{"version":"configuration-source-6","evidencePolicy":"documented","snapshotId":"sha256-0b34099efb151066ec22056e009a9e3f7c52e2fbbd868d149b8048536deb478e","effortDatasetId":"sha256-cffe59fa16a1dc623567e648803fec61bb2e0c2cc0926a34c8ae43760f5e3915+sha256-dd005fc2bb1ab65961b2be02cd585d2d5f9c7ed268ed142deb8c49e8d545c752+sha256-158573528f2ff04fb2a7cab4ffd20a4610a8df7f0f7308b80385972b8866d433+sha256-de620ffa9569f336561f4207ee2393f9317be42bb46feb77afd0c916f7113a95+sha256-1585546fe0418ea483c694c111c94252f437ed9951b58696dc033d5a04a82f22+sha256-473c33f3c3f5409aae2743970275192c3a84c19fb88596a9a5043a3770fe30d5+sha256-09499abf878f0e4b7ad3db24c3dc30c8c8858533c163ddf67ff9e62449994fad+sha256-ec259150369a6165584c0d668fef9535662ac1fdbca50a5a672e9ab0954ec448","scope":"All collected observations, not a claim that every public result has been collected. Contributing means positive graph weight, not sufficient evidence for a rank.","models":[{"id":"qwen-3.8-max-0902","collected":28,"contributing":26,"admittedWithoutWeight":0,"excluded":2}],"observations":[{"id":"da52383d0adbea5bac566881","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d8edd7d2aa84144dc3b7207c","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa1a1bdf910ef317b8401dea","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c19a4187a390134377264605","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0859f1b81ba43c4145f5564","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e75523cf36922d42a24da9fb","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60804c4839d8668fdf2ea433","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b88e41bb58b9c73ec1d1365","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf961538bccee947e708831f","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd3d162756c1542303a70143","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5585b2281e2706ef214733b","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"568a1843c4cc6821607175c1","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf2c0f94f35b14e6893dc878","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e64bf939cef3770af807eec9","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffd1cced0f7fffa9fbef8d49","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c5748c028be706993862b536","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c52b4fcacf00d9875e5df164","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea6fb5c196f9227bddf85436","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"excluded","reason":"Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode"},{"id":"97cfbdd8759773dcb23ca28c","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d206ce1d616b3fb7831293d2","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminal-bench-science","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b23b336fbb3ed47d2adb3456","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4511d031aae80264db54af32","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-2f8Vn5QBdJnc9i5y9jzXS7","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-8qGBfpdQXMmLcSqPwz7ofm","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-FpQf5xBwJPb4ZEo6SgdKWq","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-kZUdrqdGtCEJa3ip6L9YnH","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nBcLJJomVoeg2zh5F8Mnsu","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VzeQXKBH9maR2nDcZJ8b7S","modelId":"qwen-3.8-max-0902","configurationId":"qwen-3.8-max-0902--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"}]}