch AI Inspect; task 1.0.3; scorer choice; model=Qwen3-235B-A22B-Thinking-2507; run=gu39ndv9QxWP3NRxSUJRaX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80.05050505050505,"warning":null},{"id":"epoch-run-gVdraDT3pXmaExP9VbqME4","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"gemini-3-flash-preview_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3-flash-preview_high; run=gVdraDT3pXmaExP9VbqME4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":89.39393939393939,"warning":null},{"id":"epoch-run-GVm7khGvtdnQKGfkgAHD8q","modelId":"grok-4.20-0309-reasoning","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"grok-4.20-0309-reasoning","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=grok-4.20-0309-reasoning; run=GVm7khGvtdnQKGfkgAHD8q; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":30.2,"warning":null},{"id":"epoch-run-GVmgtgKMwEqc54f3jA7auP","modelId":"claude-opus-4-8","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-opus-4-8_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-4-8_max; run=GVmgtgKMwEqc54f3jA7auP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80,"warning":null},{"id":"epoch-run-GYzmrzMfeSjNjm2J6L9PeT","modelId":"glm-4.7","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-4-model-extracted-exact-match","level":"unspecified","sourceLabel":"glm-4.7","configuration":"Epoch AI Inspect; task 1.0.4; scorer model_extracted_exact_match; model=glm-4.7; run=GYzmrzMfeSjNjm2J6L9PeT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.33333333333334,"warning":null},{"id":"epoch-run-gZ4bwozTKtpmZTqnqX3a33","modelId":"gemini-3.8-flash","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"high","sourceLabel":"gemini-3.8-flash_high","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gemini-3.8-flash_high; run=gZ4bwozTKtpmZTqnqX3a33; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":69.69999999999999,"warning":null},{"id":"epoch-run-gZERSAQwxBAevQzBsWfUie","modelId":"kimi-k3","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"kimi-k3_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k3_max; run=gZERSAQwxBAevQzBsWfUie; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":39.02439024390244,"warning":null},{"id":"epoch-run-gZMFRbVKnBmcnZU4YqqKMN","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.5-397b-a17b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.5-397b-a17b; run=gZMFRbVKnBmcnZU4YqqKMN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.85858585858585,"warning":null},{"id":"epoch-run-H2FvRXagQRQmiNa7WrNMU2","modelId":"qwen3.6-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.6-flash","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.6-flash; run=H2FvRXagQRQmiNa7WrNMU2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.33333333333334,"warning":null},{"id":"epoch-run-H3E7EjjXfGCPnm9ooLdmAo","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-3-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemini-3-flash-preview","configuration":"Epoch AI Inspect; task 1.0.3; scorer model_extracted_exact_match; model=gemini-3-flash-preview; run=H3E7EjjXfGCPnm9ooLdmAo; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":92.77777777777779,"warning":null},{"id":"epoch-run-h9aoDxyWEhybvARHpyuoco","modelId":"qwen3.5-35b-a3b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.5-35b-a3b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-35b-a3b_none; run=h9aoDxyWEhybvARHpyuoco; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":70,"warning":null},{"id":"epoch-run-hDESmyGFrbZDomjff3rqzD","modelId":"minimax-m3","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"MiniMax-M3","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=MiniMax-M3; run=hDESmyGFrbZDomjff3rqzD; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.9090909090909,"warning":null},{"id":"epoch-run-hFRxCUnXRNMcpQzUy8GYL5","modelId":"qwen3.7-plus","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.7-plus","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-plus; run=hFRxCUnXRNMcpQzUy8GYL5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":24,"warning":null},{"id":"epoch-run-HhiYxEx3Bf8YDPUh34K4DC","modelId":"claude-sonnet-5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"xhigh","sourceLabel":"claude-sonnet-5_xhigh","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-sonnet-5_xhigh; run=HhiYxEx3Bf8YDPUh34K4DC; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.53030303030303,"warning":null},{"id":"epoch-run-hHnQVatVTbQjM4sfrjw7GH","modelId":"kimi-k2.6","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"unspecified","sourceLabel":"kimi-k2.6","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=kimi-k2.6; run=hHnQVatVTbQjM4sfrjw7GH; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34.9,"warning":null},{"id":"epoch-run-hL24cexf97QKVLsv73H5TT","modelId":"gemini-3.6-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemini-3.6-flash_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.6-flash_minimal; run=hL24cexf97QKVLsv73H5TT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":35,"warning":null},{"id":"epoch-run-hnP6Z88x8bPEBRZ2PW6kps","modelId":"grok-4.6","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"grok-4.6_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=grok-4.6_high; run=hnP6Z88x8bPEBRZ2PW6kps; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.00252525252525,"warning":null},{"id":"epoch-run-hrRSYo5XSFrcs9fADb5Hox","modelId":"claude-opus-4-7","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-opus-4-7_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-7_max; run=hrRSYo5XSFrcs9fADb5Hox; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":7.000000000000001,"warning":null},{"id":"epoch-run-hVifTUdQZrFEYabgCRu8Qq","modelId":"gemini-3.1-pro","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"gemini-3.1-pro-preview","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.1-pro-preview; run=hVifTUdQZrFEYabgCRu8Qq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":59.64912280701754,"warning":null},{"id":"epoch-run-HVtbACyemDaTPW5XUDC6Jf","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3-flash-preview_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3-flash-preview_high; run=HVtbACyemDaTPW5XUDC6Jf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":40,"warning":null},{"id":"epoch-run-hwrnvtEbDAocFtjcsHqsQh","modelId":"claude-fable-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"claude-fable-5_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5_high; run=hwrnvtEbDAocFtjcsHqsQh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":100,"warning":null},{"id":"epoch-run-hYATFPeUnMq7Std2nLUVAJ","modelId":"gpt-oss-20b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"gpt-oss-20b_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-oss-20b_high; run=hYATFPeUnMq7Std2nLUVAJ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":45.95959595959596,"warning":null},{"id":"epoch-run-hYeysTWbJLkxwBrENz3Kie","modelId":"gemini-3.5-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemini-3.5-flash_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash_minimal; run=hYeysTWbJLkxwBrENz3Kie; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":43,"warning":null},{"id":"epoch-run-i2ZUgMREKiFAnE2M54w3Py","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.5-397b-a17b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-397b-a17b_none; run=i2ZUgMREKiFAnE2M54w3Py; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.22222222222221,"warning":null},{"id":"epoch-run-i62SEaSpi6GbBmWqEDSDmV","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gemini-3.5-flash-lite_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash-lite_low; run=i62SEaSpi6GbBmWqEDSDmV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":18,"warning":null},{"id":"epoch-run-i6i3gQf3ng2aAipvowPpws","modelId":"qwen3.7-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.7-flash","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.7-flash; run=i6i3gQf3ng2aAipvowPpws; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.32323232323232,"warning":null},{"id":"epoch-run-i7MVHsH5pikQKjYn6LBqHS","modelId":"qwen3.7-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.7-flash_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.7-flash_none; run=i7MVHsH5pikQKjYn6LBqHS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":14.000000000000002,"warning":null},{"id":"epoch-run-i8CTho47u9qDcnXF3psREo","modelId":"qwen3.5-9b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.5-9B_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-9B_none; run=i8CTho47u9qDcnXF3psREo; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-iCysWvFJevNyw2dbYosU6J","modelId":"glm-5.3-flash","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"glm-5.3-flash_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.3-flash_max; run=iCysWvFJevNyw2dbYosU6J; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17.073170731707318,"warning":null},{"id":"epoch-run-iE9NNTJWbGpRia2fUVGkPf","modelId":"gpt-5.6-terra","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"low","sourceLabel":"gpt-5.6-terra_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-terra_low; run=iE9NNTJWbGpRia2fUVGkPf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":19,"warning":null},{"id":"epoch-run-ig7gQ23WRms9SQLLNPtbTi","modelId":"gemini-3.5-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gemini-3.5-flash_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash_low; run=ig7gQ23WRms9SQLLNPtbTi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.88888888888889,"warning":null},{"id":"epoch-run-ii6JE9j57eSbuswEsJArTa","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=claude-sonnet-4-5-20250929_32K; run=ii6JE9j57eSbuswEsJArTa; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":81.7258883248731,"warning":null},{"id":"epoch-run-ikUWdu6HJ2qRgZynfzDCFe","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-2-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match; model=claude-opus-4-5-20251101_32K; run=ikUWdu6HJ2qRgZynfzDCFe; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.11111111111111,"warning":null},{"id":"epoch-run-imPXZhfTfq9Q9G2kq3stdg","modelId":"gemini-3.5-flash","benchmarkId":"epoch-chess-puzzles-1-1-4-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.5-flash_high","configuration":"Epoch AI Inspect; task 1.1.4; scorer model_extracted_exact_match; model=gemini-3.5-flash_high; run=imPXZhfTfq9Q9G2kq3stdg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":50,"warning":null},{"id":"epoch-run-iTY94tKhVEcZsUZivMwLJa","modelId":"gpt-5.6-luna","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"low","sourceLabel":"gpt-5.6-luna_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-luna_low; run=iTY94tKhVEcZsUZivMwLJa; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17,"warning":null},{"id":"epoch-run-ivr2LfmdZoCMfLME7jh2L8","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemini-3.5-flash-lite_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash-lite_minimal; run=ivr2LfmdZoCMfLME7jh2L8; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":51.11111111111111,"warning":null},{"id":"epoch-run-iXvqUzwxAiA3Rg3dwnutFs","modelId":"glm-5.3","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"glm-5.3_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.3_max; run=iXvqUzwxAiA3Rg3dwnutFs; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":68.77192982456141,"warning":null},{"id":"epoch-run-J2kUEjR9r6Spd594qDNTTf","modelId":"claude-haiku-4-5-20251001","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"unspecified","sourceLabel":"claude-haiku-4-5-20251001","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=claude-haiku-4-5-20251001; run=J2kUEjR9r6Spd594qDNTTf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":13.200000000000001,"warning":null},{"id":"epoch-run-J6evjTMgHkrun8txnEvzdN","modelId":"gpt-5.6-terra","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"gpt-5.6-terra_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.6-terra_max; run=J6evjTMgHkrun8txnEvzdN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.96491228070175,"warning":null},{"id":"epoch-run-J8hYKbXiGhetQRwu5bUSp6","modelId":"glm-5.2","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"glm-5.2_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_none; run=J8hYKbXiGhetQRwu5bUSp6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.888888888888886,"warning":null},{"id":"epoch-run-JarZHkwUMZ6HuA4ArMNT45","modelId":"claude-opus-4-6","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"low","sourceLabel":"claude-opus-4-6_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=claude-opus-4-6_low; run=JarZHkwUMZ6HuA4ArMNT45; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":7.000000000000001,"warning":null},{"id":"epoch-run-jbyVWnEvvFVNNc8AEF6WcQ","modelId":"qwen3.6-plus","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.6-plus","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-plus; run=jbyVWnEvvFVNNc8AEF6WcQ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":38.24561403508772,"warning":null},{"id":"epoch-run-JcgBDysccQrAnWQaUmoehs","modelId":"qwen3-4b-instruct-2507","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-4b-instruct-2507","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-4b-instruct-2507; run=JcgBDysccQrAnWQaUmoehs; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4,"warning":null},{"id":"epoch-run-JCMjXU6FRiiLV3xvs9R2Xv","modelId":"gemini-3.6-flash","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.6-flash_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.6-flash_high; run=JCMjXU6FRiiLV3xvs9R2Xv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21.951219512195124,"warning":null},{"id":"epoch-run-JcQMgXdZKU54u52B8TGQKp","modelId":"claude-opus-4-6","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"claude-opus-4-6_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-opus-4-6_max; run=JcQMgXdZKU54u52B8TGQKp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.38383838383838,"warning":null},{"id":"epoch-run-JcuoAWhcnngPEZBPmiUyLF","modelId":"gpt-5.6-terra","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"gpt-5.6-terra_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-terra_low; run=JcuoAWhcnngPEZBPmiUyLF; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.37373737373737,"warning":null},{"id":"epoch-run-JCwFm63cUipLHBfM6BdssQ","modelId":"qwen3-30b-a3b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Qwen3-30B-A3B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Qwen3-30B-A3B; run=JCwFm63cUipLHBfM6BdssQ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4,"warning":null},{"id":"epoch-run-jD6rJdvfNPErKEz9qkpssj","modelId":"gemma-2-27b-it","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"gemma-2-27b-it","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=gemma-2-27b-it; run=jD6rJdvfNPErKEz9qkpssj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1.3888888888888888,"warning":null},{"id":"epoch-run-jdFH2zZdssYKDVJQPKXvNB","modelId":"gemma-3-27b-it","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"gemma-3-27b-it","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemma-3-27b-it; run=jdFH2zZdssYKDVJQPKXvNB; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47.72727272727273,"warning":null},{"id":"epoch-run-JebA8dYLVov6H49ZQSLXh5","modelId":"glm-5.2","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"glm-5.2_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.2_max; run=JebA8dYLVov6H49ZQSLXh5; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":29.268292682926827,"warning":null},{"id":"epoch-run-jFJucVunfLgoQqoFvPVQWP","modelId":"gemma-4-31b-it","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemma-4-31b-it_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-4-31b-it_minimal; run=jFJucVunfLgoQqoFvPVQWP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":73.33333333333333,"warning":null},{"id":"epoch-run-JfkPdo29um2NkxdhT79AK2","modelId":"qwen3.7-max","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.7-max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-max; run=JfkPdo29um2NkxdhT79AK2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":19,"warning":null},{"id":"epoch-run-jGgkDRHbodcaTzQ3Mp6SxS","modelId":"qwen3.6-plus","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.6-plus_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.6-plus_none; run=jGgkDRHbodcaTzQ3Mp6SxS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-ji3kMn49Jcr9t4whxcpjj4","modelId":"claude-opus-5","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-opus-5_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-5_max; run=ji3kMn49Jcr9t4whxcpjj4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":73.17073170731707,"warning":null},{"id":"epoch-run-JiqgqBTfkGx797uowZgJbk","modelId":"claude-opus-4-8","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-opus-4-8_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-4-8_max; run=JiqgqBTfkGx797uowZgJbk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":56.09756097560976,"warning":null},{"id":"epoch-run-JoraLb9y55QXpMg4Rrmr5x","modelId":"gemini-3.6-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"gemini-3.6-flash_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.6-flash_low; run=JoraLb9y55QXpMg4Rrmr5x; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.36363636363636,"warning":null},{"id":"epoch-run-jrawnM2wHFbVfJFJsap4kS","modelId":"qwen3.5-plus","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"qwen3.5-plus","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=qwen3.5-plus; run=jrawnM2wHFbVfJFJsap4kS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25.35070140280561,"warning":null},{"id":"epoch-run-jRiWmBxtBAyiXiRBRMY8wX","modelId":"qwen3-8b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3-8b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-8b; run=jRiWmBxtBAyiXiRBRMY8wX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":56.755050505050505,"warning":null},{"id":"epoch-run-jtfdCURnwfZzak4BSiBKzx","modelId":"grok-4.6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"grok-4.6_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.6_high; run=jtfdCURnwfZzak4BSiBKzx; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.77777777777777,"warning":null},{"id":"epoch-run-Ju7pUkkwYVj6ugi9Ri5Jjp","modelId":"claude-opus-4-7","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"claude-opus-4-7_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-opus-4-7_max; run=Ju7pUkkwYVj6ugi9Ri5Jjp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.36363636363636,"warning":null},{"id":"epoch-run-JuM7FArkmhLqqKBqudySsC","modelId":"gemini-3.5-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemini-3.5-flash_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash_minimal; run=JuM7FArkmhLqqKBqudySsC; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80,"warning":null},{"id":"epoch-run-jUmmCNezoW7jWiK72SVCaP","modelId":"gpt-5.6-terra","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"gpt-5.6-terra_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-terra_max; run=jUmmCNezoW7jWiK72SVCaP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":99.72222222222223,"warning":null},{"id":"epoch-run-juNVfKBcYTwaKnk9GRA2zL","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.5-flash-lite_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.5-flash-lite_high; run=juNVfKBcYTwaKnk9GRA2zL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-Jvdw6GAXiS6T79bkpbk6Ra","modelId":"qwen3.7-plus","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.7-plus","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-plus; run=Jvdw6GAXiS6T79bkpbk6Ra; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.33333333333333,"warning":null},{"id":"epoch-run-Jvt5BNr4ERbE9QGgMcEbmT","modelId":"glm-5.3-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"glm-5.3-flash_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.3-flash_max; run=Jvt5BNr4ERbE9QGgMcEbmT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.15151515151516,"warning":null},{"id":"epoch-run-jWHk7BTYHQRXk2rXCbnpcS","modelId":"minimax-m3","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"MiniMax-M3_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=MiniMax-M3_none; run=jWHk7BTYHQRXk2rXCbnpcS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":8,"warning":null},{"id":"epoch-run-jyCZnpXG2bh9G43X8pT75m","modelId":"claude-opus-4-7","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-2-model-extracted-exact-match","level":"xhigh","sourceLabel":"claude-opus-4-7_xhigh","configuration":"Epoch AI Inspect; task 1.1.2; scorer model_extracted_exact_match; model=claude-opus-4-7_xhigh; run=jyCZnpXG2bh9G43X8pT75m; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.8,"warning":"Run-specific qualification requires review: All incorrect answers were actually cases of the model failing to submit an answer. For each sample, we average the score of the epochs that did complete for that sample. If none completed, we assign a score of 0. Then we average these scores across all samples. The resulting score is 44/45."},{"id":"epoch-run-jYiGAFfUQKJuRStPzU3PX3","modelId":"qwen3.6-plus","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.6-plus","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-plus; run=jYiGAFfUQKJuRStPzU3PX3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.33333333333333,"warning":null},{"id":"epoch-run-JYuFdyZZSiMvmSZNzMTywb","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-397b-a17b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-397b-a17b; run=JYuFdyZZSiMvmSZNzMTywb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.88888888888889,"warning":null},{"id":"epoch-run-jyWVTGV3ZXhotEFLLGQsKi","modelId":"minimax-m3","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"MiniMax-M3_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=MiniMax-M3_none; run=jyWVTGV3ZXhotEFLLGQsKi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4,"warning":null},{"id":"epoch-run-JzDofpJXt6d4f5kbRMSEmw","modelId":"gpt-5.6-terra","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-5.6-terra_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-terra_low; run=JzDofpJXt6d4f5kbRMSEmw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22,"warning":null},{"id":"epoch-run-jzqDbWHvQXhMkpYHfTjnRE","modelId":"qwen3.5-35b-a3b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.5-35b-a3b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-35b-a3b_none; run=jzqDbWHvQXhMkpYHfTjnRE; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":10,"warning":null},{"id":"epoch-run-k4zGHaXESxFRTRMkyDLZrz","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_48K (thinking 48k)","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-opus-4-5-20251101_48K; run=k4zGHaXESxFRTRMkyDLZrz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22,"warning":null},{"id":"epoch-run-k5CCeHstJwo5wKpbMFZtfw","modelId":"claude-opus-4-6","benchmarkId":"epoch-chess-puzzles-1-0-1-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-opus-4-6_64K (thinking 64k)","configuration":"Epoch AI Inspect; task 1.0.1; scorer model_extracted_exact_match; model=claude-opus-4-6_64K; run=k5CCeHstJwo5wKpbMFZtfw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":10,"warning":null},{"id":"epoch-run-k7EnhoBbZyVFUVRBowA5Pm","modelId":"kimi-k2.7-code","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"kimi-k2.7-code","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k2.7-code; run=k7EnhoBbZyVFUVRBowA5Pm; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21,"warning":null},{"id":"epoch-run-K8zTckSXLKLesoLBv24TWc","modelId":"qwen3.5-flash","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"qwen3.5-flash","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=qwen3.5-flash; run=K8zTckSXLKLesoLBv24TWc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20.32032032032032,"warning":null},{"id":"epoch-run-KAPGpH2CLMafAt8MnAQJT3","modelId":"gemma-3-4b-it","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemma-3-4b-it","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-3-4b-it; run=KAPGpH2CLMafAt8MnAQJT3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":7.5,"warning":null},{"id":"epoch-run-KB62zrQQ5ccd7hCcUwkX8j","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"claude-sonnet-4-5-20250929","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-4-5-20250929; run=KB62zrQQ5ccd7hCcUwkX8j; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":4,"warning":null},{"id":"epoch-run-KbUNQf8nnwPa8ixg6AnEwB","modelId":"deepseek-r1-distill-qwen-32b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"DeepSeek-R1-Distill-Qwen-32B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=DeepSeek-R1-Distill-Qwen-32B; run=KbUNQf8nnwPa8ixg6AnEwB; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":55.55555555555556,"warning":null},{"id":"epoch-run-kCQr6ARwJyUfkwWqKAfuDX","modelId":"qwen3.5-plus","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"unspecified","sourceLabel":"qwen3.5-plus","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=qwen3.5-plus; run=kCQr6ARwJyUfkwWqKAfuDX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":16,"warning":null},{"id":"epoch-run-kDNNbUYXhrAH5uDBGykFaf","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"medium","sourceLabel":"claude-sonnet-4-6_medium","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-4-6_medium; run=kDNNbUYXhrAH5uDBGykFaf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.22222222222221,"warning":null},{"id":"epoch-run-KesKa5EXtFG7H4UMBFzgCh","modelId":"gpt-5.5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"none","sourceLabel":"gpt-5.5_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.5_none; run=KesKa5EXtFG7H4UMBFzgCh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":77.27272727272727,"warning":null},{"id":"epoch-run-KFAFU6kX7qVekqq6QR524K","modelId":"gpt-5.6-sol","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"none","sourceLabel":"gpt-5.6-sol_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-sol_none; run=KFAFU6kX7qVekqq6QR524K; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":7.000000000000001,"warning":null},{"id":"epoch-run-KfQKr2ibCFMx5xBELoiM3Y","modelId":"gemma-3-12b-it","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"gemma-3-12b-it","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemma-3-12b-it; run=KfQKr2ibCFMx5xBELoiM3Y; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":39.457070707070706,"warning":null},{"id":"epoch-run-kgJ2d6XbKj3dZutDcBYSKU","modelId":"claude-opus-4-6","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-opus-4-6_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-4-6_max; run=kgJ2d6XbKj3dZutDcBYSKU; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":65.96491228070175,"warning":null},{"id":"epoch-run-KH7KfZvFc9kZbqiJFdfYTc","modelId":"qwen3-4b-instruct-2507","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-4b-instruct-2507","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-4b-instruct-2507; run=KH7KfZvFc9kZbqiJFdfYTc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":52.22222222222223,"warning":null},{"id":"epoch-run-kHUvo7vG9JDf7fQvWpeP7s","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3-30b-a3b-instruct-2507","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-30b-a3b-instruct-2507; run=kHUvo7vG9JDf7fQvWpeP7s; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":2,"warning":null},{"id":"epoch-run-Kk4oLoTLyDuqfnbqjPSvgZ","modelId":"deepseek-v4-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"deepseek-v4-flash-0731_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=deepseek-v4-flash-0731_max; run=Kk4oLoTLyDuqfnbqjPSvgZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":33,"warning":null},{"id":"epoch-run-KKm5DbPUgXo88eYr64g4SK","modelId":"qwen3.5-35b-a3b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3.5-35b-a3b_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.5-35b-a3b_none; run=KKm5DbPUgXo88eYr64g4SK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":81.18686868686868,"warning":null},{"id":"epoch-run-KKzu5PGJQTEtfgMTqe7pnp","modelId":"glm-4.7-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"glm-4.7-flash","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-4.7-flash; run=KKzu5PGJQTEtfgMTqe7pnp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-KM4G49tQZB8ce67RxYGyMy","modelId":"minimax-m3","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"MiniMax-M3_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=MiniMax-M3_none; run=KM4G49tQZB8ce67RxYGyMy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":81.31313131313132,"warning":null},{"id":"epoch-run-kmHbjBrwGgEKNr65JrXcGX","modelId":"glm-5.1","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"glm-5.1","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.1; run=kmHbjBrwGgEKNr65JrXcGX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":19,"warning":null},{"id":"epoch-run-Knij32Jp6bQJ2V9NHpg5VS","modelId":"gpt-5.5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"high","sourceLabel":"gpt-5.5_high","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.5_high; run=Knij32Jp6bQJ2V9NHpg5VS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":52,"warning":null},{"id":"epoch-run-KptKXK5nE2Ns2WbiaSSnbc","modelId":"gemini-3.7-flash","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.7-flash_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.7-flash_high; run=KptKXK5nE2Ns2WbiaSSnbc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":36.58536585365854,"warning":null},{"id":"epoch-run-kQjrYCaa7yYyMXofeR23Dd","modelId":"gemini-3.7-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.7-flash_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.7-flash_high; run=kQjrYCaa7yYyMXofeR23Dd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.22222222222221,"warning":null},{"id":"epoch-run-kR9F3oHBCnwQW4AiTPKwpd","modelId":"gemini-3.1-pro","benchmarkId":"epoch-gpqa-diamond-1-0-5-choice","level":"unspecified","sourceLabel":"gemini-3.1-pro-preview","configuration":"Epoch AI Inspect; task 1.0.5; scorer choice; model=gemini-3.1-pro-preview; run=kR9F3oHBCnwQW4AiTPKwpd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.1,"warning":"Run-specific qualification requires review: In the initial run, 3% of samples failed to complete. Inspect defaults to not scoring these at all, but we override this behavior when >2% of epochs fail. For each sample, we average the score of the epochs that did complete for that sample. If none completed, we assign the random baseline of 25%. Then we average these scores across all samples. In this case, the resulting difference is very small: 94.1% modified vs. 94.4% original."},{"id":"epoch-run-kRPSnHnDdheajNdqmKsMjs","modelId":"gpt-6-astra","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"low","sourceLabel":"gpt-6-astra_low","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-6-astra_low; run=kRPSnHnDdheajNdqmKsMjs; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.8048780487805,"warning":null},{"id":"epoch-run-kwT2PhMLMheWkxaqwh8PKq","modelId":"glm-5.2","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"glm-5.2_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_none; run=kwT2PhMLMheWkxaqwh8PKq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":6,"warning":null},{"id":"epoch-run-Kwwo3UFcPDk6iLAeSeeRaa","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-gpqa-diamond-1-0-2-choice","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.2; scorer choice; model=claude-opus-4-5-20251101_32K; run=Kwwo3UFcPDk6iLAeSeeRaa; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.0479797979798,"warning":null},{"id":"epoch-run-KxvHAT9SV2dTDn7jBnTk6f","modelId":"claude-opus-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-opus-5_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-5_max; run=KxvHAT9SV2dTDn7jBnTk6f; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":98.88888888888889,"warning":null},{"id":"epoch-run-KxxB8kDa9obqrPuec4PEiv","modelId":"qwen3.5-35b-a3b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-35b-a3b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-35b-a3b; run=KxxB8kDa9obqrPuec4PEiv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1,"warning":null},{"id":"epoch-run-kZ3VgrQJxfKQ5msjpmSaAz","modelId":"claude-opus-4-6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-4-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-opus-4-6_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.4; scorer model_extracted_exact_match; model=claude-opus-4-6_32K; run=kZ3VgrQJxfKQ5msjpmSaAz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.05555555555556,"warning":null},{"id":"epoch-run-L7kW8yxFKCjVXhxNnt3VTq","modelId":"gpt-6-astra","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"gpt-6-astra_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-6-astra_max; run=L7kW8yxFKCjVXhxNnt3VTq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":100,"warning":null},{"id":"epoch-run-LcttjHHzTyAW6MqNE29xiK","modelId":"qwen3-8b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3-8b_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-8b_none; run=LcttjHHzTyAW6MqNE29xiK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47.474747474747474,"warning":null},{"id":"epoch-run-Lgy52ZT4YpFrUqqKVu2qUs","modelId":"gemini-3.8-flash","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.8-flash_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.8-flash_high; run=Lgy52ZT4YpFrUqqKVu2qUs; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21.951219512195124,"warning":null},{"id":"epoch-run-LHRL6nQJZXGJmYppR7kbGw","modelId":"llama-3.2-90b-vision-instruct","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"Llama-3.2-90B-Vision-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=Llama-3.2-90B-Vision-Instruct; run=LHRL6nQJZXGJmYppR7kbGw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":2.638888888888889,"warning":null},{"id":"epoch-run-LiRiryJsGb3h5UuxX8bmJv","modelId":"deepseek-r1-0528","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"DeepSeek-R1-0528","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=DeepSeek-R1-0528; run=LiRiryJsGb3h5UuxX8bmJv; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":76.32575757575758,"warning":null},{"id":"epoch-run-LjgJoDosTLkiGVT59smA7q","modelId":"kimi-k2.6","benchmarkId":"epoch-gpqa-diamond-1-0-8-choice","level":"unspecified","sourceLabel":"kimi-k2.6","configuration":"Epoch AI Inspect; task 1.0.8; scorer choice; model=kimi-k2.6; run=LjgJoDosTLkiGVT59smA7q; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.78282828282829,"warning":null},{"id":"epoch-run-LJyKf8Xy4dymxNHbGLwNdA","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"high","sourceLabel":"claude-sonnet-4-6_high","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=claude-sonnet-4-6_high; run=LJyKf8Xy4dymxNHbGLwNdA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":35.5,"warning":null},{"id":"epoch-run-LkVuUxvsHNzpcg3sUiH7f3","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_16K (thinking 16k)","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=claude-sonnet-4-5-20250929_16K; run=LkVuUxvsHNzpcg3sUiH7f3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":78.78787878787878,"warning":null},{"id":"epoch-run-LmRxqPrS2Gm6Gq2cSNc92G","modelId":"gpt-5.6-terra","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"none","sourceLabel":"gpt-5.6-terra_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-terra_none; run=LmRxqPrS2Gm6Gq2cSNc92G; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":5,"warning":null},{"id":"epoch-run-LPo74T9L3CawnKX5LLUrSZ","modelId":"claude-sonnet-5","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"claude-sonnet-5_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-sonnet-5_max; run=LPo74T9L3CawnKX5LLUrSZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":33.7,"warning":null},{"id":"epoch-run-LSKDetgzyVojru45w7RJhf","modelId":"gpt-5.5-pro","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"gpt-5.5-pro_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.5-pro_xhigh; run=LSKDetgzyVojru45w7RJhf; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.71929824561403,"warning":null},{"id":"epoch-run-LsnPrukDADRTP8fsn8zD9S","modelId":"claude-opus-4-7","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"unspecified","sourceLabel":"claude-opus-4-7","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=claude-opus-4-7; run=LsnPrukDADRTP8fsn8zD9S; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":13,"warning":null},{"id":"epoch-run-LurNQWcpKjLWQ7AXSD6Ab3","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemini-3.1-flash-lite_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.1-flash-lite_minimal; run=LurNQWcpKjLWQ7AXSD6Ab3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":24,"warning":null},{"id":"epoch-run-LWbCXNGMXtjQYxyM2uoFMV","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"deepseek-r1-0528-qwen3-8b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=deepseek-r1-0528-qwen3-8b; run=LWbCXNGMXtjQYxyM2uoFMV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":43.888888888888886,"warning":null},{"id":"epoch-run-LWkDtkmd3TNmLzMhfZD5HW","modelId":"gpt-5.6-luna","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"gpt-5.6-luna_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-luna_max; run=LWkDtkmd3TNmLzMhfZD5HW; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.60353535353535,"warning":null},{"id":"epoch-run-M8sY8vHnvSLxQUg3HTMTCp","modelId":"gemini-3.6-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"low","sourceLabel":"gemini-3.6-flash_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3.6-flash_low; run=M8sY8vHnvSLxQUg3HTMTCp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":23,"warning":null},{"id":"epoch-run-McJyXLHBzx5VjAqXjmrrsb","modelId":"gemma-3-4b-it","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"gemma-3-4b-it","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemma-3-4b-it; run=McJyXLHBzx5VjAqXjmrrsb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":23.232323232323232,"warning":null},{"id":"epoch-run-MEhV5sh6nbM8cKJGQ6HzcS","modelId":"claude-opus-4-8","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"claude-opus-4-8_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-8_low; run=MEhV5sh6nbM8cKJGQ6HzcS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":97.77777777777777,"warning":null},{"id":"epoch-run-mEkZaYpiurQ6TEMAALK3su","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-gpqa-diamond-1-0-2-choice","level":"unspecified","sourceLabel":"claude-opus-4-5-20251101","configuration":"Epoch AI Inspect; task 1.0.2; scorer choice; model=claude-opus-4-5-20251101; run=mEkZaYpiurQ6TEMAALK3su; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80.68181818181817,"warning":null},{"id":"epoch-run-MEwMcmSV32JHrsNoAq4BFL","modelId":"llama-3.1-70b-instruct","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"Llama-3.1-70B-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=Llama-3.1-70B-Instruct; run=MEwMcmSV32JHrsNoAq4BFL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":44.19191919191919,"warning":null},{"id":"epoch-run-MFTd4BUbtzbfcCky6d79d4","modelId":"gpt-5.6-terra","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"gpt-5.6-terra_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-terra_max; run=MFTd4BUbtzbfcCky6d79d4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":35,"warning":null},{"id":"epoch-run-Mg2yb9Tp3yc2H3ApJX6JBK","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"low","sourceLabel":"gemini-3.5-flash-lite_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3.5-flash-lite_low; run=Mg2yb9Tp3yc2H3ApJX6JBK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":19,"warning":null},{"id":"epoch-run-mGXYSUNCMisvaRzhQp6g2L","modelId":"qwen3.5-plus","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.5-plus","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.5-plus; run=mGXYSUNCMisvaRzhQp6g2L; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84.84848484848484,"warning":null},{"id":"epoch-run-MHAMdn52f7wLMZ6MSCs5E2","modelId":"gpt-5.5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"none","sourceLabel":"gpt-5.5_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.5_none; run=MHAMdn52f7wLMZ6MSCs5E2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":18,"warning":null},{"id":"epoch-run-MhqeuRVx4JcRfxPQDYPq7Z","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"unspecified","sourceLabel":"claude-sonnet-4-5-20250929","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=claude-sonnet-4-5-20250929; run=MhqeuRVx4JcRfxPQDYPq7Z; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":23.7,"warning":null},{"id":"epoch-run-Mhwme9odWJMzMjoYkW8r6B","modelId":"glm-5.1","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"glm-5.1","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.1; run=Mhwme9odWJMzMjoYkW8r6B; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":36.84210526315789,"warning":null},{"id":"epoch-run-Mifz96Jm442bn43Qnxj5rT","modelId":"gpt-5.6-sol","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-5.6-sol_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-sol_low; run=Mifz96Jm442bn43Qnxj5rT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.55555555555556,"warning":null},{"id":"epoch-run-mKhVMEicZeGjdvJdTRd7mK","modelId":"deepseek-v4-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"deepseek-v4-flash-0731_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=deepseek-v4-flash-0731_max; run=mKhVMEicZeGjdvJdTRd7mK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":57.54385964912281,"warning":null},{"id":"epoch-run-mLLmVVvo6t23MM5yxq7ryW","modelId":"muse-spark-1.2","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"xhigh","sourceLabel":"muse-spark-1.2_xhigh","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=muse-spark-1.2_xhigh; run=mLLmVVvo6t23MM5yxq7ryW; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":60.30150753768844,"warning":null},{"id":"epoch-run-mLmUnBuX6DYKtb6x46GteM","modelId":"claude-opus-5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"claude-opus-5","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-opus-5; run=mLmUnBuX6DYKtb6x46GteM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":92.92929292929293,"warning":null},{"id":"epoch-run-mM6vdJpgjLY9prnetXzZJS","modelId":"grok-4.20-0309-reasoning","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"grok-4.20-0309-reasoning","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.20-0309-reasoning; run=mM6vdJpgjLY9prnetXzZJS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":92.22222222222223,"warning":null},{"id":"epoch-run-Mmbo8x2A3WpafV5D6fvS7v","modelId":"glm-4.7-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"glm-4.7-flash_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-4.7-flash_none; run=Mmbo8x2A3WpafV5D6fvS7v; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-mQ3UwD6hUioWSp2s2oELY4","modelId":"gemini-2.5-pro","benchmarkId":"epoch-chess-puzzles-1-0-0-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemini-2.5-pro","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=gemini-2.5-pro; run=mQ3UwD6hUioWSp2s2oELY4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-mqsc4vFuKtAHXxbYyX9WwK","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.5-flash-lite_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash-lite_high; run=mqsc4vFuKtAHXxbYyX9WwK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":71.11111111111111,"warning":null},{"id":"epoch-run-mRAASXsUuoJmc2oR5G89zR","modelId":"claude-fable-5-1","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-fable-5-1_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5-1_max; run=mRAASXsUuoJmc2oR5G89zR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":100,"warning":null},{"id":"epoch-run-mS5EwCRZVpvUvJEehPUDZu","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-4-5-20251101_32K; run=mS5EwCRZVpvUvJEehPUDZu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34.385964912280706,"warning":null},{"id":"epoch-run-mstwSH7noJfvhGcd6Lz5kd","modelId":"gemma-4-26b-a4b-it","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemma-4-26b-a4b-it_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-4-26b-a4b-it_minimal; run=mstwSH7noJfvhGcd6Lz5kd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.22222222222221,"warning":null},{"id":"epoch-run-MsXAXDEKP3xBKtiA7aTBBG","modelId":"llama-4-scout","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"Llama-4-Scout-17B-16E-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=Llama-4-Scout-17B-16E-Instruct; run=MsXAXDEKP3xBKtiA7aTBBG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":51.830808080808076,"warning":null},{"id":"epoch-run-MvdunHkVURna3JuyDjhzEc","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"high","sourceLabel":"gemini-3-flash-preview_high","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3-flash-preview_high; run=MvdunHkVURna3JuyDjhzEc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-mvNb3hNgSZ2gS6jHMtvCdk","modelId":"kimi-k3","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"kimi-k3_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=kimi-k3_low; run=mvNb3hNgSZ2gS6jHMtvCdk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84.84848484848484,"warning":null},{"id":"epoch-run-MVZf59jt9uEoWG9w5W9apB","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.1-flash-lite_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.1-flash-lite_high; run=MVZf59jt9uEoWG9w5W9apB; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":27.719298245614034,"warning":null},{"id":"epoch-run-MYGuFuvkWEwLC7US5UR363","modelId":"qwen3-32b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Qwen3-32B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Qwen3-32B; run=MYGuFuvkWEwLC7US5UR363; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":5,"warning":null},{"id":"epoch-run-mZLWt2JSYvJyGhMvji7CT8","modelId":"kimi-k3","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"kimi-k3_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=kimi-k3_max; run=mZLWt2JSYvJyGhMvji7CT8; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":50.6,"warning":null},{"id":"epoch-run-n4hyz75SVpwPEisKVVjvNg","modelId":"glm-5","benchmarkId":"epoch-gpqa-diamond-1-0-5-choice","level":"unspecified","sourceLabel":"glm-5","configuration":"Epoch AI Inspect; task 1.0.5; scorer choice; model=glm-5; run=n4hyz75SVpwPEisKVVjvNg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.81725888324873,"warning":null},{"id":"epoch-run-N5beL4W3WahAubJgDKivnE","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-chess-puzzles-1-0-2-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-sonnet-4-6_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match; model=claude-sonnet-4-6_32K; run=N5beL4W3WahAubJgDKivnE; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":13,"warning":null},{"id":"epoch-run-n9gpXfUzo8SbWqvrG2q4xM","modelId":"mistral-large-2411","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"mistral-large-2411","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=mistral-large-2411; run=n9gpXfUzo8SbWqvrG2q4xM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":51.32575757575758,"warning":null},{"id":"epoch-run-NaNEVAYahYyobdLPgCeNK9","modelId":"gemma-3-12b-it","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemma-3-12b-it","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-3-12b-it; run=NaNEVAYahYyobdLPgCeNK9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-nb9LnDeeQyvRCqsbsTANGD","modelId":"gemini-3.6-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.6-flash_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.6-flash_high; run=nb9LnDeeQyvRCqsbsTANGD; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":58.94736842105262,"warning":null},{"id":"epoch-run-NCikvVWc5SEyMEbCqvVNb2","modelId":"glm-5.3-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"glm-5.3-flash_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.3-flash_max; run=NCikvVWc5SEyMEbCqvVNb2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.88888888888889,"warning":null},{"id":"epoch-run-nDsNFM5ioGzyWcpeUKVotg","modelId":"qwen3.6-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.6-flash","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-flash; run=nDsNFM5ioGzyWcpeUKVotg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17.192982456140353,"warning":null},{"id":"epoch-run-nE4hmJo3QV6X5jeGWAeAze","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"gemini-3.1-flash-lite_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.1-flash-lite_high; run=nE4hmJo3QV6X5jeGWAeAze; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":81.81818181818183,"warning":null},{"id":"epoch-run-nEJGtXGN588zynPkynZkxz","modelId":"deepseek-v4-pro","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"deepseek-v4-pro-0813_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=deepseek-v4-pro-0813_max; run=nEJGtXGN588zynPkynZkxz; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":91.66666666666666,"warning":null},{"id":"epoch-run-NeYuqgQyWtFWAHEjQYPm5Z","modelId":"gemini-3.8-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.8-flash_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.8-flash_high; run=NeYuqgQyWtFWAHEjQYPm5Z; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":98.88888888888889,"warning":null},{"id":"epoch-run-neZvEzLi6yeL9z5KjGef7H","modelId":"claude-haiku-4-5-20251001","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-haiku-4-5-20251001_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=claude-haiku-4-5-20251001_32K; run=neZvEzLi6yeL9z5KjGef7H; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.66666666666666,"warning":null},{"id":"epoch-run-NfN7VwMPjSVqViqrBQPWk2","modelId":"glm-5.2","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"medium","sourceLabel":"glm-5.2_medium","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.2_medium; run=NfN7VwMPjSVqViqrBQPWk2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":15,"warning":null},{"id":"epoch-run-NGhhhxcbTVcftKdk8S7rAX","modelId":"qwen3.7-plus","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.7-plus_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-plus_none; run=NGhhhxcbTVcftKdk8S7rAX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":9,"warning":null},{"id":"epoch-run-NGQ4Q8Wrb4aroMu5RecTS6","modelId":"grok-4.6","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"grok-4.6_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.6_high; run=NGQ4Q8Wrb4aroMu5RecTS6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":40,"warning":null},{"id":"epoch-run-nhim2QCRgpir5cZdqrmUz3","modelId":"gemini-3.1-pro","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.1-pro-preview_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.1-pro-preview_high; run=nhim2QCRgpir5cZdqrmUz3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":95.55555555555556,"warning":null},{"id":"epoch-run-njpkLAWZTvept6tnkraYrR","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"minimal","sourceLabel":"gemini-3-flash-preview_minimal","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3-flash-preview_minimal; run=njpkLAWZTvept6tnkraYrR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25,"warning":null},{"id":"epoch-run-NLiiJJSyA9wmg2FHENFpAq","modelId":"gpt-5.6-luna","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"gpt-5.6-luna_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.6-luna_max; run=NLiiJJSyA9wmg2FHENFpAq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":60.97560975609756,"warning":null},{"id":"epoch-run-NMdaAXyqqPRmWfuxZUfHFF","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.1-flash-lite_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.1-flash-lite_high; run=NMdaAXyqqPRmWfuxZUfHFF; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80,"warning":null},{"id":"epoch-run-nrh3xa3Bn765Q6DXWoVfbS","modelId":"gemini-3.5-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"low","sourceLabel":"gemini-3.5-flash_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3.5-flash_low; run=nrh3xa3Bn765Q6DXWoVfbS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.000000000000004,"warning":null},{"id":"epoch-run-nSb2focDRMyPJXErk3MV94","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-2-model-extracted-exact-match","level":"unspecified","sourceLabel":"claude-opus-4-5-20251101","configuration":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match; model=claude-opus-4-5-20251101; run=nSb2focDRMyPJXErk3MV94; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":48.05555555555556,"warning":null},{"id":"epoch-run-nSLGeLNawfzhCbR33agwer","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gemini-3.1-flash-lite_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.1-flash-lite_low; run=nSLGeLNawfzhCbR33agwer; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25,"warning":null},{"id":"epoch-run-nuKCgZReCBsXKCkNj9bK37","modelId":"gpt-5.6-sol","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"gpt-5.6-sol_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-sol_max; run=nuKCgZReCBsXKCkNj9bK37; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.49747474747475,"warning":null},{"id":"epoch-run-NV5tAZdTHYzP6F6Ym4dUus","modelId":"qwen3-32b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"Qwen3-32B_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Qwen3-32B_none; run=NV5tAZdTHYzP6F6Ym4dUus; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1,"warning":null},{"id":"epoch-run-nW39ZzuDQ3xTAGVoEfFG95","modelId":"gpt-5.6-luna","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"gpt-5.6-luna_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gpt-5.6-luna_low; run=nW39ZzuDQ3xTAGVoEfFG95; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.32323232323232,"warning":null},{"id":"epoch-run-o5th8Rb9WiaDbv4oEMDoFa","modelId":"qwen3.7-plus","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.7-plus_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-plus_none; run=o5th8Rb9WiaDbv4oEMDoFa; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80,"warning":null},{"id":"epoch-run-o6migB5WP27uLr9nUWpCiM","modelId":"qwen3.5-9b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.5-9B","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.5-9B; run=o6migB5WP27uLr9nUWpCiM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":78.97727272727273,"warning":null},{"id":"epoch-run-o6VtA8qruLpoShhPy2JdLg","modelId":"qwen3.6-27b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.6-27b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-27b_none; run=o6VtA8qruLpoShhPy2JdLg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.66666666666666,"warning":null},{"id":"epoch-run-oAu9CZSNPZgwiwKnoNpM8Q","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-gpqa-diamond-1-0-3-choice","level":"unspecified","sourceLabel":"gemini-3-flash-preview","configuration":"Epoch AI Inspect; task 1.0.3; scorer choice; model=gemini-3-flash-preview; run=oAu9CZSNPZgwiwKnoNpM8Q; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.20707070707071,"warning":null},{"id":"epoch-run-oB8tcqTgWoZYX7BTFj4c8v","modelId":"qwen3-14b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3-14b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-14b_none; run=oB8tcqTgWoZYX7BTFj4c8v; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-opus-4-7-chess-puzzles-prelim-lower-bound","modelId":"claude-opus-4-7","benchmarkId":"epoch-chess-puzzles-1-1-1-model-extracted-exact-match","level":"xhigh","sourceLabel":"claude-opus-4-7_xhigh","configuration":"Epoch AI Inspect; task 1.1.1; scorer model_extracted_exact_match; model=claude-opus-4-7_xhigh; run=opus-4-7-chess-puzzles-prelim-lower-bound; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":30,"warning":"Run-specific qualification requires review: Opus 4.7 hit its max_tokens limit of 128K without responding on 31/100 samples. We intend to improve elicitation in the future, and this score should be understood as a lower bound."},{"id":"epoch-run-oU38rqq2TvJTxvvPsnEQsH","modelId":"claude-opus-4-8","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"claude-opus-4-8_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-8_none; run=oU38rqq2TvJTxvvPsnEQsH; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":13,"warning":null},{"id":"epoch-run-oXZ7ZVZtADrwFPKAe6zTvL","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"claude-sonnet-4-6_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-4-6_high; run=oXZ7ZVZtADrwFPKAe6zTvL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":75.55555555555556,"warning":null},{"id":"epoch-run-P4LXQ9PyDDziEANMB5jVRd","modelId":"claude-opus-4-7","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-opus-4-7_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-4-7_max; run=P4LXQ9PyDDziEANMB5jVRd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":31.70731707317073,"warning":null},{"id":"epoch-run-P5L8qbXo42vTvbU3UvTNjk","modelId":"gemma-4-31b-it","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"minimal","sourceLabel":"gemma-4-31b-it_minimal","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemma-4-31b-it_minimal; run=P5L8qbXo42vTvbU3UvTNjk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":75.75757575757575,"warning":null},{"id":"epoch-run-P7kyrA6oQ68tVGHyekP7Qj","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-chess-puzzles-1-0-0-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=claude-opus-4-5-20251101_32K; run=P7kyrA6oQ68tVGHyekP7Qj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12,"warning":null},{"id":"epoch-run-PBRdMZyz4L4CqPpXyLD2Lk","modelId":"qwen-3.8-max","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"qwen3.8-max_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.8-max_xhigh; run=PBRdMZyz4L4CqPpXyLD2Lk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":46.34146341463415,"warning":null},{"id":"epoch-run-PBrQpAgRCXeUSNveEn4aDE","modelId":"gpt-5.6-luna","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"none","sourceLabel":"gpt-5.6-luna_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-luna_none; run=PBrQpAgRCXeUSNveEn4aDE; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-Pc6CyTEYKbcdDUDKzGZnS9","modelId":"gemma-3-1b-it","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"gemma-3-1b-it","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemma-3-1b-it; run=Pc6CyTEYKbcdDUDKzGZnS9; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":19.94949494949495,"warning":null},{"id":"epoch-run-PKSMspJiJdNThB6qNvaBSM","modelId":"gpt-5.5","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"gpt-5.5_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.5_xhigh; run=PKSMspJiJdNThB6qNvaBSM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":72.5,"warning":null},{"id":"epoch-run-PPbjbUncV6qa9jNRKjYrfp","modelId":"qwen-3.8-max","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"xhigh","sourceLabel":"qwen3.8-max_xhigh","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.8-max_xhigh; run=PPbjbUncV6qa9jNRKjYrfp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.999999999999996,"warning":null},{"id":"epoch-run-PppwnX7EjXx2SeTcFN8Ujn","modelId":"gpt-6-astra","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"gpt-6-astra_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gpt-6-astra_max; run=PppwnX7EjXx2SeTcFN8Ujn; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":75.6,"warning":null},{"id":"epoch-run-PtxHF8BH8WuNdNfDnutGBb","modelId":"qwq-plus","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"qwq-plus","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=qwq-plus; run=PtxHF8BH8WuNdNfDnutGBb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":65.40404040404042,"warning":null},{"id":"epoch-run-Q3WpHdurYNvawj6ycXyj6e","modelId":"claude-opus-4-8","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"claude-opus-4-8_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-opus-4-8_max; run=Q3WpHdurYNvawj6ycXyj6e; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":36,"warning":null},{"id":"epoch-run-Q8RAfong7NRCvww73BB3AT","modelId":"llama-3.1-8b-instruct","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Llama-3.1-8B-Instruct","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Llama-3.1-8B-Instruct; run=Q8RAfong7NRCvww73BB3AT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-QDZRoAVaEDtdS6nECEeE35","modelId":"gemini-3.5-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"minimal","sourceLabel":"gemini-3.5-flash_minimal","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.5-flash_minimal; run=QDZRoAVaEDtdS6nECEeE35; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.36363636363636,"warning":null},{"id":"epoch-run-QeVP4X52JBDZBdeefZjEmb","modelId":"qwen3.5-2b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.5-2b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-2b_none; run=QeVP4X52JBDZBdeefZjEmb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-QHfAMMDjjzQF6xitN2vBbA","modelId":"gpt-5.5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"low","sourceLabel":"gpt-5.5_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.5_low; run=QHfAMMDjjzQF6xitN2vBbA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.000000000000004,"warning":null},{"id":"epoch-run-QJ5rJMVypB4PMxPcBGftc8","modelId":"gpt-5.6-sol","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"gpt-5.6-sol_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.6-sol_max; run=QJ5rJMVypB4PMxPcBGftc8; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.92682926829268,"warning":null},{"id":"epoch-run-QuqPmMUTbiEsUvoFYZx5Mk","modelId":"gpt-5.5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"none","sourceLabel":"gpt-5.5_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.5_none; run=QuqPmMUTbiEsUvoFYZx5Mk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":57.77777777777777,"warning":null},{"id":"epoch-run-QUuykbQhKapHn3gjLFjTam","modelId":"claude-haiku-4-5-20251001","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-haiku-4-5-20251001_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-haiku-4-5-20251001_32K; run=QUuykbQhKapHn3gjLFjTam; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":8,"warning":null},{"id":"epoch-run-Qw4tGw38pk4sdsEehhrLSR","modelId":"claude-sonnet-5","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"xhigh","sourceLabel":"claude-sonnet-5_xhigh","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-sonnet-5_xhigh; run=Qw4tGw38pk4sdsEehhrLSR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":32.9,"warning":null},{"id":"epoch-run-QWw65xeTn8x42SymMsVREN","modelId":"mistral-medium-2505","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"mistral-medium-2505","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=mistral-medium-2505; run=QWw65xeTn8x42SymMsVREN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":32.22222222222222,"warning":null},{"id":"epoch-run-QX76VGMs6CYv9BGBKMCCNW","modelId":"gpt-oss-20b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-oss-20b_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-oss-20b_low; run=QX76VGMs6CYv9BGBKMCCNW; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":2,"warning":null},{"id":"epoch-run-QyJe5cEG4rYmwvZv9b3oyG","modelId":"gemma-3-4b-it","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemma-3-4b-it","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-3-4b-it; run=QyJe5cEG4rYmwvZv9b3oyG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-QYZ6wRuT7WMkaYPKc9dRPy","modelId":"gpt-5.6-luna","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"none","sourceLabel":"gpt-5.6-luna_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-luna_none; run=QYZ6wRuT7WMkaYPKc9dRPy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":40,"warning":null},{"id":"epoch-run-R2fMFAtRXah864hMifdQGV","modelId":"glm-5.1","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"unspecified","sourceLabel":"glm-5.1","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=glm-5.1; run=R2fMFAtRXah864hMifdQGV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34,"warning":null},{"id":"epoch-run-R9XpD2PaYpPiokjjSWnMYT","modelId":"grok-4.3","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"grok-4.3_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.3_high; run=R9XpD2PaYpPiokjjSWnMYT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25,"warning":null},{"id":"epoch-run-RA5MRbmWJpFPR29BQxfvZt","modelId":"kimi-k2.6","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"kimi-k2.6","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=kimi-k2.6; run=RA5MRbmWJpFPR29BQxfvZt; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":18,"warning":null},{"id":"epoch-run-RAwuPRwJedy7P2KeQhEmr8","modelId":"phi-4","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"phi-4","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=phi-4; run=RAwuPRwJedy7P2KeQhEmr8; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":56.060606060606055,"warning":null},{"id":"epoch-run-ReDAtJGGfRtrEGGWf4Zbsd","modelId":"claude-fable-5","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-fable-5_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-fable-5_max; run=ReDAtJGGfRtrEGGWf4Zbsd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.2,"warning":null},{"id":"epoch-run-RG2biwnmGybSVTVxxMdRWa","modelId":"qwen3.7-max","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.7-max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.7-max; run=RG2biwnmGybSVTVxxMdRWa; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":64.56140350877193,"warning":null},{"id":"epoch-run-RiyrdXiqrXT98mKM9nMsmu","modelId":"grok-4.6","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"xhigh","sourceLabel":"grok-4.6_xhigh","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=grok-4.6_xhigh; run=RiyrdXiqrXT98mKM9nMsmu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":31,"warning":null},{"id":"epoch-run-RMcys99fv45vvgTgakXXWn","modelId":"qwen3-14b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3-14b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3-14b_none; run=RMcys99fv45vvgTgakXXWn; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25.833333333333336,"warning":null},{"id":"epoch-run-RMeUVa4tq3fURqCMtQWkfe","modelId":"gpt-5.6-sol","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"low","sourceLabel":"gpt-5.6-sol_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-sol_low; run=RMeUVa4tq3fURqCMtQWkfe; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26,"warning":null},{"id":"epoch-run-RoscWx4NUGVqcHdko6QhKd","modelId":"qwen3.6-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"qwen3.6-flash_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-flash_none; run=RoscWx4NUGVqcHdko6QhKd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22.45614035087719,"warning":null},{"id":"epoch-run-RWjuCuVGvaRd4vDjJJ6aP2","modelId":"qwen3.5-35b-a3b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.5-35b-a3b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.5-35b-a3b; run=RWjuCuVGvaRd4vDjJJ6aP2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":83.45959595959596,"warning":null},{"id":"epoch-run-RXsYuuSedkYZ5ubc8swxGp","modelId":"qwen3.6-plus","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.6-plus","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-plus; run=RXsYuuSedkYZ5ubc8swxGp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17,"warning":null},{"id":"epoch-run-S5pm7ctk9zgPfbyHrbD9AV","modelId":"claude-fable-5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"claude-fable-5_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-fable-5_max; run=S5pm7ctk9zgPfbyHrbD9AV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":85.85858585858585,"warning":null},{"id":"epoch-run-S5QYXSvQBRSbUbXSnAGbMm","modelId":"llama-3.1-405b-instruct","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"Llama-3.1-405B-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=Llama-3.1-405B-Instruct; run=S5QYXSvQBRSbUbXSnAGbMm; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":50.91540404040404,"warning":null},{"id":"epoch-run-S7wbot7JR53BAjM8F9gaws","modelId":"qwen3.5-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.5-flash","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.5-flash; run=S7wbot7JR53BAjM8F9gaws; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.32323232323232,"warning":null},{"id":"epoch-run-SAZy8rk2HgyPjA8XZJFUmR","modelId":"qwen3.5-4b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.5-4b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-4b_none; run=SAZy8rk2HgyPjA8XZJFUmR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":55.833333333333336,"warning":null},{"id":"epoch-run-SB6Qj6rCBDk8jZmFcCTzWc","modelId":"glm-5.2","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"glm-5.2_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.2_low; run=SB6Qj6rCBDk8jZmFcCTzWc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.87878787878788,"warning":null},{"id":"epoch-run-SEePRKRcv8oqn5HpD2KFxB","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"max","sourceLabel":"claude-sonnet-4-6_max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-sonnet-4-6_max; run=SEePRKRcv8oqn5HpD2KFxB; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":78.78787878787878,"warning":null},{"id":"epoch-run-SEnvgtunRa5GwAtU2sHa87","modelId":"claude-fable-5","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"xhigh","sourceLabel":"claude-fable-5_xhigh","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=claude-fable-5_xhigh; run=SEnvgtunRa5GwAtU2sHa87; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":70.7,"warning":null},{"id":"epoch-run-SFKXCPUu73mwxMoUotiZM2","modelId":"gpt-5.5-pro","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"gpt-5.5-pro_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.5-pro_xhigh; run=SFKXCPUu73mwxMoUotiZM2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":78.04878048780488,"warning":null},{"id":"epoch-run-SH5jr76ni3RnpXVMETMy2H","modelId":"claude-opus-4-5-20251101","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-2-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-opus-4-5-20251101_16K (thinking 16k)","configuration":"Epoch AI Inspect; task 1.0.2; scorer model_extracted_exact_match; model=claude-opus-4-5-20251101_16K; run=SH5jr76ni3RnpXVMETMy2H; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":81.66666666666667,"warning":null},{"id":"epoch-run-SLJyD8yew4TxcmprJfVvuE","modelId":"qwen3-4b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3-4b_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-4b_none; run=SLJyD8yew4TxcmprJfVvuE; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":43.56060606060606,"warning":null},{"id":"epoch-run-SoCkYbcxzkYHXqcqnEQwFN","modelId":"claude-fable-5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"claude-fable-5_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5_high; run=SoCkYbcxzkYHXqcqnEQwFN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":41,"warning":null},{"id":"epoch-run-STxFZiSPAPScUuENvXBWLc","modelId":"grok-4.20-0309-reasoning","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"grok-4.20-0309-reasoning","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=grok-4.20-0309-reasoning; run=STxFZiSPAPScUuENvXBWLc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":89.33080808080808,"warning":null},{"id":"epoch-run-SX5FCWMk3HF83gGsP3WFA6","modelId":"grok-4.20-0309-reasoning","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"grok-4.20-0309-reasoning","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=grok-4.20-0309-reasoning; run=SX5FCWMk3HF83gGsP3WFA6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17.073170731707318,"warning":null},{"id":"epoch-run-SZDgstFQJAGeGQwMXgNx6w","modelId":"qwen3.7-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.7-flash_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-flash_none; run=SZDgstFQJAGeGQwMXgNx6w; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":77.77777777777779,"warning":null},{"id":"epoch-run-T2wFfuSkUdyjpyqurxNmNK","modelId":"claude-sonnet-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"xhigh","sourceLabel":"claude-sonnet-5_xhigh","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-5_xhigh; run=T2wFfuSkUdyjpyqurxNmNK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.72222222222221,"warning":null},{"id":"epoch-run-T3X5DeC47iqCaoRYXu5k8L","modelId":"llama-4-scout","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"Llama-4-Scout-17B-16E-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=Llama-4-Scout-17B-16E-Instruct; run=T3X5DeC47iqCaoRYXu5k8L; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":7.777777777777778,"warning":null},{"id":"epoch-run-T4y4iGHMqA8tXCdBKr5GjS","modelId":"claude-opus-4-7","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-opus-4-7_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-7_max; run=T4y4iGHMqA8tXCdBKr5GjS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.66666666666667,"warning":null},{"id":"epoch-run-T56N3X4KLA3xz7tf5aCMGb","modelId":"claude-fable-5-1","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-fable-5-1_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-fable-5-1_max; run=T56N3X4KLA3xz7tf5aCMGb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.8048780487805,"warning":null},{"id":"epoch-run-T7KJtht8Fesh35M5ayMPnE","modelId":"claude-opus-4-7","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"claude-opus-4-7_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-4-7_low; run=T7KJtht8Fesh35M5ayMPnE; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-TAGZYToqgQmFZr7uYL4rSF","modelId":"gpt-6-astra","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"gpt-6-astra_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-6-astra_max; run=TAGZYToqgQmFZr7uYL4rSF; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":72,"warning":null},{"id":"epoch-run-TDT98jZXHbUMFYTphGEpqC","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-sonnet-4-6_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-4-6_max; run=TDT98jZXHbUMFYTphGEpqC; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":3,"warning":null},{"id":"epoch-run-TEVNDC9QXBh7PQvX9kHZip","modelId":"qwen-3.8-max","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"xhigh","sourceLabel":"qwen3.8-max_xhigh","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.8-max_xhigh; run=TEVNDC9QXBh7PQvX9kHZip; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":92.67676767676768,"warning":null},{"id":"epoch-run-TijCafTTJUFrJ6jPGvBbgq","modelId":"gpt-5.5","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"xhigh","sourceLabel":"gpt-5.5_xhigh","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gpt-5.5_xhigh; run=TijCafTTJUFrJ6jPGvBbgq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":63,"warning":null},{"id":"epoch-run-TjoS7sNuqVTc4LVyGRo4wa","modelId":"qwen3.7-flash","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.7-flash","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-flash; run=TjoS7sNuqVTc4LVyGRo4wa; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.66666666666667,"warning":null},{"id":"epoch-run-TMM3rPrAHcpBG5Pvw9kr4L","modelId":"glm-5.3-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"glm-5.3-flash_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.3-flash_max; run=TMM3rPrAHcpBG5Pvw9kr4L; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":8,"warning":null},{"id":"epoch-run-TpHYtuPG6kYZFvMK7Z6Hqj","modelId":"grok-4.6","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"high","sourceLabel":"grok-4.6_high","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=grok-4.6_high; run=TpHYtuPG6kYZFvMK7Z6Hqj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":49.3,"warning":null},{"id":"epoch-run-TqFmiGvqozt7TSZYmhgF8m","modelId":"deepseek-v4-flash","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"deepseek-v4-flash-0731_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=deepseek-v4-flash-0731_max; run=TqFmiGvqozt7TSZYmhgF8m; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":33.633633633633636,"warning":null},{"id":"epoch-run-Tt8tBXHoCEYqGLePWXkM8u","modelId":"qwen3.7-plus","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"qwen3.7-plus_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.7-plus_none; run=Tt8tBXHoCEYqGLePWXkM8u; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34.385964912280706,"warning":null},{"id":"epoch-run-TTuCPacMDpNaCSs3Hpbdjp","modelId":"glm-5.2","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"glm-5.2_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.2_max; run=TTuCPacMDpNaCSs3Hpbdjp; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":59.205776173285194,"warning":null},{"id":"epoch-run-TUPC8VdX4jApFa4MGfNP4t","modelId":"claude-opus-4-6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-4-model-extracted-exact-match","level":"thinking","sourceLabel":"claude-opus-4-6_64K (thinking 64k)","configuration":"Epoch AI Inspect; task 1.0.4; scorer model_extracted_exact_match; model=claude-opus-4-6_64K; run=TUPC8VdX4jApFa4MGfNP4t; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.44444444444444,"warning":null},{"id":"epoch-run-TxXS78Wg2pSCDbpmeJuzQn","modelId":"llama-3.3-70b-instruct","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"Llama-3.3-70B-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=Llama-3.3-70B-Instruct; run=TxXS78Wg2pSCDbpmeJuzQn; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":47.44318181818182,"warning":null},{"id":"epoch-run-TY8R8FV7zCwByEipkqyg2P","modelId":"glm-5.3","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"glm-5.3_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=glm-5.3_max; run=TY8R8FV7zCwByEipkqyg2P; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":41,"warning":null},{"id":"epoch-run-U5PsUdX2ak4kJ2hgnQkWnX","modelId":"claude-fable-5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"claude-fable-5_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-fable-5_low; run=U5PsUdX2ak4kJ2hgnQkWnX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":78.78787878787878,"warning":null},{"id":"epoch-run-U8H8juE3Ko83jsR6TRntbh","modelId":"nemotron-3-ultra","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"unspecified","sourceLabel":"nemotron-3-ultra","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=nemotron-3-ultra; run=U8H8juE3Ko83jsR6TRntbh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-Ua5RK6JRxdyrHRa3hVFQwq","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.6-35b-a3b_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.6-35b-a3b_none; run=Ua5RK6JRxdyrHRa3hVFQwq; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22,"warning":null},{"id":"epoch-run-UbTx6Qbh6T2uXoQbpGV8i3","modelId":"gemma-3-1b-it","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemma-3-1b-it","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-3-1b-it; run=UbTx6Qbh6T2uXoQbpGV8i3; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0,"warning":null},{"id":"epoch-run-UgqBt5cFjsC96ALwiTFCPR","modelId":"qwen3.5-plus","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.5-plus","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-plus; run=UgqBt5cFjsC96ALwiTFCPR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22,"warning":null},{"id":"epoch-run-UhmACN5spAPyAtWWBf4MAP","modelId":"gpt-5.6-luna","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-5.6-luna_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-luna_low; run=UhmACN5spAPyAtWWBf4MAP; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21,"warning":null},{"id":"epoch-run-UnKHyc2idtTmoTUGxGeNJV","modelId":"glm-5.2","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"low","sourceLabel":"glm-5.2_low","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.2_low; run=UnKHyc2idtTmoTUGxGeNJV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":54.736842105263165,"warning":null},{"id":"epoch-run-UnRUSuZzm2X27TUbpeMPva","modelId":"gpt-5.6-sol","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"max","sourceLabel":"gpt-5.6-sol_max","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=gpt-5.6-sol_max; run=UnRUSuZzm2X27TUbpeMPva; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":69.69999999999999,"warning":null},{"id":"epoch-run-URoWjw9Htc6QPwABVcrybw","modelId":"qwen3.7-plus","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.7-plus","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.7-plus; run=URoWjw9Htc6QPwABVcrybw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.87878787878788,"warning":null},{"id":"epoch-run-Usx9KaiXvHZU4qrzgc4sLg","modelId":"gemma-4-26b-a4b-it","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"minimal","sourceLabel":"gemma-4-26b-a4b-it_minimal","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemma-4-26b-a4b-it_minimal; run=Usx9KaiXvHZU4qrzgc4sLg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":73.23232323232324,"warning":null},{"id":"epoch-run-Utgs6DuaQDDdi98ZWH22qL","modelId":"gemini-3.8-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"high","sourceLabel":"gemini-3.8-flash_high","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.8-flash_high; run=Utgs6DuaQDDdi98ZWH22qL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":68.42105263157895,"warning":null},{"id":"epoch-run-UTVSgirxQpTgmTHbgE9EUk","modelId":"kimi-k2.7-code","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"kimi-k2.7-code","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k2.7-code; run=UTVSgirxQpTgmTHbgE9EUk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12.195121951219512,"warning":null},{"id":"epoch-run-UUq99Qhq3qizcoJo5vdhuK","modelId":"glm-5.3","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"glm-5.3_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=glm-5.3_max; run=UUq99Qhq3qizcoJo5vdhuK; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":33,"warning":null},{"id":"epoch-run-UxakyoDNbLKtxnxeMsa7cU","modelId":"claude-opus-5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"claude-opus-5","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-5; run=UxakyoDNbLKtxnxeMsa7cU; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":33,"warning":null},{"id":"epoch-run-V6YuGpcu8MCbJNXKoJMA6b","modelId":"claude-sonnet-5","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-sonnet-5_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-sonnet-5_max; run=V6YuGpcu8MCbJNXKoJMA6b; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":65.6140350877193,"warning":null},{"id":"epoch-run-V8VuDYREHNne27eUQT8gir","modelId":"qwen3-30b-a3b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"Qwen3-30B-A3B_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Qwen3-30B-A3B_none; run=V8VuDYREHNne27eUQT8gir; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":1,"warning":null},{"id":"epoch-run-VBpT2WWYKBZtUxG9Z3svGh","modelId":"gpt-5.6-sol","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"gpt-5.6-sol_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.6-sol_max; run=VBpT2WWYKBZtUxG9Z3svGh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":89.12280701754386,"warning":null},{"id":"epoch-run-VcuyQvF8LWuYhQCx2FGDHh","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"low","sourceLabel":"gemini-3.1-flash-lite_low","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3.1-flash-lite_low; run=VcuyQvF8LWuYhQCx2FGDHh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22.45614035087719,"warning":null},{"id":"epoch-run-VFYhE54autgdYcMJNXicwU","modelId":"claude-opus-4-7","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"claude-opus-4-7_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-opus-4-7_max; run=VFYhE54autgdYcMJNXicwU; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":28.000000000000004,"warning":null},{"id":"epoch-run-VGeF8Xac4WcSAGgSXVdEBi","modelId":"gemini-3.1-pro","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"high","sourceLabel":"gemini-3.1-pro-preview_high","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=gemini-3.1-pro-preview_high; run=VGeF8Xac4WcSAGgSXVdEBi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":73.5,"warning":null},{"id":"epoch-run-VhBM9HgJ2RuSVwXriRXMVJ","modelId":"claude-haiku-4-5-20251001","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"thinking","sourceLabel":"claude-haiku-4-5-20251001_32K (thinking 32k)","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-haiku-4-5-20251001_32K; run=VhBM9HgJ2RuSVwXriRXMVJ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":12.6,"warning":null},{"id":"epoch-run-VhQBa9AViRt2UKSNpEAyjN","modelId":"qwen3-4b-instruct-2507","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3-4b-instruct-2507","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-4b-instruct-2507; run=VhQBa9AViRt2UKSNpEAyjN; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":45.83333333333333,"warning":null},{"id":"epoch-run-ViC6pxQZUVS3E9M9iEubF7","modelId":"claude-opus-4-8","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"claude-opus-4-8_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-opus-4-8_max; run=ViC6pxQZUVS3E9M9iEubF7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":53,"warning":null},{"id":"epoch-run-VJezHrJ5YPCbpui8pZgcJg","modelId":"claude-opus-4-7","benchmarkId":"epoch-gpqa-diamond-1-0-7-choice","level":"xhigh","sourceLabel":"claude-opus-4-7_xhigh","configuration":"Epoch AI Inspect; task 1.0.7; scorer choice; model=claude-opus-4-7_xhigh; run=VJezHrJ5YPCbpui8pZgcJg; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.15151515151516,"warning":null},{"id":"epoch-run-VjfWxdhdNerrh4huSHT8PT","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"unspecified","sourceLabel":"claude-sonnet-4-6","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=claude-sonnet-4-6; run=VjfWxdhdNerrh4huSHT8PT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":14.000000000000002,"warning":null},{"id":"epoch-run-VonoEhAsGSJ2FHU33qnhui","modelId":"qwen3.6-27b","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"qwen3.6-27b","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-27b; run=VonoEhAsGSJ2FHU33qnhui; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":35.08771929824561,"warning":null},{"id":"epoch-run-VRLKwMA8hJnNRpp8M3WDCw","modelId":"qwen3.5-397b-a17b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.5-397b-a17b_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-397b-a17b_none; run=VRLKwMA8hJnNRpp8M3WDCw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":13,"warning":null},{"id":"epoch-run-Vw7spGUnJyf3vuzSjTcj2F","modelId":"grok-4.3","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"grok-4.3_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=grok-4.3_high; run=Vw7spGUnJyf3vuzSjTcj2F; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.82575757575758,"warning":null},{"id":"epoch-run-W6mTanyjvXhasFBzHukv4S","modelId":"qwen3.7-max","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3.7-max","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.7-max; run=W6mTanyjvXhasFBzHukv4S; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":90.9090909090909,"warning":null},{"id":"epoch-run-WcCQQSHTFAhXk6qCWEeSLh","modelId":"gpt-5.6-terra","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"medium","sourceLabel":"gpt-5.6-terra_medium","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gpt-5.6-terra_medium; run=WcCQQSHTFAhXk6qCWEeSLh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":10,"warning":null},{"id":"epoch-run-WeP7Q27N5PzxSgg4ybgijX","modelId":"qwen3.6-27b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3.6-27b_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.6-27b_none; run=WeP7Q27N5PzxSgg4ybgijX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":84.84848484848484,"warning":null},{"id":"epoch-run-WfaJS4L7Xdz5ZBXgJMbRGb","modelId":"claude-opus-5","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"low","sourceLabel":"claude-opus-5_low","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-opus-5_low; run=WfaJS4L7Xdz5ZBXgJMbRGb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.87878787878788,"warning":null},{"id":"epoch-run-WgjFZzojpiv54XqUhvfuUG","modelId":"glm-5.2","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"glm-5.2_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=glm-5.2_max; run=WgjFZzojpiv54XqUhvfuUG; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34.2,"warning":null},{"id":"epoch-run-Wh3JxFdvxP688EWwE3t2Uk","modelId":"qwen3.6-27b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"qwen3.6-27b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-27b; run=Wh3JxFdvxP688EWwE3t2Uk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":22,"warning":null},{"id":"epoch-run-WjXdTPMnJUAT27azUKo3Ka","modelId":"qwen3.6-27b","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"qwen3.6-27b_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-27b_none; run=WjXdTPMnJUAT27azUKo3Ka; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":34.03508771929825,"warning":null},{"id":"epoch-run-WNE7cveVN8rsi7DmsFsFVy","modelId":"gemma-2-9b-it","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"gemma-2-9b-it","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=gemma-2-9b-it; run=WNE7cveVN8rsi7DmsFsFVy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":0.5555555555555556,"warning":null},{"id":"epoch-run-WueZbBM3NwMUZPveuagrZo","modelId":"gemini-3.1-pro","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"medium","sourceLabel":"gemini-3.1-pro-preview_medium","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3.1-pro-preview_medium; run=WueZbBM3NwMUZPveuagrZo; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":32,"warning":null},{"id":"epoch-run-WYs83xB6NwrkMNyQJtuMcQ","modelId":"deepseek-v4-flash","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"deepseek-v4-flash-0731_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=deepseek-v4-flash-0731_max; run=WYs83xB6NwrkMNyQJtuMcQ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":24.390243902439025,"warning":null},{"id":"epoch-run-WYTWr3Xk4qxymhMsm7vRQ2","modelId":"nemotron-3-ultra","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"nemotron-3-ultra","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=nemotron-3-ultra; run=WYTWr3Xk4qxymhMsm7vRQ2; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.66666666666667,"warning":null},{"id":"epoch-run-X29V6KG3aVe5Nv5r3tsLHX","modelId":"claude-fable-5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"claude-fable-5_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-fable-5_max; run=X29V6KG3aVe5Nv5r3tsLHX; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":52,"warning":null},{"id":"epoch-run-X2tQXGELXtEbc2VX6gARd7","modelId":"llama-3.1-70b-instruct","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"Llama-3.1-70B-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=Llama-3.1-70B-Instruct; run=X2tQXGELXtEbc2VX6gARd7; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":3.6111111111111107,"warning":null},{"id":"epoch-run-X3HfncZtnLKUPoUuRc9YsR","modelId":"qwen3-30b-a3b-instruct-2507","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3-30b-a3b-instruct-2507","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-30b-a3b-instruct-2507; run=X3HfncZtnLKUPoUuRc9YsR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":55.61868686868687,"warning":null},{"id":"epoch-run-X3RxRkt2pBUXYJjAQHsUo6","modelId":"kimi-k2.7-code","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"kimi-k2.7-code","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k2.7-code; run=X3RxRkt2pBUXYJjAQHsUo6; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":54.03508771929825,"warning":null},{"id":"epoch-run-X5FL4gkJQYjzJ7axz23rfd","modelId":"qwen3.5-122b-a10b","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.5-122b-a10b_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.5-122b-a10b_none; run=X5FL4gkJQYjzJ7axz23rfd; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17,"warning":null},{"id":"epoch-run-X6WHjwmjSHe7pF8R7F3zsT","modelId":"gemini-3.5-flash-lite","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"minimal","sourceLabel":"gemini-3.5-flash-lite_minimal","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.5-flash-lite_minimal; run=X6WHjwmjSHe7pF8R7F3zsT; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":21,"warning":null},{"id":"epoch-run-XaGuWDxPtqVvyxqdMncKFj","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_59K (thinking 59k)","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=claude-sonnet-4-5-20250929_59K; run=XaGuWDxPtqVvyxqdMncKFj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.32323232323232,"warning":null},{"id":"epoch-run-XbtWdvRz65dbPPnHcSBvmF","modelId":"qwen3.5-plus","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"non-reasoning","sourceLabel":"qwen3.5-plus_none","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.5-plus_none; run=XbtWdvRz65dbPPnHcSBvmF; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17,"warning":null},{"id":"epoch-run-XCSWtbDquA7FUiWfd7kh9q","modelId":"open-mistral-nemo-2407","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"open-mistral-nemo-2407","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=open-mistral-nemo-2407; run=XCSWtbDquA7FUiWfd7kh9q; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":29.892676767676768,"warning":null},{"id":"epoch-run-XfjRkSyP4ub4gDsWcgS7KY","modelId":"qwen3-30b-a3b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"Qwen3-30B-A3B","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Qwen3-30B-A3B; run=XfjRkSyP4ub4gDsWcgS7KY; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":62.77777777777778,"warning":null},{"id":"epoch-run-XGK9DjJHHVWr2LyT298ooL","modelId":"qwen3-14b","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"qwen3-14b","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3-14b; run=XGK9DjJHHVWr2LyT298ooL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":63.76262626262626,"warning":null},{"id":"epoch-run-XjFqou6MyT2XLpkUsCrgxM","modelId":"glm-5.2","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"glm-5.2_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=glm-5.2_max; run=XjFqou6MyT2XLpkUsCrgxM; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.38888888888889,"warning":null},{"id":"epoch-run-XneEig6pACkAWeekvgCwNk","modelId":"kimi-k2.7-code","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"unspecified","sourceLabel":"kimi-k2.7-code","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=kimi-k2.7-code; run=XneEig6pACkAWeekvgCwNk; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":87.87878787878788,"warning":null},{"id":"epoch-run-XnQVH5qSfxVjpzoPwUEmnh","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-sonnet-4-6_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-4-6_max; run=XnQVH5qSfxVjpzoPwUEmnh; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":71.11111111111111,"warning":null},{"id":"epoch-run-XQEGUQjpXupjdyKoGuSmum","modelId":"claude-sonnet-4-5-20250929","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"thinking","sourceLabel":"claude-sonnet-4-5-20250929_59K (thinking 59k)","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-sonnet-4-5-20250929_59K; run=XQEGUQjpXupjdyKoGuSmum; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":30.7,"warning":null},{"id":"epoch-run-XRutLYUVUePe69APTSTw8S","modelId":"claude-sonnet-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"max","sourceLabel":"claude-sonnet-5_max","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-5_max; run=XRutLYUVUePe69APTSTw8S; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80,"warning":null},{"id":"epoch-run-XRVSYnR4bhQ8Zb62Un7GrS","modelId":"gpt-5.5","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"none","sourceLabel":"gpt-5.5_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.5_none; run=XRVSYnR4bhQ8Zb62Un7GrS; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":10,"warning":null},{"id":"epoch-run-XwemU6ABotEuG9o5TRLG2r","modelId":"minimax-m3","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"MiniMax-M3","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=MiniMax-M3; run=XwemU6ABotEuG9o5TRLG2r; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":14.000000000000002,"warning":null},{"id":"epoch-run-XWpHpVPCaVjcwPpdpXuuGH","modelId":"qwen3-235b-a22b-thinking-2507","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-3-model-extracted-exact-match","level":"unspecified","sourceLabel":"Qwen3-235B-A22B-Thinking-2507","configuration":"Epoch AI Inspect; task 1.0.3; scorer model_extracted_exact_match; model=Qwen3-235B-A22B-Thinking-2507; run=XWpHpVPCaVjcwPpdpXuuGH; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":86.66666666666667,"warning":null},{"id":"epoch-run-XyVL3VffJ6UboY97vxpohL","modelId":"gemini-3.7-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"high","sourceLabel":"gemini-3.7-flash_high","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3.7-flash_high; run=XyVL3VffJ6UboY97vxpohL; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":94.82323232323232,"warning":null},{"id":"epoch-run-Y39ZRp553ULpUDBV2XrBbc","modelId":"grok-4.3","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"high","sourceLabel":"grok-4.3_high","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=grok-4.3_high; run=Y39ZRp553ULpUDBV2XrBbc; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":33.2,"warning":null},{"id":"epoch-run-YBMTDnW5LmCN6tBp2QYHzi","modelId":"qwen3.5-9b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.5-9B_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.5-9B_none; run=YBMTDnW5LmCN6tBp2QYHzi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":61.66666666666667,"warning":null},{"id":"epoch-run-YBqiCXPjMUSAgAjDUoz5sy","modelId":"gemini-3.6-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"high","sourceLabel":"gemini-3.6-flash_high","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gemini-3.6-flash_high; run=YBqiCXPjMUSAgAjDUoz5sy; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":30,"warning":null},{"id":"epoch-run-YC2u9wykbYQg4gdkf76j26","modelId":"glm-5.3-flash","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"glm-5.3-flash_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=glm-5.3-flash_max; run=YC2u9wykbYQg4gdkf76j26; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":55.78947368421052,"warning":null},{"id":"epoch-run-Yd3YzZmLa8D7eiZWo77WSm","modelId":"deepseek-r1-0528-qwen3-8b","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"deepseek-r1-0528-qwen3-8b","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=deepseek-r1-0528-qwen3-8b; run=Yd3YzZmLa8D7eiZWo77WSm; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":3,"warning":null},{"id":"epoch-run-YdcyYXLzqfPUSSgGv4MTED","modelId":"claude-sonnet-5","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"max","sourceLabel":"claude-sonnet-5_max","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-sonnet-5_max; run=YdcyYXLzqfPUSSgGv4MTED; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":35,"warning":null},{"id":"epoch-run-YDQJAMgMjLaikPkeVDbAjr","modelId":"glm-5.2","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"glm-5.2_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=glm-5.2_none; run=YDQJAMgMjLaikPkeVDbAjr; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":71.21212121212122,"warning":null},{"id":"epoch-run-YdyvoMQ4mA5V8Ymg6Tksxu","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"low","sourceLabel":"claude-sonnet-4-6_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=claude-sonnet-4-6_low; run=YdyvoMQ4mA5V8Ymg6Tksxu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":16,"warning":null},{"id":"epoch-run-YFmtuHAcUZeGwPBe9Jbcxw","modelId":"gemini-3.1-flash-lite","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"high","sourceLabel":"gemini-3.1-flash-lite_high","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3.1-flash-lite_high; run=YFmtuHAcUZeGwPBe9Jbcxw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20,"warning":null},{"id":"epoch-run-Yhds8GYkCXWgRQhuLiURua","modelId":"qwen3.7-flash","benchmarkId":"epoch-gpqa-diamond-1-0-11-choice","level":"non-reasoning","sourceLabel":"qwen3.7-flash_none","configuration":"Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.7-flash_none; run=Yhds8GYkCXWgRQhuLiURua; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":80.8080808080808,"warning":null},{"id":"epoch-run-YLAk5J3Wd8EruVXee8bAQb","modelId":"gpt-5.6-luna","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"gpt-5.6-luna_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.6-luna_max; run=YLAk5J3Wd8EruVXee8bAQb; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":82.10526315789474,"warning":null},{"id":"epoch-run-YRvn36dmMyDbS5e4XkF4Xi","modelId":"qwen3.6-35b-a3b","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"qwen3.6-35b-a3b_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-35b-a3b_none; run=YRvn36dmMyDbS5e4XkF4Xi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":20.350877192982455,"warning":null},{"id":"epoch-run-YwHKNFQjbat97wVLqachmi","modelId":"gpt-5.6-luna","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"none","sourceLabel":"gpt-5.6-luna_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.6-luna_none; run=YwHKNFQjbat97wVLqachmi; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":39.64912280701755,"warning":null},{"id":"epoch-run-Z4xfwTke5pR6RrY952bttA","modelId":"qwen3.6-plus","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"non-reasoning","sourceLabel":"qwen3.6-plus_none","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-plus_none; run=Z4xfwTke5pR6RrY952bttA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":32.280701754385966,"warning":null},{"id":"epoch-run-Z5FAHm8aqmk8NUUm7tojng","modelId":"claude-opus-5","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"claude-opus-5_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-opus-5_low; run=Z5FAHm8aqmk8NUUm7tojng; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":93.33333333333333,"warning":null},{"id":"epoch-run-Z6S3nMC2tnkpKUixCPLiDj","modelId":"gpt-5.6-terra","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-5.6-terra_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-terra_low; run=Z6S3nMC2tnkpKUixCPLiDj; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":88.88888888888889,"warning":null},{"id":"epoch-run-ZavSMMq9jk5s9WSbARZr6X","modelId":"gemini-3.7-flash","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-agent-submitted-next-move-scorer","level":"high","sourceLabel":"gemini-3.7-flash_high","configuration":"Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=gemini-3.7-flash_high; run=ZavSMMq9jk5s9WSbARZr6X; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":37,"warning":null},{"id":"epoch-run-Zb2AKwa942D7dBTTcebAba","modelId":"grok-4.6","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"xhigh","sourceLabel":"grok-4.6_xhigh","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=grok-4.6_xhigh; run=Zb2AKwa942D7dBTTcebAba; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":65.96491228070175,"warning":null},{"id":"epoch-run-ZczEhu69FQ9Cnns8NT6ew4","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"unspecified","sourceLabel":"gemini-3-flash-preview","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3-flash-preview; run=ZczEhu69FQ9Cnns8NT6ew4; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":17.073170731707318,"warning":null},{"id":"epoch-run-ZfPv4GCnueHrnaoV2dBdVw","modelId":"qwen3.7-flash","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"qwen3.7-flash_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.7-flash_none; run=ZfPv4GCnueHrnaoV2dBdVw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":9,"warning":null},{"id":"epoch-run-Zftz2yk4X5NF28JQzjN3hZ","modelId":"claude-opus-5","benchmarkId":"epoch-simpleqa-verified-1-0-0-simpleqa-scorer","level":"max","sourceLabel":"claude-opus-5_max","configuration":"Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=claude-opus-5_max; run=Zftz2yk4X5NF28JQzjN3hZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":59.9,"warning":null},{"id":"epoch-run-ZgU8BagFmaj7BE94y3JDZA","modelId":"gpt-5.6-luna","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"low","sourceLabel":"gpt-5.6-luna_low","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gpt-5.6-luna_low; run=ZgU8BagFmaj7BE94y3JDZA; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":66.66666666666666,"warning":null},{"id":"epoch-run-ZjsXQpZ7SsejXDo52aetZZ","modelId":"llama-3.3-70b-instruct","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-0-0-model-graded","level":"unspecified","sourceLabel":"Llama-3.3-70B-Instruct","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_graded; model=Llama-3.3-70B-Instruct; run=ZjsXQpZ7SsejXDo52aetZZ; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":5.138888888888888,"warning":null},{"id":"epoch-run-ZkNQ7GER7Mc9FSPmpUzgKH","modelId":"claude-opus-4-7","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"max","sourceLabel":"claude-opus-4-7_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-opus-4-7_max; run=ZkNQ7GER7Mc9FSPmpUzgKH; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":70.17543859649122,"warning":null},{"id":"epoch-run-ZMRExFd2WEEwTRSQPLXXwu","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-chess-puzzles-1-0-0-model-extracted-exact-match","level":"unspecified","sourceLabel":"gemini-3-flash-preview","configuration":"Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=gemini-3-flash-preview; run=ZMRExFd2WEEwTRSQPLXXwu; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":38,"warning":null},{"id":"epoch-run-ZQMcTQjHcDSevCN2dYYHKY","modelId":"gemini-3-flash-preview","benchmarkId":"epoch-mystery-game-puzzles-1-0-4-exact-match-next-move-scorer","level":"low","sourceLabel":"gemini-3-flash-preview_low","configuration":"Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3-flash-preview_low; run=ZQMcTQjHcDSevCN2dYYHKY; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":26,"warning":null},{"id":"epoch-run-ZryXhNUpPedPvGhbqdNBEw","modelId":"gpt-5.6-luna","benchmarkId":"epoch-frontiermath-tiers-1-3-v2-2-0-0-verification-code","level":"low","sourceLabel":"gpt-5.6-luna_low","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.6-luna_low; run=ZryXhNUpPedPvGhbqdNBEw; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":41.40350877192983,"warning":null},{"id":"epoch-run-Zs5fCvNzaz8LhqgwDSAztU","modelId":"claude-sonnet-4-6","benchmarkId":"epoch-simpleqa-verified-1-2-0-simpleqa-scorer","level":"max","sourceLabel":"claude-sonnet-4-6_max","configuration":"Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-sonnet-4-6_max; run=Zs5fCvNzaz8LhqgwDSAztU; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":32.800000000000004,"warning":null},{"id":"epoch-run-ZS6cAYkdeNAeRNz7AWQ4LR","modelId":"magistral-small-2509","benchmarkId":"epoch-chess-puzzles-1-1-6-model-extracted-exact-match","level":"unspecified","sourceLabel":"magistral-small-2509","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=magistral-small-2509; run=ZS6cAYkdeNAeRNz7AWQ4LR; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":3,"warning":null},{"id":"epoch-run-ZUJxsJDpHnLXxNiDcvj22W","modelId":"gemma-2-27b-it","benchmarkId":"epoch-gpqa-diamond-1-0-0-choice","level":"unspecified","sourceLabel":"gemma-2-27b-it","configuration":"Epoch AI Inspect; task 1.0.0; scorer choice; model=gemma-2-27b-it; run=ZUJxsJDpHnLXxNiDcvj22W; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":36.48989898989899,"warning":null},{"id":"epoch-run-ZUygpkXqg3NjchXXfedAWV","modelId":"gpt-5.6-terra","benchmarkId":"epoch-frontiermath-tier-4-v2-2-0-0-verification-code","level":"max","sourceLabel":"gpt-5.6-terra_max","configuration":"Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gpt-5.6-terra_max; run=ZUygpkXqg3NjchXXfedAWV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":70.73170731707317,"warning":null},{"id":"epoch-run-ZzbWv2QGVfg4o2DTX45nqV","modelId":"qwen3-30b-a3b","benchmarkId":"epoch-otis-mock-aime-2024-2025-1-1-6-model-extracted-exact-match","level":"non-reasoning","sourceLabel":"Qwen3-30B-A3B_none","configuration":"Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=Qwen3-30B-A3B_none; run=ZzbWv2QGVfg4o2DTX45nqV; mean accuracy; https://epoch.ai/data/benchmarks.csv","score":25.555555555555554,"warning":null},{"id":"vals-finance-agent-v2:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.8-flash\",\"evaluatorModel\":\"google/gemini-3.8-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":61.435,"warning":null},{"id":"vals-finance-agent-v2:meta/muse_spark_1_2","modelId":"muse-spark-1.2","benchmarkId":"vals-finance-agent-v2","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.2\",\"evaluatorModel\":\"meta/muse_spark_1_2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":60.599,"warning":null},{"id":"vals-finance-agent-v2:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.7-flash\",\"evaluatorModel\":\"google/gemini-3.7-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":59.042,"warning":null},{"id":"vals-finance-agent-v2:meta/muse_spark_1_3","modelId":"muse-spark-1.3","benchmarkId":"vals-finance-agent-v2","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.3\",\"evaluatorModel\":\"meta/muse_spark_1_3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":58.901,"warning":null},{"id":"vals-finance-agent-v2:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"{\"checkpoint\":\"claude-fable-5-1\",\"evaluatorModel\":\"anthropic/claude-fable-5-1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":58.877,"warning":null},{"id":"vals-finance-agent-v2:anthropic/claude-opus-5","modelId":"claude-opus-5","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"Claude Opus 5 (max)","configuration":"{\"checkpoint\":\"claude-opus-5\",\"evaluatorModel\":\"anthropic/claude-opus-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":58.633,"warning":"One run-task used an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-finance-agent-v2:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash\",\"evaluatorModel\":\"google/gemini-3.5-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":57.861,"warning":null},{"id":"vals-finance-agent-v2:zai/glm-5.3-flash","modelId":"glm-5.3-flash","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"{\"checkpoint\":\"glm-5.3-flash\",\"evaluatorModel\":\"zai/glm-5.3-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Fireworks AI\",\"harness\":null}","score":57.85,"warning":null},{"id":"vals-finance-agent-v2:meta/muse_spark_1_1","modelId":"muse-spark-1.1","benchmarkId":"vals-finance-agent-v2","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"{\"checkpoint\":\"muse_spark_1_1\",\"evaluatorModel\":\"meta/muse_spark_1_1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":57.207,"warning":null},{"id":"vals-finance-agent-v2:anthropic/claude-fable-5","modelId":"claude-fable-5","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"{\"checkpoint\":\"claude-fable-5\",\"evaluatorModel\":\"anthropic/claude-fable-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":56.314,"warning":null},{"id":"vals-finance-agent-v2:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.6-flash\",\"evaluatorModel\":\"google/gemini-3.6-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":56.296,"warning":null},{"id":"vals-finance-agent-v2:zai/glm-5.3","modelId":"glm-5.3","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"{\"checkpoint\":\"glm-5.3\",\"evaluatorModel\":\"zai/glm-5.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Fireworks AI\",\"harness\":null}","score":55.84,"warning":null},{"id":"vals-finance-agent-v2:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"{\"checkpoint\":\"gpt-5.6-luna\",\"evaluatorModel\":\"openai/gpt-5.6-luna\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":55.044,"warning":null},{"id":"vals-finance-agent-v2:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"{\"checkpoint\":\"gpt-5.6-terra\",\"evaluatorModel\":\"openai/gpt-5.6-terra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":54.436,"warning":null},{"id":"vals-finance-agent-v2:kimi/kimi-k3","modelId":"kimi-k3","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"Kimi K3 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k3\",\"evaluatorModel\":\"kimi/kimi-k3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":262144,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":54.36,"warning":null},{"id":"vals-finance-agent-v2:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-8\",\"evaluatorModel\":\"anthropic/claude-opus-4-8\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":53.918,"warning":null},{"id":"vals-finance-agent-v2:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-5\",\"evaluatorModel\":\"anthropic/claude-sonnet-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":53.909,"warning":null},{"id":"vals-finance-agent-v2:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"{\"checkpoint\":\"gpt-5.6-sol\",\"evaluatorModel\":\"openai/gpt-5.6-sol\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":53.756,"warning":null},{"id":"vals-finance-agent-v2:grok/grok-4.6","modelId":"grok-4.6","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"{\"checkpoint\":\"grok-4.6\",\"evaluatorModel\":\"grok/grok-4.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":53.682,"warning":null},{"id":"vals-finance-agent-v2:openai/gpt-6-astra","modelId":"gpt-6-astra","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"{\"checkpoint\":\"gpt-6-astra\",\"evaluatorModel\":\"openai/gpt-6-astra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":53.54,"warning":null},{"id":"vals-finance-agent-v2:openai/gpt-5.5","modelId":"gpt-5.5","benchmarkId":"vals-finance-agent-v2","level":"xhigh","sourceLabel":"GPT 5.5 (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.5\",\"evaluatorModel\":\"openai/gpt-5.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":51.76,"warning":null},{"id":"vals-finance-agent-v2:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Claude Opus 4.7 (high)","configuration":"{\"checkpoint\":\"claude-opus-4-7\",\"evaluatorModel\":\"anthropic/claude-opus-4-7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"high\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":51.509,"warning":null},{"id":"vals-finance-agent-v2:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-4-6\",\"evaluatorModel\":\"anthropic/claude-sonnet-4-6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":true,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":51.035,"warning":null},{"id":"vals-finance-agent-v2:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","benchmarkId":"vals-finance-agent-v2","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (max)","configuration":"{\"checkpoint\":\"deepseek-v4-pro\",\"evaluatorModel\":\"deepseek/deepseek-v4-pro-0813\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":50.393,"warning":null},{"id":"vals-finance-agent-v2:zai/glm-5.2","modelId":"glm-5.2","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"GLM 5.2 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.2\",\"evaluatorModel\":\"zai/glm-5.2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":49.699,"warning":null},{"id":"vals-finance-agent-v2:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"{\"checkpoint\":\"deepseek-v4-flash\",\"evaluatorModel\":\"deepseek/deepseek-v4-flash-0731\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":49.517,"warning":null},{"id":"vals-finance-agent-v2:grok/grok-4.5","modelId":"grok-4.5","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"{\"checkpoint\":\"grok-4.5\",\"evaluatorModel\":\"grok/grok-4.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":48.349,"warning":null},{"id":"vals-finance-agent-v2:minimax/MiniMax-M3","modelId":"minimax-m3","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"MiniMax-M3 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M3\",\"evaluatorModel\":\"minimax/MiniMax-M3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":512000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":48.269,"warning":null},{"id":"vals-finance-agent-v2:alibaba/qwen3.7-max","modelId":"qwen3.7-max","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"Qwen 3.7 Max (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-max\",\"evaluatorModel\":\"alibaba/qwen3.7-max\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":47.776,"warning":null},{"id":"vals-finance-agent-v2:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Gemini 3.5 Flash Lite (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash-lite\",\"evaluatorModel\":\"google/gemini-3.5-flash-lite\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":47.442,"warning":null},{"id":"vals-finance-agent-v2:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","benchmarkId":"vals-finance-agent-v2","level":"xhigh","sourceLabel":"GPT 5.4 Mini (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-mini-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-mini-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":45.36,"warning":null},{"id":"vals-finance-agent-v2:kimi/kimi-k2.6","modelId":"kimi-k2.6","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"Kimi K2.6 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.6\",\"evaluatorModel\":\"kimi/kimi-k2.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":44.899,"warning":null},{"id":"vals-finance-agent-v2:zai/glm-5.1","modelId":"glm-5.1","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"GLM 5.1 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.1\",\"evaluatorModel\":\"zai/glm-5.1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":44.792,"warning":null},{"id":"vals-finance-agent-v2:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Gemini 3.1 Pro Preview (02/26) (high)","configuration":"{\"checkpoint\":\"gemini-3.1-pro-preview\",\"evaluatorModel\":\"google/gemini-3.1-pro-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":42.982,"warning":null},{"id":"vals-finance-agent-v2:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Gemini 3 Flash (12/25) (high)","configuration":"{\"checkpoint\":\"gemini-3-flash-preview\",\"evaluatorModel\":\"google/gemini-3-flash-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":42.551,"warning":null},{"id":"vals-finance-agent-v2:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"MiMo V2.5 Pro (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5-pro\",\"evaluatorModel\":\"xiaomi/mimo-v2.5-pro\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":41.502,"warning":null},{"id":"vals-finance-agent-v2:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"Qwen 3.6 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.6-plus\",\"evaluatorModel\":\"alibaba/qwen3.6-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":40.846,"warning":null},{"id":"vals-finance-agent-v2:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-plus\",\"evaluatorModel\":\"alibaba/qwen3.7-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":38.22,"warning":null},{"id":"vals-finance-agent-v2:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"GPT 5.4 Nano (high)","configuration":"{\"checkpoint\":\"gpt-5.4-nano-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-nano-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":38.217,"warning":null},{"id":"vals-finance-agent-v2:grok/grok-4.3","modelId":"grok-4.3","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"{\"checkpoint\":\"grok-4.3\",\"evaluatorModel\":\"grok/grok-4.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":37.728,"warning":null},{"id":"vals-finance-agent-v2:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"MiMo V2.5 (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5\",\"evaluatorModel\":\"xiaomi/mimo-v2.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":36.728,"warning":null},{"id":"vals-finance-agent-v2:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","benchmarkId":"vals-finance-agent-v2","level":"high","sourceLabel":"Mistral Medium 3.5 (high)","configuration":"{\"checkpoint\":\"mistral-medium-3.5\",\"evaluatorModel\":\"mistralai/mistral-medium-3.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"Mistral AI\",\"harness\":null}","score":32.103,"warning":null},{"id":"vals-finance-agent-v2:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"Claude Haiku 4.5 (Thinking) (unspecified)","configuration":"{\"checkpoint\":\"claude-haiku-4-5-20251001\",\"evaluatorModel\":\"anthropic/claude-haiku-4-5-20251001-thinking\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":64000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":31.01,"warning":null},{"id":"vals-finance-agent-v2:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"Grok 4.20 (Reasoning) (unspecified)","configuration":"{\"checkpoint\":\"grok-4.20-0309-reasoning\",\"evaluatorModel\":\"grok/grok-4.20-0309-reasoning\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":2000000,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":28.492,"warning":null},{"id":"vals-finance-agent-v2:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","benchmarkId":"vals-finance-agent-v2","level":"unspecified","sourceLabel":"MiniMax-M2.7 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M2.7\",\"evaluatorModel\":\"minimax/MiniMax-M2.7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":196608,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":27.887,"warning":null},{"id":"vals-code-migration-v1:openai/gpt-6-astra","modelId":"gpt-6-astra","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"{\"checkpoint\":\"gpt-6-astra\",\"evaluatorModel\":\"openai/gpt-6-astra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":67.74,"warning":null},{"id":"vals-code-migration-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"Claude Opus 5 (max)","configuration":"{\"checkpoint\":\"claude-opus-5\",\"evaluatorModel\":\"anthropic/claude-opus-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":57.473,"warning":null},{"id":"vals-code-migration-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"{\"checkpoint\":\"claude-fable-5\",\"evaluatorModel\":\"anthropic/claude-fable-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":55.065,"warning":null},{"id":"vals-code-migration-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"{\"checkpoint\":\"claude-fable-5-1\",\"evaluatorModel\":\"anthropic/claude-fable-5-1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":54.607,"warning":null},{"id":"vals-code-migration-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"{\"checkpoint\":\"gpt-5.6-sol\",\"evaluatorModel\":\"openai/gpt-5.6-sol\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":52.916,"warning":null},{"id":"vals-code-migration-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"{\"checkpoint\":\"gpt-5.6-terra\",\"evaluatorModel\":\"openai/gpt-5.6-terra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":47.804,"warning":null},{"id":"vals-code-migration-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-8\",\"evaluatorModel\":\"anthropic/claude-opus-4-8\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":47.25,"warning":null},{"id":"vals-code-migration-v1:openai/gpt-5.5","modelId":"gpt-5.5","benchmarkId":"vals-code-migration-v1","level":"xhigh","sourceLabel":"GPT 5.5 (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.5\",\"evaluatorModel\":\"openai/gpt-5.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":45.161,"warning":null},{"id":"vals-code-migration-v1:grok/grok-4.6","modelId":"grok-4.6","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"{\"checkpoint\":\"grok-4.6\",\"evaluatorModel\":\"grok/grok-4.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":44.572,"warning":null},{"id":"vals-code-migration-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"{\"checkpoint\":\"gpt-5.6-luna\",\"evaluatorModel\":\"openai/gpt-5.6-luna\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":44.55,"warning":null},{"id":"vals-code-migration-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-5\",\"evaluatorModel\":\"anthropic/claude-sonnet-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":44.392,"warning":null},{"id":"vals-code-migration-v1:zai/glm-5.3","modelId":"glm-5.3","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"{\"checkpoint\":\"glm-5.3\",\"evaluatorModel\":\"zai/glm-5.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":44.222,"warning":null},{"id":"vals-code-migration-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"Claude Opus 4.7 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-7\",\"evaluatorModel\":\"anthropic/claude-opus-4-7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":43.878,"warning":null},{"id":"vals-code-migration-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (max)","configuration":"{\"checkpoint\":\"deepseek-v4-pro\",\"evaluatorModel\":\"deepseek/deepseek-v4-pro-0813\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":41.54,"warning":null},{"id":"vals-code-migration-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-4-6\",\"evaluatorModel\":\"anthropic/claude-sonnet-4-6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":true,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":39.892,"warning":null},{"id":"vals-code-migration-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"{\"checkpoint\":\"deepseek-v4-flash\",\"evaluatorModel\":\"deepseek/deepseek-v4-flash-0731\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":38.631,"warning":null},{"id":"vals-code-migration-v1:zai/glm-5.2","modelId":"glm-5.2","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"GLM 5.2 (max)","configuration":"{\"checkpoint\":\"glm-5.2\",\"evaluatorModel\":\"zai/glm-5.2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":37.87,"warning":null},{"id":"vals-code-migration-v1:grok/grok-4.5","modelId":"grok-4.5","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"{\"checkpoint\":\"grok-4.5\",\"evaluatorModel\":\"grok/grok-4.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":36.596,"warning":null},{"id":"vals-code-migration-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.8-flash\",\"evaluatorModel\":\"google/gemini-3.8-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":36.546,"warning":null},{"id":"vals-code-migration-v1:openai/gpt-5.4-2026-03-05","modelId":"gpt-5.4","benchmarkId":"vals-code-migration-v1","level":"xhigh","sourceLabel":"GPT 5.4 (xhigh) (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-2026-03-05\",\"evaluatorModel\":\"openai/gpt-5.4-2026-03-05\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":34.984,"warning":null},{"id":"vals-code-migration-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.7-flash\",\"evaluatorModel\":\"google/gemini-3.7-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":34.8,"warning":null},{"id":"vals-code-migration-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","benchmarkId":"vals-code-migration-v1","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"{\"checkpoint\":\"muse_spark_1_1\",\"evaluatorModel\":\"meta/muse_spark_1_1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":31.115,"warning":null},{"id":"vals-code-migration-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.6-flash\",\"evaluatorModel\":\"google/gemini-3.6-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":30.928,"warning":null},{"id":"vals-code-migration-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","benchmarkId":"vals-code-migration-v1","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.2\",\"evaluatorModel\":\"meta/muse_spark_1_2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":29.954,"warning":null},{"id":"vals-code-migration-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"Kimi K2.6 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.6\",\"evaluatorModel\":\"kimi/kimi-k2.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":27.768,"warning":null},{"id":"vals-code-migration-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash\",\"evaluatorModel\":\"google/gemini-3.5-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":26.745,"warning":null},{"id":"vals-code-migration-v1:zai/glm-5.1","modelId":"glm-5.1","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"GLM 5.1 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.1\",\"evaluatorModel\":\"zai/glm-5.1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":25.768,"warning":null},{"id":"vals-code-migration-v1:kimi/kimi-k2.7-code","modelId":"kimi-k2.7-code","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"Kimi K2.7 Code (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.7-code\",\"evaluatorModel\":\"kimi/kimi-k2.7-code\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":32768,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":25.392,"warning":null},{"id":"vals-code-migration-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"MiMo V2.5 Pro (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5-pro\",\"evaluatorModel\":\"xiaomi/mimo-v2.5-pro\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":21.557,"warning":null},{"id":"vals-code-migration-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"{\"checkpoint\":\"glm-5.3-flash\",\"evaluatorModel\":\"zai/glm-5.3-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":20.515,"warning":null},{"id":"vals-code-migration-v1:minimax/MiniMax-M3","modelId":"minimax-m3","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"MiniMax-M3 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M3\",\"evaluatorModel\":\"minimax/MiniMax-M3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":512000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":19.925,"warning":null},{"id":"vals-code-migration-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Gemini 3.1 Pro Preview (02/26) (high)","configuration":"{\"checkpoint\":\"gemini-3.1-pro-preview\",\"evaluatorModel\":\"google/gemini-3.1-pro-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":17.313,"warning":null},{"id":"vals-code-migration-v1:kimi/kimi-k3","modelId":"kimi-k3","benchmarkId":"vals-code-migration-v1","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"{\"checkpoint\":\"kimi-k3\",\"evaluatorModel\":\"kimi/kimi-k3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":262144,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":16.099,"warning":null},{"id":"vals-code-migration-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"GPT 5.4 Nano (high)","configuration":"{\"checkpoint\":\"gpt-5.4-nano-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-nano-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":14.467,"warning":null},{"id":"vals-code-migration-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"MiMo V2.5 (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5\",\"evaluatorModel\":\"xiaomi/mimo-v2.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":14.228,"warning":null},{"id":"vals-code-migration-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Max (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-max\",\"evaluatorModel\":\"alibaba/qwen3.7-max\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":13.069,"warning":null},{"id":"vals-code-migration-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","benchmarkId":"vals-code-migration-v1","level":"xhigh","sourceLabel":"GPT 5.4 Mini (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-mini-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-mini-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":12.936,"warning":null},{"id":"vals-code-migration-v1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-plus\",\"evaluatorModel\":\"alibaba/qwen3.7-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":12.856,"warning":null},{"id":"vals-code-migration-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"Qwen 3.6 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.6-plus\",\"evaluatorModel\":\"alibaba/qwen3.6-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":11.102,"warning":null},{"id":"vals-code-migration-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"MiniMax-M2.7 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M2.7\",\"evaluatorModel\":\"minimax/MiniMax-M2.7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":8.685,"warning":null},{"id":"vals-code-migration-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"Claude Haiku 4.5 (Thinking) (unspecified)","configuration":"{\"checkpoint\":\"claude-haiku-4-5-20251001\",\"evaluatorModel\":\"anthropic/claude-haiku-4-5-20251001-thinking\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":64000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":7.551,"warning":null},{"id":"vals-code-migration-v1:grok/grok-4.3","modelId":"grok-4.3","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"{\"checkpoint\":\"grok-4.3\",\"evaluatorModel\":\"grok/grok-4.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":6.795,"warning":null},{"id":"vals-code-migration-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Gemini 3 Flash (12/25) (high)","configuration":"{\"checkpoint\":\"gemini-3-flash-preview\",\"evaluatorModel\":\"google/gemini-3-flash-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":6.391,"warning":null},{"id":"vals-code-migration-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Gemini 3.5 Flash Lite (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash-lite\",\"evaluatorModel\":\"google/gemini-3.5-flash-lite\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":6.148,"warning":null},{"id":"vals-code-migration-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","benchmarkId":"vals-code-migration-v1","level":"high","sourceLabel":"Mistral Medium 3.5 (high)","configuration":"{\"checkpoint\":\"mistral-medium-3.5\",\"evaluatorModel\":\"mistralai/mistral-medium-3.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"Mistral AI\",\"harness\":null}","score":5.127,"warning":null},{"id":"vals-code-migration-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","benchmarkId":"vals-code-migration-v1","level":"unspecified","sourceLabel":"Grok 4.20 (Reasoning) (unspecified)","configuration":"{\"checkpoint\":\"grok-4.20-0309-reasoning\",\"evaluatorModel\":\"grok/grok-4.20-0309-reasoning\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":2000000,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":0.314,"warning":null},{"id":"vals-legal-research-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"Claude Opus 5 (max)","configuration":"{\"checkpoint\":\"claude-opus-5\",\"evaluatorModel\":\"anthropic/claude-opus-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":55.288,"warning":null},{"id":"vals-legal-research-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"{\"checkpoint\":\"claude-fable-5-1\",\"evaluatorModel\":\"anthropic/claude-fable-5-1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":55.288,"warning":null},{"id":"vals-legal-research-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"{\"checkpoint\":\"claude-fable-5\",\"evaluatorModel\":\"anthropic/claude-fable-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":49.519,"warning":null},{"id":"vals-legal-research-v1:zai/glm-5.3","modelId":"glm-5.3","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"{\"checkpoint\":\"glm-5.3\",\"evaluatorModel\":\"zai/glm-5.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":49.038,"warning":null},{"id":"vals-legal-research-v1:grok/grok-4.6","modelId":"grok-4.6","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"{\"checkpoint\":\"grok-4.6\",\"evaluatorModel\":\"grok/grok-4.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":48.077,"warning":null},{"id":"vals-legal-research-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"{\"checkpoint\":\"gpt-5.6-sol\",\"evaluatorModel\":\"openai/gpt-5.6-sol\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":48.077,"warning":null},{"id":"vals-legal-research-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"{\"checkpoint\":\"glm-5.3-flash\",\"evaluatorModel\":\"zai/glm-5.3-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":45.192,"warning":null},{"id":"vals-legal-research-v1:kimi/kimi-k3","modelId":"kimi-k3","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"Kimi K3 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k3\",\"evaluatorModel\":\"kimi/kimi-k3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":262144,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":44.231,"warning":null},{"id":"vals-legal-research-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","benchmarkId":"vals-legal-research-v1","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.2\",\"evaluatorModel\":\"meta/muse_spark_1_2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":43.75,"warning":null},{"id":"vals-legal-research-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-8\",\"evaluatorModel\":\"anthropic/claude-opus-4-8\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":43.75,"warning":null},{"id":"vals-legal-research-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-5\",\"evaluatorModel\":\"anthropic/claude-sonnet-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":41.827,"warning":null},{"id":"vals-legal-research-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"{\"checkpoint\":\"gpt-5.6-terra\",\"evaluatorModel\":\"openai/gpt-5.6-terra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":41.346,"warning":null},{"id":"vals-legal-research-v1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","benchmarkId":"vals-legal-research-v1","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.3\",\"evaluatorModel\":\"meta/muse_spark_1_3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":40.865,"warning":null},{"id":"vals-legal-research-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (max)","configuration":"{\"checkpoint\":\"deepseek-v4-pro\",\"evaluatorModel\":\"deepseek/deepseek-v4-pro-0813\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":40.865,"warning":null},{"id":"vals-legal-research-v1:openai/gpt-5.5","modelId":"gpt-5.5","benchmarkId":"vals-legal-research-v1","level":"xhigh","sourceLabel":"GPT 5.5 (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.5\",\"evaluatorModel\":\"openai/gpt-5.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":40.385,"warning":null},{"id":"vals-legal-research-v1:openai/gpt-6-astra","modelId":"gpt-6-astra","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"{\"checkpoint\":\"gpt-6-astra\",\"evaluatorModel\":\"openai/gpt-6-astra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":39.423,"warning":null},{"id":"vals-legal-research-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.8-flash\",\"evaluatorModel\":\"google/gemini-3.8-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":38.942,"warning":null},{"id":"vals-legal-research-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"Claude Opus 4.7 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-7\",\"evaluatorModel\":\"anthropic/claude-opus-4-7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":38.462,"warning":null},{"id":"vals-legal-research-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-4-6\",\"evaluatorModel\":\"anthropic/claude-sonnet-4-6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":true,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":38.462,"warning":null},{"id":"vals-legal-research-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","benchmarkId":"vals-legal-research-v1","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"{\"checkpoint\":\"muse_spark_1_1\",\"evaluatorModel\":\"meta/muse_spark_1_1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":37.981,"warning":null},{"id":"vals-legal-research-v1:grok/grok-4.5","modelId":"grok-4.5","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"{\"checkpoint\":\"grok-4.5\",\"evaluatorModel\":\"grok/grok-4.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":37.981,"warning":null},{"id":"vals-legal-research-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"{\"checkpoint\":\"gpt-5.6-luna\",\"evaluatorModel\":\"openai/gpt-5.6-luna\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":36.538,"warning":null},{"id":"vals-legal-research-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.7-flash\",\"evaluatorModel\":\"google/gemini-3.7-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":34.615,"warning":null},{"id":"vals-legal-research-v1:zai/glm-5.2","modelId":"glm-5.2","benchmarkId":"vals-legal-research-v1","level":"max","sourceLabel":"GLM 5.2 (max)","configuration":"{\"checkpoint\":\"glm-5.2\",\"evaluatorModel\":\"zai/glm-5.2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":31.25,"warning":null},{"id":"vals-legal-research-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash\",\"evaluatorModel\":\"google/gemini-3.5-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":30.769,"warning":null},{"id":"vals-legal-research-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"{\"checkpoint\":\"deepseek-v4-flash\",\"evaluatorModel\":\"deepseek/deepseek-v4-flash-0731\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":30.288,"warning":null},{"id":"vals-legal-research-v1:minimax/MiniMax-M3","modelId":"minimax-m3","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"MiniMax-M3 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M3\",\"evaluatorModel\":\"minimax/MiniMax-M3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":512000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":29.808,"warning":null},{"id":"vals-legal-research-v1:zai/glm-5.1","modelId":"glm-5.1","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"GLM 5.1 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.1\",\"evaluatorModel\":\"zai/glm-5.1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":27.885,"warning":null},{"id":"vals-legal-research-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Max (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-max\",\"evaluatorModel\":\"alibaba/qwen3.7-max\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":25.481,"warning":null},{"id":"vals-legal-research-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.6-flash\",\"evaluatorModel\":\"google/gemini-3.6-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":25,"warning":null},{"id":"vals-legal-research-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Gemini 3.1 Pro Preview (02/26) (high)","configuration":"{\"checkpoint\":\"gemini-3.1-pro-preview\",\"evaluatorModel\":\"google/gemini-3.1-pro-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":20.673,"warning":null},{"id":"vals-legal-research-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Gemini 3 Flash (12/25) (high)","configuration":"{\"checkpoint\":\"gemini-3-flash-preview\",\"evaluatorModel\":\"google/gemini-3-flash-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":18.269,"warning":null},{"id":"vals-legal-research-v1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-plus\",\"evaluatorModel\":\"alibaba/qwen3.7-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":16.346,"warning":null},{"id":"vals-legal-research-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"MiMo V2.5 Pro (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5-pro\",\"evaluatorModel\":\"xiaomi/mimo-v2.5-pro\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":15.865,"warning":null},{"id":"vals-legal-research-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"Kimi K2.6 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.6\",\"evaluatorModel\":\"kimi/kimi-k2.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":15.865,"warning":null},{"id":"vals-legal-research-v1:grok/grok-4.3","modelId":"grok-4.3","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"{\"checkpoint\":\"grok-4.3\",\"evaluatorModel\":\"grok/grok-4.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":15.385,"warning":null},{"id":"vals-legal-research-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"Qwen 3.6 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.6-plus\",\"evaluatorModel\":\"alibaba/qwen3.6-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":14.904,"warning":null},{"id":"vals-legal-research-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Gemini 3.5 Flash Lite (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash-lite\",\"evaluatorModel\":\"google/gemini-3.5-flash-lite\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":13.942,"warning":null},{"id":"vals-legal-research-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"Grok 4.20 (Reasoning) (unspecified)","configuration":"{\"checkpoint\":\"grok-4.20-0309-reasoning\",\"evaluatorModel\":\"grok/grok-4.20-0309-reasoning\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":2000000,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":13.942,"warning":null},{"id":"vals-legal-research-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","benchmarkId":"vals-legal-research-v1","level":"xhigh","sourceLabel":"GPT 5.4 Mini (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-mini-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-mini-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":12.5,"warning":null},{"id":"vals-legal-research-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"Claude Haiku 4.5 (Thinking) (unspecified)","configuration":"{\"checkpoint\":\"claude-haiku-4-5-20251001\",\"evaluatorModel\":\"anthropic/claude-haiku-4-5-20251001-thinking\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":64000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":10.577,"warning":null},{"id":"vals-legal-research-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"MiniMax-M2.7 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M2.7\",\"evaluatorModel\":\"minimax/MiniMax-M2.7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":10.577,"warning":null},{"id":"vals-legal-research-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","benchmarkId":"vals-legal-research-v1","level":"unspecified","sourceLabel":"MiMo V2.5 (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5\",\"evaluatorModel\":\"xiaomi/mimo-v2.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":9.135,"warning":null},{"id":"vals-legal-research-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"Mistral Medium 3.5 (high)","configuration":"{\"checkpoint\":\"mistral-medium-3.5\",\"evaluatorModel\":\"mistralai/mistral-medium-3.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"Mistral AI\",\"harness\":null}","score":9.135,"warning":null},{"id":"vals-legal-research-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","benchmarkId":"vals-legal-research-v1","level":"high","sourceLabel":"GPT 5.4 Nano (high)","configuration":"{\"checkpoint\":\"gpt-5.4-nano-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-nano-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":6.25,"warning":null},{"id":"vals-emb-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"{\"checkpoint\":\"claude-fable-5-1\",\"evaluatorModel\":\"anthropic/claude-fable-5-1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":76.67,"warning":null},{"id":"vals-emb-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"{\"checkpoint\":\"claude-fable-5\",\"evaluatorModel\":\"anthropic/claude-fable-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":73.666,"warning":null},{"id":"vals-emb-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"Claude Opus 5 (max)","configuration":"{\"checkpoint\":\"claude-opus-5\",\"evaluatorModel\":\"anthropic/claude-opus-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":73.556,"warning":null},{"id":"vals-emb-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"{\"checkpoint\":\"gpt-5.6-sol\",\"evaluatorModel\":\"openai/gpt-5.6-sol\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":72.339,"warning":null},{"id":"vals-emb-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.8-flash\",\"evaluatorModel\":\"google/gemini-3.8-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":72.196,"warning":null},{"id":"vals-emb-v1:openai/gpt-6-astra","modelId":"gpt-6-astra","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"{\"checkpoint\":\"gpt-6-astra\",\"evaluatorModel\":\"openai/gpt-6-astra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":71.7,"warning":null},{"id":"vals-emb-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.7-flash\",\"evaluatorModel\":\"google/gemini-3.7-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":71.326,"warning":null},{"id":"vals-emb-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-8\",\"evaluatorModel\":\"anthropic/claude-opus-4-8\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":69.373,"warning":null},{"id":"vals-emb-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"{\"checkpoint\":\"gpt-5.6-luna\",\"evaluatorModel\":\"openai/gpt-5.6-luna\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":67.116,"warning":null},{"id":"vals-emb-v1:kimi/kimi-k3","modelId":"kimi-k3","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"{\"checkpoint\":\"kimi-k3\",\"evaluatorModel\":\"kimi/kimi-k3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":262144,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":66.399,"warning":null},{"id":"vals-emb-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-5\",\"evaluatorModel\":\"anthropic/claude-sonnet-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":66.316,"warning":null},{"id":"vals-emb-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"{\"checkpoint\":\"gpt-5.6-terra\",\"evaluatorModel\":\"openai/gpt-5.6-terra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":66.205,"warning":null},{"id":"vals-emb-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.6-flash\",\"evaluatorModel\":\"google/gemini-3.6-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":65.411,"warning":null},{"id":"vals-emb-v1:openai/gpt-5.5","modelId":"gpt-5.5","benchmarkId":"vals-emb-v1","level":"xhigh","sourceLabel":"GPT 5.5 (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.5\",\"evaluatorModel\":\"openai/gpt-5.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":64.543,"warning":null},{"id":"vals-emb-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"Claude Opus 4.7 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-7\",\"evaluatorModel\":\"anthropic/claude-opus-4-7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":63.728,"warning":null},{"id":"vals-emb-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash\",\"evaluatorModel\":\"google/gemini-3.5-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":63.548,"warning":null},{"id":"vals-emb-v1:grok/grok-4.6","modelId":"grok-4.6","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"{\"checkpoint\":\"grok-4.6\",\"evaluatorModel\":\"grok/grok-4.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":62.727,"warning":null},{"id":"vals-emb-v1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","benchmarkId":"vals-emb-v1","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.3\",\"evaluatorModel\":\"meta/muse_spark_1_3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":62.712,"warning":null},{"id":"vals-emb-v1:zai/glm-5.2","modelId":"glm-5.2","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"GLM 5.2 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.2\",\"evaluatorModel\":\"zai/glm-5.2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":61.532,"warning":null},{"id":"vals-emb-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-4-6\",\"evaluatorModel\":\"anthropic/claude-sonnet-4-6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":true,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":60.154,"warning":null},{"id":"vals-emb-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"Kimi K2.6 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.6\",\"evaluatorModel\":\"kimi/kimi-k2.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":57.855,"warning":null},{"id":"vals-emb-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Max (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-max\",\"evaluatorModel\":\"alibaba/qwen3.7-max\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":57.041,"warning":null},{"id":"vals-emb-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","benchmarkId":"vals-emb-v1","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.2\",\"evaluatorModel\":\"meta/muse_spark_1_2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":56.978,"warning":null},{"id":"vals-emb-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"{\"checkpoint\":\"deepseek-v4-flash\",\"evaluatorModel\":\"deepseek/deepseek-v4-flash-0731\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":56.977,"warning":null},{"id":"vals-emb-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","benchmarkId":"vals-emb-v1","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"{\"checkpoint\":\"muse_spark_1_1\",\"evaluatorModel\":\"meta/muse_spark_1_1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":56.361,"warning":null},{"id":"vals-emb-v1:zai/glm-5.3","modelId":"glm-5.3","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"{\"checkpoint\":\"glm-5.3\",\"evaluatorModel\":\"zai/glm-5.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":56.344,"warning":null},{"id":"vals-emb-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"{\"checkpoint\":\"glm-5.3-flash\",\"evaluatorModel\":\"zai/glm-5.3-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":55.932,"warning":null},{"id":"vals-emb-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"MiMo V2.5 Pro (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5-pro\",\"evaluatorModel\":\"xiaomi/mimo-v2.5-pro\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":55.228,"warning":null},{"id":"vals-emb-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"MiMo V2.5 (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5\",\"evaluatorModel\":\"xiaomi/mimo-v2.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":55.092,"warning":null},{"id":"vals-emb-v1:grok/grok-4.5","modelId":"grok-4.5","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"{\"checkpoint\":\"grok-4.5\",\"evaluatorModel\":\"grok/grok-4.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":52.911,"warning":null},{"id":"vals-emb-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","benchmarkId":"vals-emb-v1","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (max)","configuration":"{\"checkpoint\":\"deepseek-v4-pro\",\"evaluatorModel\":\"deepseek/deepseek-v4-pro-0813\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":52.803,"warning":null},{"id":"vals-emb-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Gemini 3.1 Pro Preview (02/26) (high)","configuration":"{\"checkpoint\":\"gemini-3.1-pro-preview\",\"evaluatorModel\":\"google/gemini-3.1-pro-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":52.616,"warning":null},{"id":"vals-emb-v1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-plus\",\"evaluatorModel\":\"alibaba/qwen3.7-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":49.345,"warning":null},{"id":"vals-emb-v1:minimax/MiniMax-M3","modelId":"minimax-m3","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"MiniMax-M3 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M3\",\"evaluatorModel\":\"minimax/MiniMax-M3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":512000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":47.759,"warning":null},{"id":"vals-emb-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","benchmarkId":"vals-emb-v1","level":"xhigh","sourceLabel":"GPT 5.4 Mini (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-mini-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-mini-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":45.426,"warning":null},{"id":"vals-emb-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"GPT 5.4 Nano (high)","configuration":"{\"checkpoint\":\"gpt-5.4-nano-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-nano-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":44.751,"warning":null},{"id":"vals-emb-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Gemini 3.5 Flash Lite (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash-lite\",\"evaluatorModel\":\"google/gemini-3.5-flash-lite\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":43.231,"warning":null},{"id":"vals-emb-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"Qwen 3.6 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.6-plus\",\"evaluatorModel\":\"alibaba/qwen3.6-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":32.867,"warning":null},{"id":"vals-emb-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"MiniMax-M2.7 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M2.7\",\"evaluatorModel\":\"minimax/MiniMax-M2.7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":28.451,"warning":null},{"id":"vals-emb-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Gemini 3 Flash (12/25) (high)","configuration":"{\"checkpoint\":\"gemini-3-flash-preview\",\"evaluatorModel\":\"google/gemini-3-flash-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":26.017,"warning":null},{"id":"vals-emb-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"Claude Haiku 4.5 (Thinking) (unspecified)","configuration":"{\"checkpoint\":\"claude-haiku-4-5-20251001\",\"evaluatorModel\":\"anthropic/claude-haiku-4-5-20251001-thinking\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":64000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":22.664,"warning":null},{"id":"vals-emb-v1:grok/grok-4.3","modelId":"grok-4.3","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"{\"checkpoint\":\"grok-4.3\",\"evaluatorModel\":\"grok/grok-4.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":18.394,"warning":null},{"id":"vals-emb-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","benchmarkId":"vals-emb-v1","level":"unspecified","sourceLabel":"Grok 4.20 (Reasoning) (unspecified)","configuration":"{\"checkpoint\":\"grok-4.20-0309-reasoning\",\"evaluatorModel\":\"grok/grok-4.20-0309-reasoning\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":2000000,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":11.739,"warning":null},{"id":"vals-emb-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","benchmarkId":"vals-emb-v1","level":"high","sourceLabel":"Mistral Medium 3.5 (high)","configuration":"{\"checkpoint\":\"mistral-medium-3.5\",\"evaluatorModel\":\"mistralai/mistral-medium-3.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"Mistral AI\",\"harness\":null}","score":11.185,"warning":null},{"id":"vals-mmlu-pro-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"{\"checkpoint\":\"claude-fable-5-1\",\"evaluatorModel\":\"anthropic/claude-fable-5-1\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":92.375,"warning":null},{"id":"vals-mmlu-pro-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"Claude Opus 5 (max)","configuration":"{\"checkpoint\":\"claude-opus-5\",\"evaluatorModel\":\"anthropic/claude-opus-5\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":91.591,"warning":null},{"id":"vals-mmlu-pro-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"{\"checkpoint\":\"claude-fable-5\",\"evaluatorModel\":\"anthropic/claude-fable-5\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":91.502,"warning":null},{"id":"vals-mmlu-pro-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Gemini 3.1 Pro Preview (02/26) (high)","configuration":"{\"checkpoint\":\"gemini-3.1-pro-preview\",\"evaluatorModel\":\"google/gemini-3.1-pro-preview\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65535,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":90.987,"warning":null},{"id":"vals-mmlu-pro-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.8-flash\",\"evaluatorModel\":\"google/gemini-3.8-flash\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":90.221,"warning":null},{"id":"vals-mmlu-pro-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.7-flash\",\"evaluatorModel\":\"google/gemini-3.7-flash\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":90.121,"warning":null},{"id":"vals-mmlu-pro-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"Claude Opus 4.7 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-7\",\"evaluatorModel\":\"anthropic/claude-opus-4-7\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":89.871,"warning":null},{"id":"vals-mmlu-pro-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-8\",\"evaluatorModel\":\"anthropic/claude-opus-4-8\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":89.585,"warning":null},{"id":"vals-mmlu-pro-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash\",\"evaluatorModel\":\"google/gemini-3.5-flash\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":89.515,"warning":null},{"id":"vals-mmlu-pro-v1:grok/grok-4.6","modelId":"grok-4.6","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"{\"checkpoint\":\"grok-4.6\",\"evaluatorModel\":\"grok/grok-4.6\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":89.4,"warning":null},{"id":"vals-mmlu-pro-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Max (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-max\",\"evaluatorModel\":\"alibaba/qwen3.7-max\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":89.311,"warning":null},{"id":"vals-mmlu-pro-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.6-flash\",\"evaluatorModel\":\"google/gemini-3.6-flash\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":89.276,"warning":null},{"id":"vals-mmlu-pro-v1:grok/grok-4.5","modelId":"grok-4.5","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"{\"checkpoint\":\"grok-4.5\",\"evaluatorModel\":\"grok/grok-4.5\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":89.216,"warning":null},{"id":"vals-mmlu-pro-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"{\"checkpoint\":\"gpt-5.6-sol\",\"evaluatorModel\":\"openai/gpt-5.6-sol\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":89.1,"warning":null},{"id":"vals-mmlu-pro-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","benchmarkId":"vals-mmlu-pro-v1","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"{\"checkpoint\":\"muse_spark_1_1\",\"evaluatorModel\":\"meta/muse_spark_1_1\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":88.726,"warning":null},{"id":"vals-mmlu-pro-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Gemini 3 Flash (12/25) (high)","configuration":"{\"checkpoint\":\"gemini-3-flash-preview\",\"evaluatorModel\":\"google/gemini-3-flash-preview\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":88.592,"warning":null},{"id":"vals-mmlu-pro-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","benchmarkId":"vals-mmlu-pro-v1","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.2\",\"evaluatorModel\":\"meta/muse_spark_1_2\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":88.275,"warning":null},{"id":"vals-mmlu-pro-v1:openai/gpt-5.5","modelId":"gpt-5.5","benchmarkId":"vals-mmlu-pro-v1","level":"xhigh","sourceLabel":"GPT 5.5 (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.5\",\"evaluatorModel\":\"openai/gpt-5.5\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":88.144,"warning":null},{"id":"vals-mmlu-pro-v1:kimi/kimi-k3","modelId":"kimi-k3","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"Kimi K3 (max)","configuration":"{\"checkpoint\":\"kimi-k3\",\"evaluatorModel\":\"kimi/kimi-k3\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":262144,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":87.973,"warning":null},{"id":"vals-mmlu-pro-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"Qwen 3.6 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.6-plus\",\"evaluatorModel\":\"alibaba/qwen3.6-plus\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":87.668,"warning":null},{"id":"vals-mmlu-pro-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"Kimi K2.6 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.6\",\"evaluatorModel\":\"kimi/kimi-k2.6\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":87.572,"warning":null},{"id":"vals-mmlu-pro-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-5\",\"evaluatorModel\":\"anthropic/claude-sonnet-5\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":87.545,"warning":null},{"id":"vals-mmlu-pro-v1:openai/gpt-5.4-2026-03-05","modelId":"gpt-5.4","benchmarkId":"vals-mmlu-pro-v1","level":"xhigh","sourceLabel":"GPT 5.4 (xhigh) (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-2026-03-05\",\"evaluatorModel\":\"openai/gpt-5.4-2026-03-05\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":87.482,"warning":null},{"id":"vals-mmlu-pro-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-4-6\",\"evaluatorModel\":\"anthropic/claude-sonnet-4-6\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":true,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":87.341,"warning":null},{"id":"vals-mmlu-pro-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (max)","configuration":"{\"checkpoint\":\"deepseek-v4-pro\",\"evaluatorModel\":\"deepseek/deepseek-v4-pro-0813\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":86.972,"warning":null},{"id":"vals-mmlu-pro-v1:zai/glm-5.1","modelId":"glm-5.1","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"GLM 5.1 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.1\",\"evaluatorModel\":\"zai/glm-5.1\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":86.9,"warning":null},{"id":"vals-mmlu-pro-v1:zai/glm-5.3","modelId":"glm-5.3","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"{\"checkpoint\":\"glm-5.3\",\"evaluatorModel\":\"zai/glm-5.3\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":86.77,"warning":null},{"id":"vals-mmlu-pro-v1:zai/glm-5.2","modelId":"glm-5.2","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"GLM 5.2 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.2\",\"evaluatorModel\":\"zai/glm-5.2\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":86.714,"warning":null},{"id":"vals-mmlu-pro-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","benchmarkId":"vals-mmlu-pro-v1","level":"xhigh","sourceLabel":"GPT-5.6 Terra (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.6-terra\",\"evaluatorModel\":\"openai/gpt-5.6-terra\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":86.659,"warning":null},{"id":"vals-mmlu-pro-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"Grok 4.20 (Reasoning) (unspecified)","configuration":"{\"checkpoint\":\"grok-4.20-0309-reasoning\",\"evaluatorModel\":\"grok/grok-4.20-0309-reasoning\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":2000000,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":86.254,"warning":null},{"id":"vals-mmlu-pro-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"{\"checkpoint\":\"deepseek-v4-flash\",\"evaluatorModel\":\"deepseek/deepseek-v4-flash-0731\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":86.206,"warning":null},{"id":"vals-mmlu-pro-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"{\"checkpoint\":\"glm-5.3-flash\",\"evaluatorModel\":\"zai/glm-5.3-flash\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":86.059,"warning":null},{"id":"vals-mmlu-pro-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","benchmarkId":"vals-mmlu-pro-v1","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"{\"checkpoint\":\"gpt-5.6-luna\",\"evaluatorModel\":\"openai/gpt-5.6-luna\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":86.036,"warning":null},{"id":"vals-mmlu-pro-v1:grok/grok-4.3","modelId":"grok-4.3","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"{\"checkpoint\":\"grok-4.3\",\"evaluatorModel\":\"grok/grok-4.3\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":85.838,"warning":null},{"id":"vals-mmlu-pro-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Gemini 3.5 Flash Lite (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash-lite\",\"evaluatorModel\":\"google/gemini-3.5-flash-lite\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":85.836,"warning":null},{"id":"vals-mmlu-pro-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"MiMo V2.5 Pro (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5-pro\",\"evaluatorModel\":\"xiaomi/mimo-v2.5-pro\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":84.595,"warning":null},{"id":"vals-mmlu-pro-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","benchmarkId":"vals-mmlu-pro-v1","level":"xhigh","sourceLabel":"GPT 5.4 Mini (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-mini-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-mini-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":84.554,"warning":null},{"id":"vals-mmlu-pro-v1:minimax/MiniMax-M3","modelId":"minimax-m3","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"MiniMax-M3 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M3\",\"evaluatorModel\":\"minimax/MiniMax-M3\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":512000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":84.22,"warning":null},{"id":"vals-mmlu-pro-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"MiMo V2.5 (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5\",\"evaluatorModel\":\"xiaomi/mimo-v2.5\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":82.931,"warning":null},{"id":"vals-mmlu-pro-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"MiniMax-M2.7 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M2.7\",\"evaluatorModel\":\"minimax/MiniMax-M2.7\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":80.427,"warning":null},{"id":"vals-mmlu-pro-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","benchmarkId":"vals-mmlu-pro-v1","level":"unspecified","sourceLabel":"Claude Haiku 4.5 (Thinking) (unspecified)","configuration":"{\"checkpoint\":\"claude-haiku-4-5-20251001\",\"evaluatorModel\":\"anthropic/claude-haiku-4-5-20251001-thinking\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":64000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":78.715,"warning":null},{"id":"vals-mmlu-pro-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"GPT 5.4 Nano (high)","configuration":"{\"checkpoint\":\"gpt-5.4-nano-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-nano-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":77.172,"warning":null},{"id":"vals-mmlu-pro-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","benchmarkId":"vals-mmlu-pro-v1","level":"high","sourceLabel":"Mistral Medium 3.5 (high)","configuration":"{\"checkpoint\":\"mistral-medium-3.5\",\"evaluatorModel\":\"mistralai/mistral-medium-3.5\",\"sourceUpdatedOn\":\"2026-09-01\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"Mistral AI\",\"harness\":null}","score":75.335,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-6-astra","modelId":"gpt-6-astra","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"{\"checkpoint\":\"gpt-6-astra\",\"evaluatorModel\":\"openai/gpt-6-astra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":87.266,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"{\"checkpoint\":\"gpt-5.6-sol\",\"evaluatorModel\":\"openai/gpt-5.6-sol\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":85.768,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Claude Fable 5.1 (high)","configuration":"{\"checkpoint\":\"claude-fable-5-1\",\"evaluatorModel\":\"anthropic/claude-fable-5-1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"high\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":85.019,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-opus-5","modelId":"claude-opus-5","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Claude Opus 5 (high)","configuration":"{\"checkpoint\":\"claude-opus-5\",\"evaluatorModel\":\"anthropic/claude-opus-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"high\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":84.644,"warning":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.8-flash\",\"evaluatorModel\":\"google/gemini-3.8-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":81.273,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k3","modelId":"kimi-k3","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Kimi K3 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k3\",\"evaluatorModel\":\"kimi/kimi-k3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":262144,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":80.899,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-fable-5","modelId":"claude-fable-5","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Claude Fable 5 (unspecified)","configuration":"{\"checkpoint\":\"claude-fable-5\",\"evaluatorModel\":\"anthropic/claude-fable-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":80.524,"warning":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"{\"checkpoint\":\"gpt-5.6-luna\",\"evaluatorModel\":\"openai/gpt-5.6-luna\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":79.026,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.6","modelId":"grok-4.6","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"{\"checkpoint\":\"grok-4.6\",\"evaluatorModel\":\"grok/grok-4.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":78.277,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.7-flash\",\"evaluatorModel\":\"google/gemini-3.7-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":77.528,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"{\"checkpoint\":\"gpt-5.6-terra\",\"evaluatorModel\":\"openai/gpt-5.6-terra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":77.528,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.5","modelId":"gpt-5.5","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"GPT 5.5 (high)","configuration":"{\"checkpoint\":\"gpt-5.5\",\"evaluatorModel\":\"openai/gpt-5.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":76.404,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-5\",\"evaluatorModel\":\"anthropic/claude-sonnet-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":74.532,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash\",\"evaluatorModel\":\"google/gemini-3.5-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":74.157,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.6-flash\",\"evaluatorModel\":\"google/gemini-3.6-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":73.783,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.3\",\"evaluatorModel\":\"meta/muse_spark_1_3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":72.285,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-8\",\"evaluatorModel\":\"anthropic/claude-opus-4-8\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":71.91,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.3","modelId":"glm-5.3","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"{\"checkpoint\":\"glm-5.3\",\"evaluatorModel\":\"zai/glm-5.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":71.536,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Gemini 3.1 Pro Preview (02/26) (high)","configuration":"{\"checkpoint\":\"gemini-3.1-pro-preview\",\"evaluatorModel\":\"google/gemini-3.1-pro-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":70.787,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.2\",\"evaluatorModel\":\"meta/muse_spark_1_2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":69.663,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"{\"checkpoint\":\"muse_spark_1_1\",\"evaluatorModel\":\"meta/muse_spark_1_1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":69.288,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Claude Opus 4.7 (high)","configuration":"{\"checkpoint\":\"claude-opus-4-7\",\"evaluatorModel\":\"anthropic/claude-opus-4-7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"high\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":68.539,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.5","modelId":"grok-4.5","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"{\"checkpoint\":\"grok-4.5\",\"evaluatorModel\":\"grok/grok-4.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":67.79,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.2","modelId":"glm-5.2","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"GLM 5.2 (max)","configuration":"{\"checkpoint\":\"glm-5.2\",\"evaluatorModel\":\"zai/glm-5.2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":1,\"max_output_tokens\":48000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":67.79,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"DeepSeek V4 Flash 0731 (unspecified)","configuration":"{\"checkpoint\":\"deepseek-v4-flash\",\"evaluatorModel\":\"deepseek/deepseek-v4-flash-0731\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":false,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":67.041,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k2.7-code","modelId":"kimi-k2.7-code","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Kimi K2.7 Code (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.7-code\",\"evaluatorModel\":\"kimi/kimi-k2.7-code\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":32768,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":67.041,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"{\"checkpoint\":\"glm-5.3-flash\",\"evaluatorModel\":\"zai/glm-5.3-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Fireworks AI\",\"harness\":null}","score":62.921,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Qwen 3.7 Max (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-max\",\"evaluatorModel\":\"alibaba/qwen3.7-max\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":61.049,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"MiMo V2.5 (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5\",\"evaluatorModel\":\"xiaomi/mimo-v2.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":60.674,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-4-6\",\"evaluatorModel\":\"anthropic/claude-sonnet-4-6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":false,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":57.303,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"MiMo V2.5 Pro (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5-pro\",\"evaluatorModel\":\"xiaomi/mimo-v2.5-pro\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":57.303,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.1","modelId":"glm-5.1","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"GLM 5.1 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.1\",\"evaluatorModel\":\"zai/glm-5.1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":56.929,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"GPT 5.4 Mini (high)","configuration":"{\"checkpoint\":\"gpt-5.4-mini-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-mini-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":54.682,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (max)","configuration":"{\"checkpoint\":\"deepseek-v4-pro\",\"evaluatorModel\":\"deepseek/deepseek-v4-pro-0813\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":54.682,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Gemini 3 Flash (12/25) (high)","configuration":"{\"checkpoint\":\"gemini-3-flash-preview\",\"evaluatorModel\":\"google/gemini-3-flash-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":53.933,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k2.6","modelId":"kimi-k2.6","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Kimi K2.6 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.6\",\"evaluatorModel\":\"kimi/kimi-k2.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":53.558,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:minimax/MiniMax-M3","modelId":"minimax-m3","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"MiniMax-M3 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M3\",\"evaluatorModel\":\"minimax/MiniMax-M3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":512000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":53.558,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Qwen 3.6 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.6-plus\",\"evaluatorModel\":\"alibaba/qwen3.6-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":53.184,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-plus\",\"evaluatorModel\":\"alibaba/qwen3.7-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":52.809,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Gemini 3.5 Flash Lite (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash-lite\",\"evaluatorModel\":\"google/gemini-3.5-flash-lite\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":50.187,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"MiniMax-M2.7 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M2.7\",\"evaluatorModel\":\"minimax/MiniMax-M2.7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":196608,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":48.689,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Grok 4.20 (Reasoning) (unspecified)","configuration":"{\"checkpoint\":\"grok-4.20-0309-reasoning\",\"evaluatorModel\":\"grok/grok-4.20-0309-reasoning\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":2000000,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":44.195,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"unspecified","sourceLabel":"Claude Haiku 4.5 (Thinking) (unspecified)","configuration":"{\"checkpoint\":\"claude-haiku-4-5-20251001\",\"evaluatorModel\":\"anthropic/claude-haiku-4-5-20251001-thinking\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":64000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":43.82,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.3","modelId":"grok-4.3","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"{\"checkpoint\":\"grok-4.3\",\"evaluatorModel\":\"grok/grok-4.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":41.948,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"GPT 5.4 Nano (high)","configuration":"{\"checkpoint\":\"gpt-5.4-nano-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-nano-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":41.573,"warning":null},{"id":"vals-terminal-bench-2-1-v2.1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","benchmarkId":"vals-terminal-bench-2-1-v2.1","level":"high","sourceLabel":"Mistral Medium 3.5 (high)","configuration":"{\"checkpoint\":\"mistral-medium-3.5\",\"evaluatorModel\":\"mistralai/mistral-medium-3.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"Mistral AI\",\"harness\":null}","score":38.951,"warning":null},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-fable-5","modelId":"claude-fable-5","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"{\"checkpoint\":\"claude-fable-5\",\"evaluatorModel\":\"anthropic/claude-fable-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":\"OpenHands\"}","score":90.352,"warning":null},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"{\"checkpoint\":\"claude-fable-5-1\",\"evaluatorModel\":\"anthropic/claude-fable-5-1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":\"OpenHands\"}","score":90.263,"warning":null},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-6-astra","modelId":"gpt-6-astra","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"{\"checkpoint\":\"gpt-6-astra\",\"evaluatorModel\":\"openai/gpt-6-astra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":\"OpenHands\"}","score":89.594,"warning":null},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-opus-5","modelId":"claude-opus-5","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Claude Opus 5 (unspecified)","configuration":"{\"checkpoint\":\"claude-opus-5\",\"evaluatorModel\":\"anthropic/claude-opus-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":\"OpenHands\"}","score":88.404,"warning":null},{"id":"vals-vibe-code-bench-v1.1:kimi/kimi-k3","modelId":"kimi-k3","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Kimi K3 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k3\",\"evaluatorModel\":\"kimi/kimi-k3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":262144,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":\"OpenHands\"}","score":84.963,"warning":null},{"id":"vals-vibe-code-bench-v1.1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","benchmarkId":"vals-vibe-code-bench-v1.1","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.3\",\"evaluatorModel\":\"meta/muse_spark_1_3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":\"OpenHands\"}","score":82.859,"warning":null},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-8\",\"evaluatorModel\":\"anthropic/claude-opus-4-8\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":\"OpenHands\"}","score":82.725,"warning":null},{"id":"vals-vibe-code-bench-v1.1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (max)","configuration":"{\"checkpoint\":\"deepseek-v4-pro\",\"evaluatorModel\":\"deepseek/deepseek-v4-pro-0813\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":\"OpenHands\"}","score":82.297,"warning":null},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-5\",\"evaluatorModel\":\"anthropic/claude-sonnet-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":\"OpenHands\"}","score":81.325,"warning":null},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"{\"checkpoint\":\"gpt-5.6-sol\",\"evaluatorModel\":\"openai/gpt-5.6-sol\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":\"OpenHands\"}","score":80.495,"warning":null},{"id":"vals-vibe-code-bench-v1.1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","benchmarkId":"vals-vibe-code-bench-v1.1","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.2\",\"evaluatorModel\":\"meta/muse_spark_1_2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":\"OpenHands\"}","score":79.1,"warning":null},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.8-flash\",\"evaluatorModel\":\"google/gemini-3.8-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":\"OpenHands\"}","score":78.651,"warning":null},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.3","modelId":"glm-5.3","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"{\"checkpoint\":\"glm-5.3\",\"evaluatorModel\":\"zai/glm-5.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Fireworks AI\",\"harness\":\"OpenHands\"}","score":78.125,"warning":null},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"{\"checkpoint\":\"gpt-5.6-luna\",\"evaluatorModel\":\"openai/gpt-5.6-luna\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":\"OpenHands\"}","score":77.055,"warning":null},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.6","modelId":"grok-4.6","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"{\"checkpoint\":\"grok-4.6\",\"evaluatorModel\":\"grok/grok-4.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":\"OpenHands\"}","score":76.239,"warning":null},{"id":"vals-vibe-code-bench-v1.1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"{\"checkpoint\":\"deepseek-v4-flash\",\"evaluatorModel\":\"deepseek/deepseek-v4-flash-0731\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":\"OpenHands\"}","score":74.736,"warning":null},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"{\"checkpoint\":\"gpt-5.6-terra\",\"evaluatorModel\":\"openai/gpt-5.6-terra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":\"OpenHands\"}","score":74.594,"warning":null},{"id":"vals-vibe-code-bench-v1.1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","benchmarkId":"vals-vibe-code-bench-v1.1","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"{\"checkpoint\":\"muse_spark_1_1\",\"evaluatorModel\":\"meta/muse_spark_1_1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":\"OpenHands\"}","score":72.158,"warning":null},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"Claude Opus 4.7 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-7\",\"evaluatorModel\":\"anthropic/claude-opus-4-7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":\"OpenHands\"}","score":71.003,"warning":null},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.7-flash\",\"evaluatorModel\":\"google/gemini-3.7-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":\"OpenHands\"}","score":70.395,"warning":null},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.5","modelId":"gpt-5.5","benchmarkId":"vals-vibe-code-bench-v1.1","level":"xhigh","sourceLabel":"GPT 5.5 (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.5\",\"evaluatorModel\":\"openai/gpt-5.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":\"OpenHands\"}","score":69.847,"warning":null},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.5","modelId":"grok-4.5","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"{\"checkpoint\":\"grok-4.5\",\"evaluatorModel\":\"grok/grok-4.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":\"OpenHands\"}","score":69.002,"warning":null},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.4-2026-03-05","modelId":"gpt-5.4","benchmarkId":"vals-vibe-code-bench-v1.1","level":"xhigh","sourceLabel":"GPT 5.4 (xhigh) (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-2026-03-05\",\"evaluatorModel\":\"openai/gpt-5.4-2026-03-05\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":\"OpenHands\"}","score":67.421,"warning":null},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.6-flash\",\"evaluatorModel\":\"google/gemini-3.6-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":\"OpenHands\"}","score":64.005,"warning":null},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.2","modelId":"glm-5.2","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"GLM 5.2 (max)","configuration":"{\"checkpoint\":\"glm-5.2\",\"evaluatorModel\":\"zai/glm-5.2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":\"OpenHands\"}","score":63.961,"warning":null},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-4-6\",\"evaluatorModel\":\"anthropic/claude-sonnet-4-6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":true,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":\"OpenHands\"}","score":51.476,"warning":null},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash\",\"evaluatorModel\":\"google/gemini-3.5-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":\"OpenHands\"}","score":48.683,"warning":null},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","benchmarkId":"vals-vibe-code-bench-v1.1","level":"xhigh","sourceLabel":"GPT 5.4 Mini (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-mini-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-mini-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":\"OpenHands\"}","score":47.969,"warning":null},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Qwen 3.7 Max (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-max\",\"evaluatorModel\":\"alibaba/qwen3.7-max\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":\"OpenHands\"}","score":47.671,"warning":null},{"id":"vals-vibe-code-bench-v1.1:minimax/MiniMax-M3","modelId":"minimax-m3","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"MiniMax-M3 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M3\",\"evaluatorModel\":\"minimax/MiniMax-M3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":512000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":\"OpenHands\"}","score":47.566,"warning":null},{"id":"vals-vibe-code-bench-v1.1:kimi/kimi-k2.7-code","modelId":"kimi-k2.7-code","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Kimi K2.7 Code (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.7-code\",\"evaluatorModel\":\"kimi/kimi-k2.7-code\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":32768,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":\"OpenHands\"}","score":47.211,"warning":null},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-plus\",\"evaluatorModel\":\"alibaba/qwen3.7-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":\"OpenHands\"}","score":46.391,"warning":null},{"id":"vals-vibe-code-bench-v1.1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"MiMo V2.5 (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5\",\"evaluatorModel\":\"xiaomi/mimo-v2.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":\"OpenHands\"}","score":42.174,"warning":null},{"id":"vals-vibe-code-bench-v1.1:kimi/kimi-k2.6","modelId":"kimi-k2.6","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Kimi K2.6 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.6\",\"evaluatorModel\":\"kimi/kimi-k2.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":\"OpenHands\"}","score":37.891,"warning":null},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Gemini 3.5 Flash Lite (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash-lite\",\"evaluatorModel\":\"google/gemini-3.5-flash-lite\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":\"OpenHands\"}","score":37.161,"warning":null},{"id":"vals-vibe-code-bench-v1.1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"MiMo V2.5 Pro (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5-pro\",\"evaluatorModel\":\"xiaomi/mimo-v2.5-pro\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":\"OpenHands\"}","score":34.113,"warning":null},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Gemini 3.1 Pro Preview (02/26) (high)","configuration":"{\"checkpoint\":\"gemini-3.1-pro-preview\",\"evaluatorModel\":\"google/gemini-3.1-pro-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":\"OpenHands\"}","score":32.034,"warning":null},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.1","modelId":"glm-5.1","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"GLM 5.1 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.1\",\"evaluatorModel\":\"zai/glm-5.1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":\"OpenHands\"}","score":31.456,"warning":null},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","benchmarkId":"vals-vibe-code-bench-v1.1","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"{\"checkpoint\":\"glm-5.3-flash\",\"evaluatorModel\":\"zai/glm-5.3-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Fireworks AI\",\"harness\":\"OpenHands\"}","score":30.759,"warning":null},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"GPT 5.4 Nano (high)","configuration":"{\"checkpoint\":\"gpt-5.4-nano-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-nano-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":\"OpenHands\"}","score":26.097,"warning":null},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Qwen 3.6 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.6-plus\",\"evaluatorModel\":\"alibaba/qwen3.6-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":\"OpenHands\"}","score":25.565,"warning":null},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Gemini 3 Flash (12/25) (high)","configuration":"{\"checkpoint\":\"gemini-3-flash-preview\",\"evaluatorModel\":\"google/gemini-3-flash-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":\"OpenHands\"}","score":20.204,"warning":null},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.3","modelId":"grok-4.3","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"{\"checkpoint\":\"grok-4.3\",\"evaluatorModel\":\"grok/grok-4.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":\"OpenHands\"}","score":19.403,"warning":null},{"id":"vals-vibe-code-bench-v1.1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"MiniMax-M2.7 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M2.7\",\"evaluatorModel\":\"minimax/MiniMax-M2.7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":196608,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":\"OpenHands\"}","score":11.926,"warning":null},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Claude Haiku 4.5 (Thinking) (unspecified)","configuration":"{\"checkpoint\":\"claude-haiku-4-5-20251001\",\"evaluatorModel\":\"anthropic/claude-haiku-4-5-20251001-thinking\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":64000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":\"OpenHands\"}","score":11.393,"warning":null},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","benchmarkId":"vals-vibe-code-bench-v1.1","level":"unspecified","sourceLabel":"Grok 4.20 (Reasoning) (unspecified)","configuration":"{\"checkpoint\":\"grok-4.20-0309-reasoning\",\"evaluatorModel\":\"grok/grok-4.20-0309-reasoning\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":2000000,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":\"OpenHands\"}","score":4.063,"warning":null},{"id":"vals-vibe-code-bench-v1.1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","benchmarkId":"vals-vibe-code-bench-v1.1","level":"high","sourceLabel":"Mistral Medium 3.5 (high)","configuration":"{\"checkpoint\":\"mistral-medium-3.5\",\"evaluatorModel\":\"mistralai/mistral-medium-3.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"Mistral AI\",\"harness\":\"OpenHands\"}","score":2.888,"warning":null},{"id":"vals-legal-agent-benchmark-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","benchmarkId":"vals-legal-agent-benchmark-v1","level":"xhigh","sourceLabel":"Muse Spark 1.2 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.2\",\"evaluatorModel\":\"meta/muse_spark_1_2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":25.417,"warning":null},{"id":"vals-legal-agent-benchmark-v1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","benchmarkId":"vals-legal-agent-benchmark-v1","level":"xhigh","sourceLabel":"Muse Spark 1.3 (xhigh)","configuration":"{\"checkpoint\":\"muse-spark-1.3\",\"evaluatorModel\":\"meta/muse_spark_1_3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":22.083,"warning":null},{"id":"vals-legal-agent-benchmark-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","benchmarkId":"vals-legal-agent-benchmark-v1","level":"xhigh","sourceLabel":"Muse Spark 1.1 (xhigh)","configuration":"{\"checkpoint\":\"muse_spark_1_1\",\"evaluatorModel\":\"meta/muse_spark_1_1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":256000,\"verbosity\":null,\"provider\":\"Meta\",\"harness\":null}","score":20,"warning":null},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.6","modelId":"grok-4.6","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Grok 4.6 (high)","configuration":"{\"checkpoint\":\"grok-4.6\",\"evaluatorModel\":\"grok/grok-4.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":15.833,"warning":null},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.5","modelId":"grok-4.5","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Grok 4.5 (high)","configuration":"{\"checkpoint\":\"grok-4.5\",\"evaluatorModel\":\"grok/grok-4.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":12.917,"warning":null},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"Claude Fable 5 (max)","configuration":"{\"checkpoint\":\"claude-fable-5\",\"evaluatorModel\":\"anthropic/claude-fable-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":11.25,"warning":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-legal-agent-benchmark-v1:kimi/kimi-k3","modelId":"kimi-k3","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"Kimi K3 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k3\",\"evaluatorModel\":\"kimi/kimi-k3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":262144,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":10.833,"warning":null},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Gemini 3.8 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.8-flash\",\"evaluatorModel\":\"google/gemini-3.8-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":10,"warning":null},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"Claude Opus 4.8 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-8\",\"evaluatorModel\":\"anthropic/claude-opus-4-8\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":9.583,"warning":null},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Gemini 3.7 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.7-flash\",\"evaluatorModel\":\"google/gemini-3.7-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":8.75,"warning":null},{"id":"vals-legal-agent-benchmark-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"DeepSeek V4 Flash 0731 (high)","configuration":"{\"checkpoint\":\"deepseek-v4-flash\",\"evaluatorModel\":\"deepseek/deepseek-v4-flash-0731\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":8.333,"warning":null},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.3","modelId":"glm-5.3","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"GLM 5.3 (max)","configuration":"{\"checkpoint\":\"glm-5.3\",\"evaluatorModel\":\"zai/glm-5.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":8.333,"warning":null},{"id":"vals-legal-agent-benchmark-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"DeepSeek V4 Pro 0813 (max)","configuration":"{\"checkpoint\":\"deepseek-v4-pro\",\"evaluatorModel\":\"deepseek/deepseek-v4-pro-0813\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":384000,\"verbosity\":null,\"provider\":\"DeepSeek\",\"harness\":null}","score":7.5,"warning":null},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.2","modelId":"glm-5.2","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"GLM 5.2 (max)","configuration":"{\"checkpoint\":\"glm-5.2\",\"evaluatorModel\":\"zai/glm-5.2\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":131072,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":7.083,"warning":null},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"Claude Opus 4.7 (max)","configuration":"{\"checkpoint\":\"claude-opus-4-7\",\"evaluatorModel\":\"anthropic/claude-opus-4-7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":6.667,"warning":null},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"GLM 5.3 Flash (max)","configuration":"{\"checkpoint\":\"glm-5.3-flash\",\"evaluatorModel\":\"zai/glm-5.3-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":6.667,"warning":null},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"Claude Opus 5 (max)","configuration":"{\"checkpoint\":\"claude-opus-5\",\"evaluatorModel\":\"anthropic/claude-opus-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":6.667,"warning":null},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"Claude Fable 5.1 (max)","configuration":"{\"checkpoint\":\"claude-fable-5-1\",\"evaluatorModel\":\"anthropic/claude-fable-5-1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":6.667,"warning":null},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-6-astra","modelId":"gpt-6-astra","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"GPT-6 Astra (max)","configuration":"{\"checkpoint\":\"gpt-6-astra\",\"evaluatorModel\":\"openai/gpt-6-astra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":5.417,"warning":null},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"Claude Sonnet 4.6 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-4-6\",\"evaluatorModel\":\"anthropic/claude-sonnet-4-6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":true,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":5,"warning":null},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"Claude Sonnet 5 (max)","configuration":"{\"checkpoint\":\"claude-sonnet-5\",\"evaluatorModel\":\"anthropic/claude-sonnet-5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":\"max\",\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":5,"warning":null},{"id":"vals-legal-agent-benchmark-v1:minimax/MiniMax-M3","modelId":"minimax-m3","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"MiniMax-M3 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M3\",\"evaluatorModel\":\"minimax/MiniMax-M3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":512000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":4.167,"warning":null},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.5","modelId":"gpt-5.5","benchmarkId":"vals-legal-agent-benchmark-v1","level":"xhigh","sourceLabel":"GPT 5.5 (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.5\",\"evaluatorModel\":\"openai/gpt-5.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":3.75,"warning":null},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Gemini 3.6 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.6-flash\",\"evaluatorModel\":\"google/gemini-3.6-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":3.333,"warning":null},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Gemini 3.5 Flash (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash\",\"evaluatorModel\":\"google/gemini-3.5-flash\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":2.5,"warning":null},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"GPT-5.6 Sol (max)","configuration":"{\"checkpoint\":\"gpt-5.6-sol\",\"evaluatorModel\":\"openai/gpt-5.6-sol\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":2.5,"warning":null},{"id":"vals-legal-agent-benchmark-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"MiMo V2.5 Pro (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5-pro\",\"evaluatorModel\":\"xiaomi/mimo-v2.5-pro\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":2.083,"warning":null},{"id":"vals-legal-agent-benchmark-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"MiMo V2.5 (unspecified)","configuration":"{\"checkpoint\":\"mimo-v2.5\",\"evaluatorModel\":\"xiaomi/mimo-v2.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Xiaomi\",\"harness\":null}","score":1.667,"warning":null},{"id":"vals-legal-agent-benchmark-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"Kimi K2.6 (unspecified)","configuration":"{\"checkpoint\":\"kimi-k2.6\",\"evaluatorModel\":\"kimi/kimi-k2.6\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":0.95,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"Moonshot AI\",\"harness\":null}","score":1.667,"warning":null},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Max (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-max\",\"evaluatorModel\":\"alibaba/qwen3.7-max\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":1.667,"warning":null},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"GPT-5.6 Luna (max)","configuration":"{\"checkpoint\":\"gpt-5.6-luna\",\"evaluatorModel\":\"openai/gpt-5.6-luna\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":1.25,"warning":null},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"Qwen 3.6 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.6-plus\",\"evaluatorModel\":\"alibaba/qwen3.6-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":1.25,"warning":null},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"Claude Haiku 4.5 (Thinking) (unspecified)","configuration":"{\"checkpoint\":\"claude-haiku-4-5-20251001\",\"evaluatorModel\":\"anthropic/claude-haiku-4-5-20251001-thinking\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":64000,\"verbosity\":null,\"provider\":\"Anthropic\",\"harness\":null}","score":0.833,"warning":null},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","benchmarkId":"vals-legal-agent-benchmark-v1","level":"max","sourceLabel":"GPT-5.6 Terra (max)","configuration":"{\"checkpoint\":\"gpt-5.6-terra\",\"evaluatorModel\":\"openai/gpt-5.6-terra\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"max\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":0.833,"warning":null},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.3","modelId":"grok-4.3","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Grok 4.3 (high)","configuration":"{\"checkpoint\":\"grok-4.3\",\"evaluatorModel\":\"grok/grok-4.3\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":0.417,"warning":null},{"id":"vals-legal-agent-benchmark-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Mistral Medium 3.5 (high)","configuration":"{\"checkpoint\":\"mistral-medium-3.5\",\"evaluatorModel\":\"mistralai/mistral-medium-3.5\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"Mistral AI\",\"harness\":null}","score":0.417,"warning":null},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Gemini 3 Flash (12/25) (high)","configuration":"{\"checkpoint\":\"gemini-3-flash-preview\",\"evaluatorModel\":\"google/gemini-3-flash-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Gemini 3.5 Flash Lite (high)","configuration":"{\"checkpoint\":\"gemini-3.5-flash-lite\",\"evaluatorModel\":\"google/gemini-3.5-flash-lite\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"GPT 5.4 Nano (high)","configuration":"{\"checkpoint\":\"gpt-5.4-nano-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-nano-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","benchmarkId":"vals-legal-agent-benchmark-v1","level":"high","sourceLabel":"Gemini 3.1 Pro Preview (02/26) (high)","configuration":"{\"checkpoint\":\"gemini-3.1-pro-preview\",\"evaluatorModel\":\"google/gemini-3.1-pro-preview\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"high\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Google\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"MiniMax-M2.7 (unspecified)","configuration":"{\"checkpoint\":\"MiniMax-M2.7\",\"evaluatorModel\":\"minimax/MiniMax-M2.7\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":1,\"top_p\":0.95,\"max_output_tokens\":80000,\"verbosity\":null,\"provider\":\"MiniMax\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.1","modelId":"glm-5.1","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"GLM 5.1 (unspecified)","configuration":"{\"checkpoint\":\"glm-5.1\",\"evaluatorModel\":\"zai/glm-5.1\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":null,\"verbosity\":null,\"provider\":\"Zhipu AI\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"Grok 4.20 (Reasoning) (unspecified)","configuration":"{\"checkpoint\":\"grok-4.20-0309-reasoning\",\"evaluatorModel\":\"grok/grok-4.20-0309-reasoning\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":0.95,\"max_output_tokens\":2000000,\"verbosity\":null,\"provider\":\"SpaceXAI\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","benchmarkId":"vals-legal-agent-benchmark-v1","level":"unspecified","sourceLabel":"Qwen 3.7 Plus (unspecified)","configuration":"{\"checkpoint\":\"qwen3.7-plus\",\"evaluatorModel\":\"alibaba/qwen3.7-plus\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":null,\"compute_effort\":null,\"reasoning\":null,\"temperature\":0.7,\"top_p\":null,\"max_output_tokens\":65536,\"verbosity\":null,\"provider\":\"Alibaba\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","benchmarkId":"vals-legal-agent-benchmark-v1","level":"xhigh","sourceLabel":"GPT 5.4 Mini (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-mini-2026-03-17\",\"evaluatorModel\":\"openai/gpt-5.4-mini-2026-03-17\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":0,"warning":null},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.4-2026-03-05","modelId":"gpt-5.4","benchmarkId":"vals-legal-agent-benchmark-v1","level":"xhigh","sourceLabel":"GPT 5.4 (xhigh) (xhigh)","configuration":"{\"checkpoint\":\"gpt-5.4-2026-03-05\",\"evaluatorModel\":\"openai/gpt-5.4-2026-03-05\",\"sourceUpdatedOn\":\"2026-09-10\",\"reasoning_effort\":\"xhigh\",\"compute_effort\":null,\"reasoning\":null,\"temperature\":null,\"top_p\":null,\"max_output_tokens\":128000,\"verbosity\":null,\"provider\":\"OpenAI\",\"harness\":null}","score":0,"warning":null}],"skipped":[{"source":"aa-gdpval-aa","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Motif 3 (Beta)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"G9v3-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdpval-aa","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-analyst-agent","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-analyst-agent","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-aa-briefcase","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Claude 4 Opus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-aime-2025","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"o1-preview","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"QwQ 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-aime-2025","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-aime-2025","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-aime-2025","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-apex-agents-aa","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-apex-agents-aa","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-apex-agents-aa","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Motif 3 (Beta)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-artificial-analysis-long-context-reasoning","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"G9v3-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"QwQ 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-artificial-analysis-long-context-reasoning","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-automationbench-aa","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Motif 3 (Beta)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-critpt","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-critpt","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-critpt","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-critpt","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"G9v3-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-critpt","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-critpt","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Gemini 3 Deep Think","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-critpt","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-enterprise-ops-gym-aa","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-enterprise-ops-gym-aa","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-enterprise-ops-gym-aa","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-enterprise-ops-gym-aa","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-gdp-pdf","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-global-mmlu-lite","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-global-mmlu-lite","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-global-mmlu-lite","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Motif 3 (Beta)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-gpqa-diamond","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-gpqa-diamond","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-gpqa-diamond","label":"Claude 4 Opus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.5 Pro Preview (Mar' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.5 Pro Preview (May' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-gpqa-diamond","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.5 Flash Preview (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"o1-preview","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"G9v3-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"o1-mini","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"QwQ 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.0 Flash Thinking Experimental (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Solar Pro 2 (Preview) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.0 Pro Experimental (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 3 Opus","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Sonar Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.5 Flash Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.0 Flash (experimental)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen2.5 Max","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 1.5 Pro (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Solar Pro 2 (Preview) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 3.5 Sonnet (Oct '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Sonar","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Sonar Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"QwQ 32B-Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-gpqa-diamond","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.0 Flash-Lite (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 2.0 Flash-Lite (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 3.5 Sonnet (June '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.1 Tulu3 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok 2 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 1.5 Flash (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-gpqa-diamond","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Grok Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen2.5 Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen2.5 Coder Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek-V2.5 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral Saba","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 1.5 Pro (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen2.5 Turbo","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.2 Instruct 90B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen2 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 1.5 Flash-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepHermes 3 - Mistral 24B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Jamba 1.5 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Hermes 3 - Llama-3.1 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Jamba 1.6 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 1.5 Flash (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 3 Sonnet","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral Small (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemma 3n E4B Instruct Preview (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen2.5 Coder Instruct 7B ","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral Large (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mixtral 8x22B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 2 Chat 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Qwen1.5 Chat 110B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 2.1","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral Small (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM 40B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Gemini 1.0 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepSeek Coder V2 Lite Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 2 Chat 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 2 Chat 13B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"OpenChat 3.5 (1210)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DBRX Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Jamba 1.5 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Jamba 1.6 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mixtral 8x7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Claude Instant","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-gpqa-diamond","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Motif 3 (Beta)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-humanitys-last-exam","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-humanitys-last-exam","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-humanitys-last-exam","label":"Claude 4 Opus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.5 Pro Preview (Mar' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.5 Pro Preview (May' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-humanitys-last-exam","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.5 Flash Preview (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"G9v3-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"o1-mini","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"QwQ 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.0 Flash Thinking Experimental (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Solar Pro 2 (Preview) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.0 Pro Experimental (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 3 Opus","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.5 Flash Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.0 Flash (experimental)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen2.5 Max","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 1.5 Pro (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Solar Pro 2 (Preview) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 3.5 Sonnet (Oct '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Sonar","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Sonar Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"QwQ 32B-Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-humanitys-last-exam","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.0 Flash-Lite (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 2.0 Flash-Lite (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 3.5 Sonnet (June '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.1 Tulu3 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok 2 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 1.5 Flash (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-humanitys-last-exam","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Grok Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen2.5 Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen2.5 Coder Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral Saba","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 1.5 Pro (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen2.5 Turbo","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.2 Instruct 90B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen2 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 1.5 Flash-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepHermes 3 - Mistral 24B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Jamba 1.5 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Hermes 3 - Llama-3.1 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Jamba 1.6 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 1.5 Flash (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 3 Sonnet","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral Small (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemma 3n E4B Instruct Preview (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Qwen2.5 Coder Instruct 7B ","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral Large (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mixtral 8x22B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 2 Chat 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 2.1","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral Small (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM 40B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Gemini 1.0 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepSeek Coder V2 Lite Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 2 Chat 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 2 Chat 13B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"OpenChat 3.5 (1210)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DBRX Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Jamba 1.5 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Jamba 1.6 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mixtral 8x7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Claude Instant","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-humanitys-last-exam","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-ifbench","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-ifbench","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-ifbench","label":"Claude 4 Opus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-ifbench","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"QwQ 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-ifbench","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-ifbench","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-ifbench","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-itbench-aa","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-itbench-aa","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 4 Opus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.5 Pro Preview (Mar' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.5 Pro Preview (May' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-livecodebench","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.5 Flash Preview (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"o1-mini","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"QwQ 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.0 Flash Thinking Experimental (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Solar Pro 2 (Preview) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.0 Pro Experimental (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 3 Opus","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.5 Flash Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.0 Flash (experimental)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen2.5 Max","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 1.5 Pro (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Solar Pro 2 (Preview) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 3.5 Sonnet (Oct '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Sonar","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Sonar Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"QwQ 32B-Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-livecodebench","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.0 Flash-Lite (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 2.0 Flash-Lite (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.1 Tulu3 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok 2 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 1.5 Flash (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-livecodebench","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Grok Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen2.5 Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen2.5 Coder Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 1.5 Pro (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen2.5 Turbo","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.2 Instruct 90B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen2 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 1.5 Flash-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepHermes 3 - Mistral 24B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Jamba 1.5 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Hermes 3 - Llama-3.1 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Jamba 1.6 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 1.5 Flash (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 3 Sonnet","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mistral Small (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemma 3n E4B Instruct Preview (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Qwen2.5 Coder Instruct 7B ","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mistral Large (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mixtral 8x22B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 2 Chat 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 2.1","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mistral Small (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mistral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"LFM 40B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Gemini 1.0 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepSeek Coder V2 Lite Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 2 Chat 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 2 Chat 13B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"OpenChat 3.5 (1210)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DBRX Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Jamba 1.5 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Jamba 1.6 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mixtral 8x7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Claude Instant","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-livecodebench","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 4 Opus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.5 Pro Preview (Mar' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.5 Pro Preview (May' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Sonar Reasoning Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.5 Flash Preview (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"o1-preview","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"o1-mini","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"QwQ 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.0 Flash Thinking Experimental (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Solar Pro 2 (Preview) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.0 Pro Experimental (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 3 Opus","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Sonar Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.5 Flash Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.0 Flash (experimental)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Qwen2.5 Max","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 1.5 Pro (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Solar Pro 2 (Preview) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 3.5 Sonnet (Oct '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Sonar","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Sonar Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"QwQ 32B-Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-math-500","label":"Gemini 2.0 Flash-Lite (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.0 Flash-Lite (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 3.5 Sonnet (June '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.1 Tulu3 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Grok 2 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 1.5 Flash (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-math-500","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Grok Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Qwen2.5 Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Qwen2.5 Coder Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"DeepSeek-V2.5 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 2.0 Flash Thinking Experimental (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral Saba","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 1.5 Pro (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"R1 1776","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Qwen2.5 Turbo","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Reka Flash (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.2 Instruct 90B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Solar Mini","reason":"2024 evaluator model must not map to current April 2025 API revision"},{"source":"aa-math-500","label":"Qwen2 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 1.5 Flash-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"DeepHermes 3 - Mistral 24B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Jamba 1.5 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Hermes 3 - Llama-3.1 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"DeepSeek-Coder-V2","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Jamba 1.6 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 1.5 Flash (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 3 Sonnet","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral Small (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemma 3n E4B Instruct Preview (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Qwen2.5 Coder Instruct 7B ","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral Large (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mixtral 8x22B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 2 Chat 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 2.1","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral Small (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"LFM 40B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Gemini 1.0 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 2 Chat 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 2 Chat 13B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"OpenChat 3.5 (1210)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"DBRX Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Jamba 1.5 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Jamba 1.6 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mixtral 8x7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Claude Instant","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-math-500","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-mlcr-aa","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-mlcr-aa","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 4 Opus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.5 Pro Preview (Mar' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.5 Pro Preview (May' 25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-mmlu-pro","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.5 Flash Preview (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"o1-preview","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"o1-mini","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"QwQ 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.0 Flash Thinking Experimental (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Solar Pro 2 (Preview) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.0 Pro Experimental (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 3 Opus","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.5 Flash Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.0 Flash (experimental)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen2.5 Max","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 1.5 Pro (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Solar Pro 2 (Preview) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 3.5 Sonnet (Oct '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Sonar","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Sonar Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"QwQ 32B-Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-mmlu-pro","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 2.0 Flash-Lite (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 3.5 Sonnet (June '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.1 Tulu3 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok 2 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 1.5 Flash (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-mmlu-pro","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Grok Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen2.5 Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen2.5 Coder Instruct 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek-V2.5 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral Saba","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 1.5 Pro (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen2.5 Turbo","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.2 Instruct 90B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen2 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 1.5 Flash-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepHermes 3 - Mistral 24B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Jamba 1.5 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Hermes 3 - Llama-3.1 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Jamba 1.6 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 1.5 Flash (May '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 3 Sonnet","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral Small (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemma 3n E4B Instruct Preview (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Qwen2.5 Coder Instruct 7B ","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral Large (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mixtral 8x22B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 2 Chat 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 2.1","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral Small (Feb '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"LFM 40B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Gemini 1.0 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepSeek Coder V2 Lite Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 2 Chat 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 2 Chat 13B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"OpenChat 3.5 (1210)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DBRX Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Jamba 1.5 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Jamba 1.6 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mixtral 8x7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Claude Instant","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-mmlu-pro","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-mmmu-pro","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Gemini 2.5 Flash Preview (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Gemini 1.5 Pro (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Gemini 1.5 Flash (Sep '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Llama 3.2 Instruct 90B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Gemini 1.5 Flash-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-mmmu-pro","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Motif 3 (Beta)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-omniscience","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-omniscience","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-omniscience","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-omniscience","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"G9v3-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-omniscience","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-omniscience","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Motif 3 (Beta)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-omniscience-accuracy","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-omniscience-accuracy","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-omniscience-accuracy","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-omniscience-accuracy","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"G9v3-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-omniscience-accuracy","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-omniscience-accuracy","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-omniscience-accuracy","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-scicode","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-tau2-bench","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-tau2-bench","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-tau2-bench","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-tau2-bench","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-tau2-bench","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-tau2-bench","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Mistral Small 3","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Solar Mini","reason":"2024 evaluator model must not map to current April 2025 API revision"},{"source":"aa-tau2-bench","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.2 Instruct 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Mistral 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-tau2-bench","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-tau3-banking","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"MiMo-V2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"GPT-5.2 Codex (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Qwen3.6 Max Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Gemini 3 Pro Preview (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4.20 0309 v2 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4.20 0309 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"MiMo-V2-Omni-0327","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"GPT-5 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"MiMo-V2-Omni","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"GPT-5.1 Codex (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Claude 4.1 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"GPT-5.5 Instant (May 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"MiMo-V2-Flash (Feb 2026)","reason":"February API revision is distinct from the original MiMo V2 Flash weights"},{"source":"aa-terminalbench-hard","label":"Gemini 3 Pro Preview (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Kimi K2 Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Qwen3 Max Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Claude 4 Opus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"GPT-5.1 Codex mini (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4.1 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Kimi K2.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"JT-35B-Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"KAT-Coder-Pro V1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4 Fast (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Claude 3.7 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Ling-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Step 3.5 Flash 2603","reason":"Source explicitly labels 2603; exact match to current provider weights needs checkpoint review"},{"source":"aa-terminalbench-hard","label":"Step 3.5 Flash","reason":"February checkpoint must not map to the current rolling Step 3.5 Flash model"},{"source":"aa-terminalbench-hard","label":"Claude 4 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek V3.2 Exp (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Qwen3 Max Thinking (Preview)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Kimi K2 0905","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Claude 3.7 Sonnet (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 3 mini Reasoning (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4.20 0309 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4.20 0309 v2 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok Code Fast 1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek V3.1 Terminus (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek V3.2 Exp (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Apriel-v1.5-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek V3.1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Nova 2.0 Omni (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek V3.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Qwen3 VL 235B A22B (Reasoning)","reason":"Evaluator reasoning label conflicts with its linked Instruct checkpoint. Hold out until the evaluator identifies the actual Thinking or Instruct weights."},{"source":"aa-terminalbench-hard","label":"Apriel-v1.6-15B-Thinker","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Kimi K2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"JT-MINI","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 3","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LongCat Flash Lite","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"HyperCLOVA X SEED Think (32B)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4.1 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Nova 2.0 Omni (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Grok 4 Fast (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Mi:dm K 2.5 Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Ring-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"INTELLECT-3","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"K2-V2 (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Tri-21B-think Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Motif-2-12.7B-Reasoning","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Ling-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Magistral Medium 1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"K2-V2 (medium)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama Nemotron Super 49B v1.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Devstral Medium","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Tri-21B-Think","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Gemini 2.0 Flash (Feb '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"MiniCPM5-1B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Sarvam 105B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Devstral Small (May '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"MiniCPM5-1B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Magistral Small 1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Nova 2.0 Omni (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Hermes 4 - Llama-3.1 70B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Falcon-H1R-7B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Ling-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Qwen3 Omni 30B A3B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Qwen2.5 Instruct 72B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Devstral Small (Jul '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Mistral Large 2 (Nov '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Hermes 4 - Llama-3.1 405B (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Solar Pro 2 (Reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-terminalbench-hard","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Hermes 4 - Llama-3.1 405B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"K2-V2 (low)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.1 Instruct 405B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LFM2.5-8B-A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Ring-flash-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Olmo 3.1 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Solar Pro 2 (Non-reasoning)","reason":"July 2025 evaluator release must not map to current December 2025 API revision"},{"source":"aa-terminalbench-hard","label":"Command A","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.1 Nemotron Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.1 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Sarvam 30B (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Olmo 3.1 32B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Olmo 3 32B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Jamba 1.7 Large","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 4.0 H Small","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"OLMo 2 32B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LFM2 24B A2B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Phi-3 Mini Instruct 3.8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Jamba Reasoning 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Reka Flash 3","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Olmo 3 7B Think","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Claude 3 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"OLMo 2 7B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Molmo 7B-D","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Ling-mini-2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.2 Instruct 11B (Vision)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Sarvam M (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Olmo 3 7B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LFM2.5-1.2B-Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Jamba 1.7 Mini","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LFM2 2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LFM2.5-1.2B-Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 4.0 H 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Apertus 70B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 4.0 Micro","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 4.0 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Molmo2-8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LFM2 8B A1B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 3.3 8B (Non-reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LFM2 1.2B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"LFM2.5-VL-1.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 4.0 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3.2 Instruct 1B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Llama 3 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Apertus 8B Instruct","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Granite 4.0 H 350M","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Mi:dm K 2.5 Pro Preview","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-hard","label":"Cogito v2.1 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Agnes 2.5 Pro Beta","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Motif 3","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Motif 3 (Beta)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Muse Spark","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"K2 Horizon 375B A23B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Apodex 1.1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Nex-N2-Pro","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"JT-4.1 Flash 236B A21B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Grok Build 0.1 0616","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Ling 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Kimi K2.5 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"A.X-K2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"G9v3-39A5B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"KAT Coder Pro V2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Claude 4 Sonnet (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Granite 4.2 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"HyperNova 60B 2605 (high, based on gpt-oss-120b)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Nemotron Cascade 2 30B A3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"K2 Think V2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"G9v3-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Ling 2.6 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Claude 3.5 Haiku","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Nanbeige4.1-3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"LFM2.5-2.6B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Llama 3.3 Instruct 70B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Granite 4.1 30B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Llama 3.1 Instruct 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Granite 4.1 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"Granite 4.1 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v2-1","label":"MiniCPM-V 4.6 1.3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"DeepSeek V4.1 Flash (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Agnes 3.0 Flash","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"DeepSeek V4 Flash Vision (Reasoning, Max Effort)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Quasar 438B (max, based on GLM-5.2)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"GPT-5.5 Instant (June 2026)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Inkling Small","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Inkling (xhigh)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Ling-3.0-flash-VL","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"LongCat 2.0","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Muse Glimmer (high)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Ring-2.6-1T","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"DeepSeek V3.1 Terminus (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"North Mini Code","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Ling 3.0 Tiny","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Granite 4.2 8B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Mercury 2","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"DeepSeek R1 (Jan '25)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Trinity Large Thinking","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"DeepSeek V3 0324","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Granite 4.2 3B","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"DeepSeek V3 (Dec '24)","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Mistral Small 3.1","reason":"Unresolved exact catalog identity"},{"source":"aa-terminalbench-v4-0","label":"Celeris-1","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude 4.7 (High)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude 4.7 (Low)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude 4.7 (Max)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude 4.7 (Medium)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude Opus 4 (Thinking 16K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude Opus 4 (Thinking 1K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude Opus 4 (Thinking 8K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Opus 4.5 (Thinking, 16K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Opus 4.5 (Thinking, 64K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Opus 4.5 (Thinking, 8K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Opus 4.5 (Thinking, None)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude Sonnet 4 (Thinking 16K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude Sonnet 4 (Thinking 1K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Claude Sonnet 4 (Thinking 8K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Gemini 2.5 Flash (Preview) (Thinking 16K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Gemini 2.5 Flash (Preview) (Thinking 1K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Gemini 2.5 Flash (Preview) (Thinking 24K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Gemini 2.5 Flash (Preview) (Thinking 8K)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Grok 3 Mini (Low)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Grok 4 (Thinking)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Grok 4 (Fast Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Grok 4.20 (Reasoning)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Magistral Medium (Thinking)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"GPT-5.6 Luna 2026-07-30 (High)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"GPT-5.6 Luna 2026-07-30 (Low)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"GPT-5.6 Luna 2026-07-30 (Max)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"GPT-5.6 Luna 2026-07-30 (Medium)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"GPT-5.6 Luna 2026-07-30 (None)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"GPT-5.6 Luna 2026-07-30 (XHigh)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Inkling Small (High)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Inkling Small (Low)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Inkling Small (Medium)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Inkling Small (Minimal)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Inkling Small (None)","reason":"Unresolved exact catalog identity"},{"source":"arc-v2semiprivate","label":"Inkling Small (XHigh)","reason":"Unresolved exact catalog identity"},{"source":"terminal-terminus2","label":"Gemini 3 Pro","reason":"Unresolved exact catalog identity"},{"source":"terminal-geminicli","label":"Gemini 3 Pro","reason":"Unresolved exact catalog identity"},{"source":"livecode-generationpass1","label":"Claude-Opus-4 (Thinking)","reason":"Unresolved exact catalog identity"},{"source":"livecode-generationpass1","label":"Claude-Sonnet-4 (Thinking)","reason":"Unresolved exact catalog identity"},{"source":"livecode-generationpass1","label":"Grok-3-Mini (High)","reason":"Unresolved exact catalog identity"},{"source":"livecode-generationpass1","label":"O3-Mini-2025-01-31 (High)","reason":"Unresolved exact catalog identity"},{"source":"livecode-generationpass1","label":"O3-Mini-2025-01-31 (Low)","reason":"Unresolved exact catalog identity"},{"source":"vulcanbench-v3-13-deepseek-v4-pro","label":"DeepSeek V4 Pro","reason":"No exact catalog identity. Unversioned DeepSeek report predates current Pro revision; do not assume equivalence."},{"source":"vulcanbench-v3-13-deepseek-v4-pro","label":"DeepSeek V4-Flash","reason":"No exact catalog identity. Unversioned DeepSeek report predates current Pro revision; do not assume equivalence."},{"source":"Cognition","label":"SWE-2","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-2","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-2","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-2","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-2","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-2","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-1.7","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-1.7","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"Kimi K2.7","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"Kimi K2.7","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"Composer 2.5","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"Composer 2.5","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"Inkling","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"Inkling","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-1.6","reason":"No unambiguous catalog identity"},{"source":"Cognition","label":"SWE-1.6","reason":"No unambiguous catalog identity"},{"source":"ARC Prize","label":"GPT-5.6 Luna extra-high","reason":"Unreviewed effort label"},{"source":"ARC Prize","label":"GPT-5.6 Sol extra-high","reason":"Unreviewed effort label"},{"source":"ARC Prize","label":"GPT-5.6 Terra extra-high","reason":"Unreviewed effort label"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"GPT 6 Astra","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Gemini 3.8 Flash","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gpt-5.4-pro-2026-03-05","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Muse Spark","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gemini-3-pro-preview","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gpt-5.4-2026-03-05 (xhigh thinking)","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"claude-opus-4-7","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gpt-5-pro-2025-10-06","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gpt-5.2-2025-12-11","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gpt-5-2025-08-07","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"kimi-k2.5","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gemini-2.5-pro-preview-06-05","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"o3 (high) (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gpt-5-mini-2025-08-07","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"o3 (medium) (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Gemini 2.5 Pro Experimental (March 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"o4-mini (high) (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Gemini 2.5 Pro Preview (May 06 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"o4-mini (medium) (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"claude-opus-4-5-20251101","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Gemini 2.5 Flash (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"claude-opus-4-1-20250805-thinking","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Gemini 2.5 Flash Preview (May 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Claude Opus 4 (Thinking)","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gemini-3.1-flash-lite-preview","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"glm-4p5","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"glm-4p5-air","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"o1 Pro","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Claude 3.7 Sonnet (Thinking)","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"o1 (December 2024)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"claude-opus-4-1-20250805","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Claude Sonnet 4 (Thinking)","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"claude-sonnet-4-5-20250929","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"gpt-5.1-instant","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Claude Opus 4","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Gemini 2.0 Flash Thinking (January 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Llama 4 Maverick","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Claude Sonnet 4","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"GPT 4.5 Preview","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"GPT-4.1","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Gemini-1.5-Pro-002","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Mistral Medium 3","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Nova Pro","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Claude 3.5 Sonnet (October 2024)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"Nova Lite","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam","label":"GPT-4o (November 2024)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"GPT 6 Astra","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-5.4-pro-2026-03-05","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Gemini 3.8 Flash","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Muse Spark","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gemini-3-pro-preview","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-5.4-2026-03-05 (xhigh thinking)","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-5-pro-2025-10-06","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-5.2-2025-12-11","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-5-2025-08-07","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gemini-2.5-pro-preview-06-05","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"o3 (high) (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"o3 (medium) (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-5-mini-2025-08-07","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"o4-mini (high) (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Gemini 2.5 Pro Experimental (March 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Gemini 2.5 Pro Preview (May 06 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-oss-120b","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Qwen3-235B-A22B-Thinking-2507","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"o4-mini (medium) (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"DeepSeek-R1-0528","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"claude-opus-4-5-20251101","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"DeepSeek-V3.1","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Gemini 2.5 Flash (April 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Qwen3-235B-A22B","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"claude-opus-4-1-20250805-thinking","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Claude Opus 4 (Thinking)","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Gemini 2.5 Flash Preview (May 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-oss-20b","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"glm-4p5","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"glm-4p5-air","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"DeepSeek R1","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gemini-3.1-flash-lite-preview","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Claude 3.7 Sonnet (Thinking)","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"o1 (December 2024)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"o1 Pro","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"claude-sonnet-4-5-20250929","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Claude Sonnet 4 (Thinking)","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"claude-opus-4-1-20250805","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Gemini 2.0 Flash Thinking (January 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"gpt-5.1-instant","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Claude Opus 4","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"GPT 4.5 Preview","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Claude Sonnet 4","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Llama 4 Maverick","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"GPT-4.1","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"kimi-k2-instruct","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"DeepSeek V3 (March 2025)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Gemini-1.5-Pro-002","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Nova Micro","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Mistral Medium 3","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Claude 3.5 Sonnet (October 2024)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Nova Pro","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"Nova Lite","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","label":"GPT-4o (November 2024)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"GLM 5.2 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Gemini 3.8 Flash (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Opus 4.7 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Gpt 5.4 xHigh (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Opus 4.6 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"GPT 5.3 (Codex) xHigh","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Sonnet 4.6 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Opus 4.6 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"DeepSeek V4 Pro (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Muse Spark","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Glm 5 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Gemini 3.1 Pro (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Kimi K2.5 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Minimax M2.5 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-qna","label":"Gemini 3 Flash (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Opus-4.7 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Opus 4.8 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Gemini 3.8 Flash (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"GLM 5.2 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"GPT 5.3 (Codex) xHigh","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Opus-4.6 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Gemini-3.1-Pro (Gemini CLI)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Sonnet-4.6 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Glm-5 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Kimi-K2.5 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Minimax-M2.5 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-refactoring","label":"Gemini-3-Flash (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Gemini 3.8 Flash (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"GLM 5.2 (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"GPT 5.3 (Codex) xHigh","reason":"No unambiguous exact catalog checkpoint"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Opus 4.7 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Opus-4.6 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Opus-4.6 (Mini-SWE)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Sonnet-4.6 (Claude Code)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Muse Spark","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Gemini-3-Flash (Mini-SWE)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Gemini-3.1-Pro (Mini-SWE)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Glm-5 (Mini-SWE)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Deepseek V4 Pro (Mini-SWE-Agent)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Kimi-K2.5 (Mini-SWE)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"https://labs.scale.com/leaderboard/sweatlas-tw","label":"Minimax-M2.5 (Mini-SWE)","reason":"Exact effort or harness not identified; no default inferred"},{"source":"LiveBench","label":"deepseek-v4-flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"deepseek-v4-pro","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"glm-5.2","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"gpt-5.2-codex","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"grok-4.3","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"grok-4.5","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"grok-build-0.1","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"kimi-k2.6-thinking","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"kimi-k2.7-code","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"minimax-m3","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"qwen3.6-27b","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"qwen3.6-plus","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"qwen3.7-max","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"kimi-k3","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"inkling-xhigh","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"deepseek-v4-flash-0731","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"qwen3.8-max","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"smaug-agentic","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"smaug-mini","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"deepseek-v4-pro-0813","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"grok-4.6","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"qwen3.8-27b","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"ox-alpha-max","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"deepseek-v4-flash-vision-exp","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"glm-5.3","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"glm-5.3-flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"qwen3.8-flash-next","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"nemotron-3-ultra-550b-a55b","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"smaug-flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"LiveBench","label":"deepseek-v4.1-flash-max","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-4.1-2025-04-14","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"DeepSeek-V3-0324","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"DeepSeek-V3","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-235B-A22B no-thinking","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-235B-A22B thinking","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-32B no-thinking","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-32B thinking","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Llama-4-Maverick-17B-128E-Instruct","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen2.5-72B-Instruct","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Llama-3.3-70B-Instruct","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Llama-4-Scout-17B-16E-Instruct","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gemma-3-27b-it","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen2.5-Coder-32B-Instruct","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-4.1-mini-2025-04-14","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-4.1-nano-2025-04-14","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gemini-2.0-flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gemini-2.5-flash-preview-05-20 no-thinking","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Devstral-Small-2505","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"DeepSeek-V3-0324","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Claude Sonnet 3.5","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Claude Sonnet 4","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gemini-2.5-flash-preview-05-20 no-thinking","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-4.1-2025-04-14","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"o3-2025-04-16","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gemini-2.5-flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gemini-2.0-flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gemini-2.5-pro","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-Coder-480B-A35B-Instruct","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-235B-A22B-Thinking-2507","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-235B-A22B-Instruct-2507","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"o4-mini-2025-04-16","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"DeepSeek-R1-0528","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"horizon-alpha","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-Coder-30B-A3B-Instruct","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"horizon-beta","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"GLM-4.5","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"GLM-4.5 Air","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Grok Code Fast 1","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-oss-120b","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-oss-20b","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-4.1-mini-2025-04-14","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Kimi K2","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-235B-A22B","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-32B","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Kimi K2 Instruct 0905","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-Next-80B-A3B-Instruct","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"DeepSeek-V3.1","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Grok 4","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Claude Sonnet 4.5","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Claude Opus 4.1","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-5-codex","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-30B-A3B-Thinking-2507","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-30B-A3B-Instruct-2507","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"GLM-4.6","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"MiniMax M2","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Claude Opus 4.5","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Gemini 3 Pro Preview","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-5.1-codex-max","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Devstral-2-123B-Instruct-2512","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Devstral-Small-2-24B-Instruct-2512","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"DeepSeek-V3.2","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Claude Code","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"MiniMax M2.1","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-5.1-codex","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Kimi K2 Thinking","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"GLM-4.7","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Gemini 3 Flash Preview","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"GLM-4.7 Flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Kimi K2.5","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-5.2-codex","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3-Coder-Next","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"GLM-5","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Codex","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"MiniMax M2.5","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Junie","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Gemini 3.1 Pro Preview","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Claude Sonnet 4.6","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"gpt-5.3-codex","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3.5-35B-A3B","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3.5-397B-A17B","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Step-3.5-Flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"GLM-5.1","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"MiniMax M2.7","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3.5-27B","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Gemma 4 31B","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Cursor","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"GLM-5.1","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Kimi K2.6","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Gemini 3.5 Flash","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"MiniMax M3","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"MiMo V2.5 Pro","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3.6-27B","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"Qwen3.6-35B-A3B","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"SWE-rebench","label":"DeepSeek-V4 Flash [high]","reason":"Model checkpoint or effort has no explicit reviewed mapping"},{"source":"Epoch AI · MirrorCode","label":"claude-fable-5-1_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"claude-fable-5-1_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"claude-opus-5_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"gpt-5.6-sol_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"qwen3.8-max-0902_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"qwen3.8-max-0902_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"qwen3.8-max-0902_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen3.8-max-0902_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"qwen3.8-max-0902_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"qwen3.8-max-0902_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Erdos","label":"claude-fable-5-1_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-4o-mini-2024-07-18","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-4o-2024-08-06","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-4.1-nano-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-4.1-mini-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-4.1-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"o3-mini-2025-01-31_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"o1-2024-12-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"claude-3-opus-20240229","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"granite-4.0-micro","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"granite-4.0-micro","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"granite-4.0-micro","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"granite-4.0-1b","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"granite-4.0-1b","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen2.5-7b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"qwen2.5-7b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"qwen2.5-7b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"qwen2.5-32b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"mistral-small-3.2-2506","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"mistral-small-3.2-2506","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"mistral-small-3.1-2503","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"mistral-small-3.1-2503","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"mistral-small-3.1-2503","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"mistral-small-3-2501","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"mistral-small-3-2501","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"mistral-small-3-2501","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"Mistral-7B-Instruct-v0.3","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"Mistral-7B-Instruct-v0.3","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"Meta-Llama-3-8B-Instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"llama-2-7b-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"qwen3-max-2025-09-23","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-2026-03-05_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MirrorCode","label":"gpt-6-astra_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"gpt-6-astra_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-6-astra_none","reason":"Source reports none, but provider only documents Low through Max; hold out unsupported setting."},{"source":"Epoch AI · GPQA diamond","label":"granite-4.0-1b","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"deepseek-llm-67b-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Erdos","label":"gpt-5.5_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Erdos","label":"gpt-6-astra_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Erdos","label":"claude-fable-5_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"mistral-small-3.2-2506","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Erdos","label":"gpt-5.6-sol_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"Meta-Llama-3-8B-Instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"Llama-2-13b-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"granite-4.0-350m","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"granite-4.0-350m","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"granite-4.0-350m","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.4-nano-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.4-mini-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.4-nano-2026-03-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.4-mini-2026-03-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"deepseek-llm-67b-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"QwQ-32B","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"QwQ-32B","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"QwQ-32B","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.2-2025-12-11_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-2026-03-05_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o1-2024-12-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-4-0613","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o1-2024-12-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o1-2024-12-17_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o3-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o3-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-4.1-mini-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-3.5-turbo-0125","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-4o-mini-2024-07-18","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"Inkling_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"inkling-small_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"kimi-k2.5","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"qwen3.6-max-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"qwen3-max-2025-09-23","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"deepseek-v4-pro_max","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · SimpleQA Verified","label":"o4-mini-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.2-2025-12-11_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.2-2025-12-11_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"o3-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.4-nano-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"o4-mini-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.4-mini-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.2-2025-12-11_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.4-pro-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.1-2025-11-13_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.4-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5.2-2025-12-11_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"o3-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"o4-mini-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"o3-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-2026-03-05_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"qwen3.6-max-preview_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"o3-mini-2025-01-31_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.1-2025-11-13_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.2-2025-12-11_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-mini-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-nano-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.1-2025-11-13_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-mini-2026-03-17_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-mini-2026-03-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-mini-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-nano-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-nano-2026-03-17_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"qwen3-max-2025-09-23","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.2-2025-12-11_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"deepseek-v4-pro_none","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-nano-2026-03-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-nano-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.1-2025-11-13_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-4.1-mini-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-mini-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-3.5-turbo-0125","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-mini-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-nano-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-nano-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-nano-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-4o-mini-2024-07-18","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o3-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-4.1-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-4-turbo-2024-04-09","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-4o-2024-08-06","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o4-mini-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o4-mini-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o3-mini-2025-01-31_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-mini-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-mini-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-nano-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o3-mini-2025-01-31_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-nano-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · EBR-bench","label":"grok-4.6_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Mystery Game Puzzles","label":"inkling-small_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"inkling-small_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"inkling-small_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"inkling-small_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"inkling-small_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"inkling-small_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MirrorCode","label":"claude-opus-4-7_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OEIS Open Lite","label":"gemini-3.5-flash_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OEIS Open Lite","label":"gpt-5.5_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OEIS Open Lite","label":"claude-opus-4-8_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OEIS Open Lite","label":"gpt-5.6-sol_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OEIS Open Lite","label":"claude-fable-5_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OEIS Open","label":"gemini-3.5-flash_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OEIS Open","label":"gpt-5.5_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OEIS Open","label":"claude-opus-4-8_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5-mini-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SimpleQA Verified","label":"gpt-5-nano-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MirrorCode","label":"gemini-3.1-pro-preview_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MirrorCode","label":"gpt-5.5_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MirrorCode","label":"gpt-5.4-2026-03-05_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MirrorCode","label":"gpt-5.6-sol_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MirrorCode","label":"claude-fable-5_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"claude-opus-4-8_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"o1-2024-12-17_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o1-2024-12-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-4-0613","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-mini-2026-03-17_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-mini-2026-03-17_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-mini-2026-03-17_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o3-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-mini-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"qwen3.6-max-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-mini-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"qwen3.6-max-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o3-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.1-2025-11-13_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-mini-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen3.6-max-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o3-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.1-2025-11-13_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-4.1-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o4-mini-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o3-mini-2025-01-31_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o3-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.1-2025-11-13_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.1-2025-11-13_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o4-mini-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o4-mini-2025-04-16_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-mini-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-mini-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-mini-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-3.5-turbo-0125","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-nano-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-nano-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-nano-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-nano-2026-03-17_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-3.5-turbo-0125","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-mini-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-nano-2026-03-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-nano-2026-03-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-mini-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-nano-2026-03-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"deepseek-v4-pro_none","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"deepseek-v4-pro_high","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · Chess Puzzles","label":"deepseek-v4-pro_none","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · Chess Puzzles","label":"deepseek-v4-pro_high","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · GPQA diamond","label":"deepseek-v4-pro_none","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · GPQA diamond","label":"deepseek-v4-pro_high","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"magistral-small-2506","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"magistral-small-2506","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"Inkling_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"Inkling_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.2-2025-12-11_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"Inkling_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"Inkling_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"Inkling_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.5-instant","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5.5-instant","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.5-instant","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.5-instant","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.5-instant","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · EBR-bench","label":"gpt-5.5_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Mystery Game Puzzles","label":"claude-opus-4-1-20250805_24K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Mystery Game Puzzles","label":"gpt-5.4-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"claude-opus-4-1-20250805","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o1-2024-12-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o3-mini-2025-01-31_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o3-mini-2025-01-31_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · EBR-bench","label":"claude-fable-5_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"deepseek-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"deepseek-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"deepseek-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o1-2024-12-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o1-2024-12-17_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o1-2024-12-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"claude-3-opus-20240229","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-4o-2024-08-06","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o3-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o3-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o3-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o3-mini-2025-01-31_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-2026-03-05_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-2026-03-05_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-2026-03-05_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-2026-03-05_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-2026-03-05_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-2026-03-05_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-2026-03-05_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-2026-03-05_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-2026-03-05_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-2026-03-05_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-2026-03-05_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-2026-03-05_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-4o-mini-2024-07-18","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-4.1-mini-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-4-turbo-2024-04-09","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-nano-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-nano-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-nano-2025-08-07_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-nano-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-nano-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-nano-2025-08-07_minimal","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.2-2025-12-11_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.2-2025-12-11_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.2-2025-12-11_none","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o4-mini-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o4-mini-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o4-mini-2025-04-16_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.6-sol_promax","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5.6-sol_promax","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · EBR-bench","label":"claude-opus-4-7_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"claude-opus-4-6_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"gpt-5-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"glm-5.2_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"gpt-5.2-2025-12-11_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"glm-5.2_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"qwen3.7-max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"gpt-5.4-2026-03-05_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"gemini-3.5-flash_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"claude-opus-4-5-20251101_128K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"kimi-k2.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"claude-sonnet-4-5-20250929","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"claude-opus-4-1-20250805","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · EBR-bench","label":"gemini-3.1-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"qwen3.7-max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"deepseek-v4-pro_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"deepseek-v4-pro_max","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"deepseek-v4-pro_max","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"deepseek-v4-pro_max","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · GPQA diamond","label":"deepseek-v4-pro_max","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · Chess Puzzles","label":"deepseek-v4-pro_max","reason":"Checkpoint is unspecified; April and August V4 Pro must not be combined."},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5.4-pro-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.4-pro-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5.2-pro-2025-12-11_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.2-pro-2025-12-11_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5-pro-2025-10-06_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-pro-2025-10-06_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-mini-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5-mini-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5.4-nano-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.4-nano-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-nano-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5-nano-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5.4-mini-2026-03-17_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.4-mini-2026-03-17_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gdm-ai-co-mathematician","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"claude-opus-4-1-20250805_32K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"claude-opus-4-1-20250805_32K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5.4-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.4-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5.2-2025-12-11_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o4-mini-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"o3-mini-2025-01-31_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"o3-mini-2025-01-31_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"o4-mini-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5.2-2025-12-11_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-v2-Private","label":"gpt-5-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-fable-5_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-fable-5_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tiers-1-3-v2-Private","label":"gpt-5-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-8_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-8_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gemini-3.5-flash_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-3.5-flash_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gemini-3.5-flash_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"qwen3.6-max-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"qwen3.6-max-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"qwen3.6-max-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"qwen3.6-max-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"qwen3.6-max-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gemini-3.5-flash_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-3.5-flash_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"glm-5.1","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"qwen3.5-plus","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"qwen3.6-plus","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"qwen3.5-plus","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"qwen3.5-plus","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"qwen3.6-plus","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"qwen3.6-plus","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"qwen3.6-plus","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"qwen3.6-flash","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"qwen3.6-flash","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"qwen3.6-flash","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"qwen3.6-plus","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"qwen3.5-flash","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"qwen3.5-flash","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"qwen3.5-flash","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"glm-5.1","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"glm-5.1","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"glm-5.1","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gdm-ai-co-mathematician","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"kimi-k2.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"kimi-k2.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"kimi-k2.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"glm-5.1","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"kimi-k2.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.5-pro-pre-release_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.5-pro-pre-release_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.5-pro-pre-release_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.5-pre-release_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.5-pre-release_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5.5-pre-release_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.5-pre-release_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.5-pro-pre-release_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.5-pro-pre-release_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.5-pro-pre-release_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.5-pro-pre-release_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.5-pre-release_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.5-pre-release_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-opus-4-7_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-opus-4-7_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-7_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-7_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-7_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-mini-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-mini-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-mini-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5.4-mini-2026-03-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.4-mini-2026-03-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.4-mini-2026-03-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.4-nano-2026-03-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.4-nano-2026-03-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-nano-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5.4-nano-2026-03-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-nano-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-nano-2026-03-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"muse-spark","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"muse-spark","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"muse-spark","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"muse-spark","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5.4-2026-03-05_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5.4-2026-03-05_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5.4-2026-03-05_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-pro-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-pro-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.4-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5.4-2026-03-05_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.4-2026-03-05_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.4-2026-03-05_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.4-pro-2026-03-05-web-app","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.4-pro-2026-03-05_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.4-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.4-2026-03-05_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5.3-codex_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gemini-3.1-pro-preview-customtools","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-sonnet-4-6_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-sonnet-4-6_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-sonnet-4-6_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-sonnet-4-6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-sonnet-4-6_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"glm-5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-3.1-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gemini-3.1-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-3.1-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gemini-3.1-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"glm-5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gemini-3-flash-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-opus-4-6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5.1-2025-11-13_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"kimi-k2.5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5.1-2025-11-13_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"glm-5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-6_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gemini-2.5-pro","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gemini-3-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-opus-4-6_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"glm-5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-6_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"glm-5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-6_max","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5.2-2025-12-11_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"o3-2025-04-16_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-opus-4-1-20250805","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-4o-2024-11-20","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-opus-4-6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-4.1-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-opus-4-6_64K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-6_64K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-6_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-opus-4-6_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-6_64K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-6_64K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-6_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-6_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-opus-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-opus-4-5-20251101","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-sonnet-4-5-20250929","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · SWE-Bench verified","label":"claude-3-7-sonnet-20250219","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"fireworks/kimi-k2p5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"fireworks/kimi-k2p5","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"fireworks/kimi-k2p5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"fireworks/kimi-k2p5","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · SWE-Bench verified","label":"gpt-5-mini-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"grok-4-0709","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"zai-org/GLM-4.7","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"zai-org/GLM-4.7","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"fireworks/kimi-k2p5","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.2-pro-2025-12-11-webapp","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"fireworks/deepseek-v3p2","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gemini-2.5-flash","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-2.5-flash","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-3-flash-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-3-flash-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gemini-3-flash-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gemini-3-flash-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"fireworks/deepseek-v3p2","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"deepseek-reasoner","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"deepseek-reasoner","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"deepseek-reasoner","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.2-2025-12-11_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.2-2025-12-11_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.2-2025-12-11_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.2-2025-12-11_xhigh","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.2-2025-12-11_xhigh","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"openai/gpt-oss-120b_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"openai/gpt-oss-120b_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"openai/gpt-oss-120b_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.2-2025-12-11_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.2-2025-12-11_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5.2-2025-12-11_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5.2-2025-12-11_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.2-2025-12-11_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.2-2025-12-11_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.2-2025-12-11_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.2-2025-12-11_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.2-2025-12-11_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5.2-2025-12-11_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.2-2025-12-11_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.2-2025-12-11_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.2-2025-12-11_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5.2-2025-12-11_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.2-2025-12-11_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.2-2025-12-11_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5.2-2025-12-11_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.2-2025-12-11_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.2-2025-12-11_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.2-2025-12-11_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5.2-2025-12-11_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"Qwen/Qwen3-235B-A22B-Thinking-2507","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"Qwen/Qwen3-235B-A22B-Thinking-2507","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"Qwen/Qwen3-235B-A22B-Thinking-2507","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"Qwen/Qwen3-235B-A22B-Thinking-2507","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"qwen3-max-2025-09-23","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"kimi-k2-thinking-turbo","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"moonshotai/Kimi-K2-Thinking","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"zai-org/GLM-4.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"zai-org/GLM-4.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"zai-org/GLM-4.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"zai-org/GLM-4.6","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · Chess Puzzles","label":"o4-mini-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5.1-2025-11-13_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gpt-5-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"o3-mini-2025-01-31_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · Chess Puzzles","label":"gemini-3-pro-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"moonshotai/Kimi-K2-Thinking","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"moonshotai/Kimi-K2-Thinking","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"moonshotai/Kimi-K2-Thinking","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.1-2025-11-13_none","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.1-2025-11-13_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.1-2025-11-13_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-5-20251101","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-5-20251101","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-5-20251101_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-5-20251101_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-5-20251101_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-5-20251101_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-5-20251101_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-5-20251101","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-2.5-pro","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gemini-3-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-3-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-3-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-3-pro-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gemini-3-pro-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gemini-3-pro-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.1-2025-11-13_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.1-2025-11-13_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.1-2025-11-13_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.1-2025-11-13_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o3-2025-04-16_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o3-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o3-2025-04-16_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-2.5-pro","reason":"Mixed or unavailable scorer summary; do not select the best scorer"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-sonnet-4-5-20250929","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-sonnet-4-5-20250929_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o4-mini-2025-04-16_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o3-mini-2025-01-31_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"kimi-k2-thinking-turbo","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5.1-2025-11-13_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5.1-2025-11-13_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5.1-2025-11-13_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5.1-2025-11-13_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-sonnet-4-5-20250929_59K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5-mini-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o4-mini-2025-04-16_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o4-mini-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5-mini-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"grok-4-0709","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"kimi-k2-thinking-turbo","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"kimi-k2-thinking-turbo","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-nano-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5-mini-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5-mini-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5-nano-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5-nano-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5-mini-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5-nano-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-nano-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5-nano-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-5-mini-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-mini-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-mini-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-5-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-2025-08-07_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-sonnet-4-5-20250929_59K","reason":"Mixed or unavailable scorer summary; do not select the best scorer"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4-0613","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4-0314","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4-0314","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-haiku-4-5-20251001_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-sonnet-4-5-20250929_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-haiku-4-5-20251001_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-haiku-4-5-20251001_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-haiku-4-5-20251001_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-sonnet-4-5-20250929_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-sonnet-4-5-20250929_32K","reason":"Mixed or unavailable scorer summary; do not select the best scorer"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-haiku-4-5-20251001","reason":"Mixed or unavailable scorer summary; do not select the best scorer"},{"source":"Epoch AI · MATH level 5","label":"claude-haiku-4-5-20251001","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-haiku-4-5-20251001","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"grok-4-heavy-web-app","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"qwen3-max-2025-09-23","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5-pro-2025-10-06_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5-pro-2025-10-06_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"qwen3-max-2025-09-23","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen3-max-2025-09-23","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-sonnet-4-5-20250929","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-sonnet-4-5-20250929","reason":"Mixed or unavailable scorer summary; do not select the best scorer"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-sonnet-4-5-20250929","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-sonnet-4-5-20250929","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"glm-4.5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"glm-4.5","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-5-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-5-nano-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-5-nano-2025-08-07_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-5-mini-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"grok-4-0709","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"grok-4-0709","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"o4-mini-2025-04-16_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"o4-mini-2025-04-16_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-mini-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-mini-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-5-nano-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-5-nano-2025-08-07_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5-mini-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5-nano-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5-mini-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5-mini-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-5-nano-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5-nano-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-5-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-5-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-5-nano-2025-08-07_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-20250514_27K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-1-20250805_27K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-1-20250805_27K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-1-20250805","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-1-20250805_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-1-20250805_27K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-opus-4-1-20250805_27K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-opus-4-1-20250805_27K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-opus-4-1-20250805_16K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-opus-4-1-20250805_16K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-1-20250805","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-opus-4-1-20250805","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-opus-4-1-20250805","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4o-mini-2024-07-18","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-opus-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-sonnet-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gemini-2.5-pro","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-2.5-pro","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gemini-2.5-pro","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-2.5-pro-preview-06-05","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gemini-2.5-pro-preview-06-05","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-2.5-pro-preview-06-05","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gemini-2.5-pro-preview-06-05","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gpt-4.1-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-sonnet-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"o3-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"grok-3-mini-beta_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-3-5-sonnet-20241022","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-3-5-sonnet-20240620","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-opus-4-20250514_27K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"o3-mini-2025-01-31_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-opus-4-20250514_27K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-3-5-sonnet-20240620","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-sonnet-4-20250514_59K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-3-5-sonnet-20241022","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-3-7-sonnet-20250219_64K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"gpt-4.1-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"o4-mini-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"o3-mini-2025-01-31_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"DeepSeek-R1-0528","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"grok-3-beta","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"grok-3-beta","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"claude-sonnet-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"claude-opus-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"o4-mini-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Public","label":"o3-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"magistral-small-2506","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gemini-2.5-pro-preview-06-05","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"qwen3-235b-a22b","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"qwen3-235b-a22b","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gemini-2.5-pro-preview-05-06","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"DeepSeek-R1-0528","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-opus-4-20250514_27K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-7-sonnet-20250219_64K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"grok-3-mini-beta_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"DeepSeek-R1","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-sonnet-4-20250514_59K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"grok-3-beta","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-sonnet-4-20250514_59K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-sonnet-4-20250514_32K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-sonnet-4-20250514_32K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-opus-4-20250514_16K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-opus-4-20250514_16K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-sonnet-4-20250514_16K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-sonnet-4-20250514_16K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-sonnet-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-sonnet-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-opus-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-opus-4-20250514","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-opus-4-20250514","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-sonnet-4-20250514","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-opus-4-20250514","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-sonnet-4-20250514","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-2.5-flash-preview-05-20","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"qwen-plus-2025-04-28","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"qwen-plus-2025-04-28","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"DeepSeek-V3-0324","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gemini-2.5-pro-preview-05-06","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gemini-2.5-pro-preview-03-25","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"mistral-medium-2505","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"mistral-medium-2505","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"mistral-medium-2505","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o4-mini-2025-04-16_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o4-mini-2025-04-16_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-2.5-flash-preview-04-17","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o3-2025-04-16_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o3-2025-04-16_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o3-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o4-mini-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"o4-mini-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o3-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"o4-mini-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o4-mini-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"o3-2025-04-16_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o3-2025-04-16_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-4.1-nano-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-4.1-nano-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-4.1-mini-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4.1-nano-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4.1-mini-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4.1-mini-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"gpt-4.1-nano-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4.1-nano-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-4.1-mini-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-4.1-mini-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-4.1-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-4.1-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-4.1-2025-04-14","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4.1-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4.1-2025-04-14","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"grok-3-mini-beta_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"grok-3-mini-beta_low","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"grok-3-mini-beta_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"grok-3-mini-beta_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"grok-3-mini-beta_low","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"grok-3-mini-beta_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"grok-3-mini-beta_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"grok-3-mini-beta_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"grok-3-mini-beta_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"grok-3-beta","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"grok-3-beta","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"grok-3-beta","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"grok-3-beta","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"Llama-4-Maverick-17B-128E-Instruct-FP8","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"Llama-4-Maverick-17B-128E-Instruct-FP8","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"Llama-4-Scout-17B-16E-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"Llama-4-Scout-17B-16E-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"Llama-4-Maverick-17B-128E-Instruct-FP8","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"Llama-4-Maverick-17B-128E-Instruct-FP8","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Llama-4-Scout-17B-16E-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"Llama-4-Maverick-17B-128E-Instruct-FP8","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"qwen-turbo-2024-11-01","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"qwen-turbo-2024-11-01","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"qwen-plus-2025-01-25","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen-turbo-2024-11-01","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen-plus-2025-01-25","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"qwen-plus-2025-01-25","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"qwen-max-2025-01-25","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"qwen-max-2025-01-25","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"qwen-max-2025-01-25","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen-max-2025-01-25","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"qwen-max-2025-01-25","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"Hermes-2-Theta-Llama-3-70B","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"DeepSeek-V3-0324","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"DeepSeek-V3-0324","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"DeepSeek-V3-0324","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gemini-2.5-pro-exp-03-25","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"mistral-small-2501","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"mistral-small-2503","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"mistral-small-2503","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"mistral-small-2503","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"claude-3-7-sonnet-20250219_64K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-7-sonnet-20250219_64K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-3-7-sonnet-20250219_64K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-3-7-sonnet-20250219_64K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-3-7-sonnet-20250219_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gemma-3-27b-it","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-3-7-sonnet-20250219_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-3-5-haiku-20241022","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-5-haiku-20241022","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gemini-1.5-flash-8b-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"claude-3-7-sonnet-20250219_32K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-7-sonnet-20250219_32K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"DeepSeek-R1-Distill-Qwen-14B","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"DeepSeek-R1-Distill-Llama-70B","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-7-sonnet-20250219_32K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-2.0-flash-001","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"DeepSeek-V3","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"DeepSeek-V3","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"Llama-3.1-Tulu-3-70B-DPO","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-2.1","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-2.0","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-2.0-flash-thinking-exp-01-21","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o1-preview-2024-09-12","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-2.0-pro-exp-02-05","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o1-2024-12-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o1-2024-12-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-4o-2024-08-06","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-2.0-flash-001","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-3-5-sonnet-20240620","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-4o-2024-08-06","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-3-5-sonnet-20240620","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-1.5-flash-002","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gemini-1.5-flash-002","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-3-5-haiku-20241022","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-3-5-haiku-20241022","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-3-5-sonnet-20241022","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-3-5-sonnet-20241022","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o1-mini-2024-09-12_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o1-mini-2024-09-12_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o1-mini-2024-09-12_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o1-mini-2024-09-12_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o1-mini-2024-09-12_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o1-mini-2024-09-12_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-3-7-sonnet-20250219_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-3-7-sonnet-20250219_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o3-mini-2025-01-31_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"o3-mini-2025-01-31_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"grok-2-1212","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"gpt-4o-2024-11-20","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"mistral-large-2411","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"claude-3-7-sonnet-20250219","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"o3-mini-2025-01-31_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Public","label":"grok-2-1212","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"claude-3-7-sonnet-20250219","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"mistral-large-2411","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gpt-4o-2024-11-20","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-4.5-preview-2025-02-27","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4.5-preview-2025-02-27","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4.5-preview-2025-02-27","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"gpt-4-turbo-2024-04-09","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4-turbo-2024-04-09","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o3-mini-2025-01-31_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4-turbo-2024-04-09","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o1-2024-12-17_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-7-sonnet-20250219_16K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"DeepSeek-R1","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-7-sonnet-20250219_16K","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"claude-3-7-sonnet-20250219_16K","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"Meta-Llama-3-70B-Instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-1.5-pro-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"grok-2-1212","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"Llama-2-70b-chat-hf","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-5-sonnet-20240620","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-1.5-pro-002","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4o-2024-08-06","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-1.5-flash-002","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen2.5-32b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"mistral-large-2402","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-1.5-flash-8b-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-sonnet-20240229","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"DeepSeek-V3","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-1.0-pro-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-7-sonnet-20250219","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-5-sonnet-20241022","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"qwen2.5-72b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4o-2024-05-13","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-5-haiku-20241022","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-1.5-flash-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-haiku-20240307","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"claude-3-opus-20240229","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"o3-mini-2025-01-31_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gpt-4o-2024-11-20","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"mistral-large-2411","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"gemini-2.0-flash-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"mistral-large-2407","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-7-sonnet-20250219","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"claude-3-7-sonnet-20250219","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"grok-2-1212","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"o1-2024-12-17_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"o1-2024-12-17_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"o1-mini-2024-09-12_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"o1-mini-2024-09-12_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o3-mini-2025-01-31_high","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"o3-mini-2025-01-31_high","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gemini-2.0-pro-exp-02-05","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gemini-2.0-flash-thinking-exp-01-21","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"gemini-2.0-pro-exp-02-05","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gemini-2.0-flash-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"gemini-2.0-flash-001","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-4o-2024-11-20","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4o-2024-11-20","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"Phi-3-medium-128k-instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"DeepSeek-R1","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"phi-4","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"o3-mini-2025-01-31_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"o3-mini-2025-01-31_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"mistral-small-2501","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"qwen2.5-32b-instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"qwen2.5-32b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"mistral-small-2501","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gemini-1.5-flash-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-2.0","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-opus-20240229","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o1-mini-2024-09-12_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4o-2024-08-06","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"o1-preview-2024-09-12","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-sonnet-20240229","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-5-sonnet-20241022","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4-0125-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-2.1","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-haiku-20240307","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"claude-3-5-sonnet-20240620","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4o-2024-05-13","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gemini-1.5-flash-002","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4-0613","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gemini-1.5-pro-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4-1106-preview","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-4o-mini-2024-07-18","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gemini-1.5-pro-002","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"gpt-3.5-turbo-0125","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"gpt-4-0613","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gemini-1.5-flash-001","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gemini-1.5-pro-002","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-3.5-turbo-0125","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gemini-1.5-pro-001","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-4-1106-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-3.5-turbo-1106","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gemini-1.5-flash-002","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-2.0","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-3-5-sonnet-20241022","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-3-5-sonnet-20240620","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-3-opus-20240229","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-3-haiku-20240307","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"claude-3-sonnet-20240229","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"Yi-1.5-34B-Chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"Yi-34B-Chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"Llama-3.1-8B-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Llama-3.1-405B-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Llama-3.1-70B-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"grok-2-1212","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"gpt-4o-2024-05-13","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-4o-mini-2024-07-18","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-4o-2024-08-06","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"qwen2-72b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"qwen1.5-72b-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"qwen1.5-32b-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"o1-mini-2024-09-12_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"Hermes-2-Theta-Llama-3-70B","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"Llama-2-70b-chat-hf","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"Meta-Llama-3-70B-Instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"Meta-Llama-3-8B-Instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"Hermes-2-Theta-Llama-3-70B","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Meta-Llama-3-8B-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Meta-Llama-3-70B-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Llama-2-70b-chat-hf","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Yi-1.5-34B-Chat","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Yi-34B-Chat","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gpt-4-0125-preview","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"Mistral-7B-Instruct-v0.3","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"deepseek-llm-67b-chat","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"Mixtral-8x7B-Instruct-v0.1","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"gemma-2-9b-it","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"gemma-2-27b-it","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"qwen2.5-72b-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"qwen2-72b-instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Mistral-7B-Instruct-v0.3","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Mixtral-8x7B-Instruct-v0.1","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"deepseek-llm-67b-chat","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"WizardLM-2-8x22B","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"dbrx-instruct","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"WizardLM-2-8x22B","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"dbrx-instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"gemini-1.0-pro-001","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"gemini-1.0-pro-001","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"mistral-large-2402","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"open-mixtral-8x22b","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"mistral-large-2407","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"open-mixtral-8x7b","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"open-mistral-7b","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"ministral-3b-2410","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"open-mistral-7b","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"ministral-8b-2410","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"mistral-large-2407","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"open-mistral-nemo-2407","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"open-mixtral-8x7b","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"open-mixtral-8x22b","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"mistral-large-2402","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Llama-3.2-90B-Vision-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"Llama-3.1-Tulu-3-70B-DPO","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · GPQA diamond","label":"Eurus-2-7B-PRIME","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"Llama-3.1-Tulu-3-70B-DPO","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"Llama-3.3-70B-Instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"qwen2.5-72b-instruct","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · MATH level 5","label":"o1-preview-2024-09-12","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"o1-2024-12-17_medium","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"o1-2024-12-17_medium","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"DeepSeek-V3","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · MATH level 5","label":"DeepSeek-V3","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · GPQA diamond","label":"grok-4-0709","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · OTIS Mock AIME 2024-2025","label":"grok-4-0709","reason":"No reviewed exact checkpoint and setting mapping"},{"source":"Epoch AI · FrontierMath-2025-02-28-Private","label":"gemini-2.5-deep-think-2025-08-01-webapp","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Epoch AI · FrontierMath-Tier-4-2025-07-01-Private","label":"gemini-2.5-deep-think-2025-08-01-webapp","reason":"Task is outside this reviewed protocol set; external/reprinted and composite results are not admitted"},{"source":"Vals AI","label":"vals-finance-agent-v2: meta/muse_spark_1_3_max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: deepseek/deepseek-v4.1-flash","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: alibaba/qwen3.8-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: alibaba/qwen3.8-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: thinkingmachines/inkling","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: deepseek/deepseek-v4-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: thinkingmachines/inkling-small","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: nvidia/nemotron-3-ultra-550b-a55b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: kimi/kimi-k2.5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: ant/ling-3.0-flash-2607","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: google/gemini-3.1-flash-lite-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: poolside/laguna-m.1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: fireworks/nemotron-lightning-3p5-30b-a3b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-finance-agent-v2: poolside/laguna-xs.2","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: meta/muse_spark_1_3_max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: deepseek/deepseek-v4.1-flash","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: deepseek/deepseek-v4-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: alibaba/qwen3.8-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: alibaba/qwen3.8-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: thinkingmachines/inkling-small","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: thinkingmachines/inkling","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: kimi/kimi-k2.5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: nvidia/nemotron-3-ultra-550b-a55b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: google/gemini-3.1-flash-lite-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: fireworks/nemotron-lightning-3p5-30b-a3b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-code-migration-v1: ant/ling-3.0-flash-2607","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: meta/muse_spark_1_3_max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: alibaba/qwen3.8-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: deepseek/deepseek-v4.1-flash","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: alibaba/qwen3.8-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: thinkingmachines/inkling","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: thinkingmachines/inkling-small","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: deepseek/deepseek-v4-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: kimi/kimi-k2.5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: nvidia/nemotron-3-ultra-550b-a55b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: google/gemini-3.1-flash-lite-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: fireworks/nemotron-lightning-3p5-30b-a3b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: poolside/laguna-m.1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: poolside/laguna-xs.2","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-research-v1: ant/ling-3.0-flash-2607","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: meta/muse_spark_1_3_max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: alibaba/qwen3.8-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: alibaba/qwen3.8-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: deepseek/deepseek-v4.1-flash","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: deepseek/deepseek-v4-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: thinkingmachines/inkling","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: thinkingmachines/inkling-small","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: nvidia/nemotron-3-ultra-550b-a55b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: kimi/kimi-k2.5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: ant/ling-3.0-flash-2607","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: fireworks/nemotron-lightning-3p5-30b-a3b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-emb-v1: google/gemini-3.1-flash-lite-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-3-pro-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-opus-4-6-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: alibaba/qwen3.8-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-opus-4-1-20250805-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-sonnet-4-5-20250929-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: meta/muse_spark","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-opus-4-5-20251101-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: deepseek/deepseek-v4-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-opus-4-1-20250805","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: alibaba/qwen3.5-plus-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: minimax/MiniMax-M2.1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-5-2025-08-07","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-5.1-2025-11-13","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: thinkingmachines/inkling","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-3.1-flash-lite-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-5.2-2025-12-11","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-opus-4-20250514","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: zai/glm-5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: kimi/kimi-k2.5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: nvidia/nemotron-3-ultra-550b-a55b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/o3-2025-04-16","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-opus-4-5-20251101","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: thinkingmachines/inkling-small","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-4-0709","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: alibaba/qwen3-max-2026-01-23","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/deepseek-v3p2-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: alibaba/qwen3-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: alibaba/qwen3.8-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-4-1-fast-reasoning","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: alibaba/qwen3.5-flash","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-2.5-pro-exp-03-25","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-sonnet-4-20250514-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-2.5-flash-preview-09-2025","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-2.5-flash-preview-09-2025-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: alibaba/qwen3-max-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/o1-2024-12-17","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/deepseek-r1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/deepseek-v3p2","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: zai/glm-4.7","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-3-7-sonnet-20250219-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-5-mini-2025-08-07","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: zai/glm-4.6","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: ant/ling-3.0-flash-2607","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-3-mini-fast-high-reasoning","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/qwen3-235b-a22b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: zai/glm-4.5","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: kimi/kimi-k2-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-3-7-sonnet-20250219","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/o4-mini-2025-04-16","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-4.1-2025-04-14","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: minimax/MiniMax-M2.5","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-3-mini-fast-low-reasoning","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-3","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: mistralai/mistral-large-2512","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-4-fast-reasoning","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/deepseek-v3-0324","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-sonnet-4-20250514","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/llama4-maverick-instruct-basic","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: together/moonshotai/Kimi-K2-Instruct","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/gpt-oss-120b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-2.5-flash-lite-preview-09-2025-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/o3-mini-2025-01-31","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-2.5-flash-lite-preview-09-2025","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-3-5-sonnet-20241022","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-2.0-flash-001","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-4.1-mini-2025-04-14","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-5-nano-2025-08-07","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-2-1212","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-1.5-pro-002","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: mistralai/mistral-medium-2505","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-4-1-fast-non-reasoning","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-4o-2024-08-06","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/deepseek-v3","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-4o-2024-11-20","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: fireworks/gpt-oss-20b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: together/langston/nim/nvidia/llama-3.3-nemotron-super-49b-v1-42e84561","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: grok/grok-4-fast-non-reasoning","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: together/meta-llama/Llama-3.3-70B-Instruct-Turbo","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: mistralai/mistral-large-2411","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: together/meta-llama/Llama-4-Scout-17B-16E-Instruct","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: together/langston/nim/nvidia/llama-3.3-nemotron-super-49b-v1-42e84561-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: cohere/command-a-03-2025","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: poolside/laguna-xs.2","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: poolside/laguna-m.1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: mistralai/magistral-medium-2509","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: mistralai/mistral-small-2503","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: google/gemini-1.5-flash-002","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: mistralai/mistral-small-2402","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: anthropic/claude-3-5-haiku-20241022","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-4.1-nano-2025-04-14","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: openai/gpt-4o-mini-2024-07-18","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: mistralai/magistral-small-2509","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: ai21labs/jamba-large-1.6","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: cohere/command-r-plus","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-mmlu-pro-v1: ai21labs/jamba-mini-1.6","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: meta/muse_spark_1_3_max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: deepseek/deepseek-v4.1-flash","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: anthropic/claude-opus-4-8-claude-code","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: alibaba/qwen3.8-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: cursor/composer-2.5","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: alibaba/qwen3.8-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: openai/gpt-5.5-codex","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: openai/gpt-5.5-factory","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: thinkingmachines/inkling-small","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: nvidia/nemotron-3-ultra-550b-a55b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: ant/ling-3.0-flash-2607","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: deepseek/deepseek-v4-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: thinkingmachines/inkling","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: kimi/kimi-k2.5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: google/gemini-3.1-flash-lite-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: poolside/laguna-m.1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: poolside/laguna-xs.2","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-terminal-bench-2-1-v2.1: fireworks/nemotron-lightning-3p5-30b-a3b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: meta/muse_spark_1_3_max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: deepseek/deepseek-v4.1-flash","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: anthropic/claude-opus-4-8-claude-code","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.5-factory","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: alibaba/qwen3.8-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: alibaba/qwen3.8-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.3-codex","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.5-codex","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: anthropic/claude-opus-4-6","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: anthropic/claude-sonnet-4-6-claude-code","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.2-2025-12-11","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: anthropic/claude-opus-4-6-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: deepseek/deepseek-v4-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: cursor/composer-2.5","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.4","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.2-codex","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.1-2025-11-13","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: zai/glm-5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: anthropic/claude-sonnet-4-5-20250929-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.1-codex-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: anthropic/claude-opus-4-5-20251101-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5-2025-08-07","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: meta/muse_spark","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: thinkingmachines/inkling","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: thinkingmachines/inkling-small","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: kimi/kimi-k2.5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: alibaba/qwen3.5-plus-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: minimax/MiniMax-M2.5","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: google/gemini-3-pro-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5-mini-2025-08-07","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: grok/grok-build-0.1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: openai/gpt-5.1-codex","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: alibaba/qwen3.6-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: poolside/laguna-m.1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: nvidia/nemotron-3-ultra-550b-a55b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: devin/swe-1-6-fast","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: poolside/laguna-xs.2","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: fireworks/deepseek-v3p2-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: alibaba/qwen3-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: zai/glm-4.6","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: ant/ling-3.0-flash-2607","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: grok/grok-4-1-fast-reasoning","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: google/gemini-2.5-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: google/gemini-3.1-flash-lite-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: fireworks/nemotron-lightning-3p5-30b-a3b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: grok/grok-4-fast-reasoning","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-vibe-code-bench-v1.1: mistralai/mistral-small-2603","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: meta/muse_spark_1_3_max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: alibaba/qwen3.8-27b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: alibaba/qwen3.8-max","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: deepseek/deepseek-v4.1-flash","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: deepseek/deepseek-v4-pro","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: thinkingmachines/inkling","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: thinkingmachines/inkling-small","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: ant/ling-3.0-flash-2607","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: nvidia/nemotron-3-ultra-550b-a55b","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: google/gemini-3.1-flash-lite-preview","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: poolside/laguna-m.1","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: poolside/laguna-xs.2","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: kimi/kimi-k2.5-thinking","reason":"No reviewed catalog checkpoint mapping"},{"source":"Vals AI","label":"vals-legal-agent-benchmark-v1: fireworks/nemotron-lightning-3p5-30b-a3b","reason":"No reviewed catalog checkpoint mapping"}]},"collections":[{"collection":"evaluators","datasetId":"sha256-1f186994047883a45f76e96fbce2f07320baf4f104506414be2bba69a334a02f","collectedOn":"2026-09-12"},{"collection":"vulcan","datasetId":"sha256-2bc644d4e2fb34bd4fecd1ef0a2a50302a9d18f3b8cd3aa0e6dfc487669f5146","collectedOn":"2026-09-12"},{"collection":"frontier","datasetId":"sha256-b6d2e58f71798704ee9f3e6b341e3627e6b0dc1caef890fc1e08b62a226e3f36","collectedOn":"2026-09-12"},{"collection":"scale","datasetId":"sha256-7a7d95c40c608cc28483fb5cef9007da8c102f1e7278882ccbcc02a16078607d","collectedOn":"2026-09-12"},{"collection":"public-panels","datasetId":"sha256-99e5ccb2eac4abb63cc6d9823b591f2ffac992cdee03ac725f66bd8a5ec086a3","collectedOn":"2026-09-12"},{"collection":"epoch","datasetId":"sha256-9fbe9729fecc9cf9232f3292684307ba1a85d69beff3920a2a7ed9e2c77bf7ef","collectedOn":"2026-09-12"},{"collection":"vals","datasetId":"sha256-7e00d90a437b5a33e79607a04b57b10dc14322bbaa63ce8bbe9ce1338eaf26f5","collectedOn":"2026-09-12"}]}