{"version":"configuration-source-5","evidencePolicy":"documented","snapshotId":"sha256-df858793dcb753b0f77beb223fce04e1de99a2c08f2c7b5f14534efcafa8c7c5","effortDatasetId":"sha256-1f186994047883a45f76e96fbce2f07320baf4f104506414be2bba69a334a02f+sha256-2bc644d4e2fb34bd4fecd1ef0a2a50302a9d18f3b8cd3aa0e6dfc487669f5146+sha256-b6d2e58f71798704ee9f3e6b341e3627e6b0dc1caef890fc1e08b62a226e3f36+sha256-7a7d95c40c608cc28483fb5cef9007da8c102f1e7278882ccbcc02a16078607d+sha256-99e5ccb2eac4abb63cc6d9823b591f2ffac992cdee03ac725f66bd8a5ec086a3+sha256-9fbe9729fecc9cf9232f3292684307ba1a85d69beff3920a2a7ed9e2c77bf7ef+sha256-7e00d90a437b5a33e79607a04b57b10dc14322bbaa63ce8bbe9ce1338eaf26f5","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":"qwen3-235b-a22b-instruct-2507","collected":16,"contributing":12,"admittedWithoutWeight":0,"excluded":4}],"observations":[{"id":"d77b602a8a35d0a4a648dd95","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67ad2e1e4f3abbfc96fd72d0","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d7d03c896b07879689bc033","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1622a07edd5343e87803e57a","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d64fc0c5fd25c6f3f2839386","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02dd73192a322d1d0f8c6c1d","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1461f99f24065e4929bc6f5","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d34742eb5d738ba73157d238","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e8399cdab1190c86e4e1550d","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f17f8f143ab442b52c0ca93","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c7456329253fb027797f510f","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70d0cd044393c24c57a06146","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b42443b66c734d0f2d7c944","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-arc2-qwen3-235b-a22b-instruct-2507-efebf61be277","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-235b-a22b-instruct-2507-465fe8c26c46","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3-235b-a22b-instruct-2507-df03094a9acf","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"}]}