{"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-thinking-2507","collected":29,"contributing":21,"admittedWithoutWeight":0,"excluded":8}],"observations":[{"id":"6d1a4f33583a5e4cf8e7a06b","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ecc084f491a729e9b7a74c9","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a5ed8eea3db9089c7dbc5ff","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb8fa7dd28b53b28a7ead28e","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1990682da03247d86412c31","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a399e93d52acd969298026c","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16c9acfa6c591aba2ddf7c2f","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0558174eaf2fcd898108553e","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72ec400df622abf0993c0b92","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07bdaa927df321564f2c1d84","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44d7a6991cc91d58c55ff9a6","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cabc23b6d1570087cdf40e87","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67ad8c31109848b751082bc1","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f706dbdb38fdc0c25ef1282","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"963e940e7972f41eb041f884","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e126146d0f6fd5e675ea5077","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"257a65544bb4192d4e6972b6","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e51a19f3141204938b7e3a3c","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2acb2f76d344a5a0435308de","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c1071699ff2079d8fdebc1b","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2f2ba29d0427aaad4c86e0c6","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2209fa80f3ef69cff5c6933e","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4ACEC4x26HWRGiAepHGw43","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-7iH4kjDYrjgRwQdKYgNACT","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"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-BP3KYD8rYyFg3LviNGtjLL","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-gu39ndv9QxWP3NRxSUJRaX","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-XWpHpVPCaVjcwPpdpXuuGH","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"s-lmarena-qwen3-235b-a22b-thinking-2507-465fe8c26c46","modelId":"qwen3-235b-a22b-thinking-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-thinking-2507-df03094a9acf","modelId":"qwen3-235b-a22b-thinking-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"}]}