{"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":"deepseek-r1-0528","collected":19,"contributing":13,"admittedWithoutWeight":0,"excluded":6}],"observations":[{"id":"28154d8ea2e87ddacaa50495","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d1f9132429ab5fb1330d2974","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d457e9fe5dc1d1849bde49ee","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89c583f754304a1af65e90d8","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89234d302d97c8daf59156c8","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2894a03cfe0dd1c35eb63b61","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"51289684897e664af54a05d2","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3bf8f6694da5448f8d82c11","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"10731a3c1d964999d4ff6598","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac159579de0c6415663fa834","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da46f877760d8faa5938e0c0","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b93f0ed6713171396a82dc72","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18a2418d73fee9d97b9e6213","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91a19a0300fec337c23eaa24","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bBV5wCrrZtihrgxEsg9jPD","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-LiRiryJsGb3h5UuxX8bmJv","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"s-lcb-deepseek-r1-0528-ad3f286332a4","modelId":"deepseek-r1-0528","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-deepseek-r1-0528-465fe8c26c46","modelId":"deepseek-r1-0528","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-deepseek-r1-0528-df03094a9acf","modelId":"deepseek-r1-0528","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"}]}