{"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-v4-pro","collected":72,"contributing":36,"admittedWithoutWeight":0,"excluded":36}],"observations":[{"id":"4708dc64616b39f8d34ca8f1","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14e10a95b270ef9d1ae373e7","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b8d6f24397d8867cf1faec4","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dd052bf6a4ebf107f6de0da","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09421a76c727dce721916f4d","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43690b5f91d764a37de970d1","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcda011b6a3f738075dafcfd","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b35b842ffe605a75e112290","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"760ef06b17543599268b84e3","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ba74afd46cc724b0e2b9629","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1556f05dd2908433d9fc662b","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a30393a098bcb7270303b12f","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49acabfd6982ca02015ff725","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89082513bd20d1cb04639c1d","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf40d9275e4b9284715bca88","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cfe21e52f99ab0089cdaebe9","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c64dd03820fdf345d94145b0","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f79426f1f5a6b4e49959783","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25337d15a8b7bed1bf41c830","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d725d4dd6ab63e2174499861","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-none","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac3167852c54be45702e8943","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"excluded","reason":"DeepSeek V4 Pro checkpoint is not identified by this source; April and August revisions must not be combined."},{"id":"28a8f1e475f0000b4b484058","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"DeepSeek V4 Pro checkpoint is unspecified; April and August must remain separate."},{"id":"78cbe45f9b9ed1991de85fd0","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f33b674105fc71448617806","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3ef1bc9e68ff51e017bc544","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"DeepSeek V4 Pro checkpoint is unspecified; April and August must remain separate."},{"id":"epoch-run-2xfFf6KZAp2gUWYhHGkFgs","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4HVvM9ZWKKPLQPcC8WYYMT","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-a4uV8HMMBAcHXLVSmZfBgX","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-b6yWmeFgsWeEiG9Qzs3NSf","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-c2KVkMCWnpo6BbnMWgdaDH","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-EyKecrMhk7Yx25e5HGW43i","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nEJGtXGN588zynPkynZkxz","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-deepseek-1136","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1137","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1148","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-deepseek-1154","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1158","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1163","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-deepseek-1169","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1175","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1180","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1186","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1192","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1201","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1215","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1223","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1252","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1281","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1289","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1297","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1305","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1313","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"s-arc2-deepseek-v4-pro-efebf61be277","modelId":"deepseek-v4-pro","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-deepswe-deepseek-v4-pro-eb88d1c756c0","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-ds-aa","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/models/comparisons/deepseek-v4-pro-vs-o3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-ds-browse","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-hle","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-lcb","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-swepro","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-swev","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-tb21","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gdpval-deepseek-v4-pro-58c478670eac","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-deepseek-v4-pro-41e862296ea6","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-deepseek-v4-pro-465fe8c26c46","modelId":"deepseek-v4-pro","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"}]}