{"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-flash","collected":50,"contributing":35,"admittedWithoutWeight":0,"excluded":15}],"observations":[{"id":"a45c68223e1ae374ae76da31","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a7f324185d4152bcefff6a8","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"198c518ceb539e173702fd0e","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f80aa4cb8ac1c1539ed4751","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5034155f9f373466e08a2796","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7aef406561c55abab75d5692","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"407f6ccc80858a01c74fe91a","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f1a652d223fdc1a82c7a442","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e9a79f5ae68e547841899c9","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35b25adff9293e9983993576","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"40312e88cf305dbd9f804e18","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ac03d02aab2b66b5ec98d6a","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06b57055d7bf20ee8731a0c4","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c415823cdba1670ec1db8602","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b00c6e5708fb4aa9f02984e9","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39a7bed5705711ac27a52863","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c846403c911a1743e84cc3c3","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcce4d406862908e10d2d67e","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a96e7a8059bfa86f6a2589c","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-none","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b3518db91f03758794ffbbc","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c92e3a3655317402e6e0fc6","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae189fcaebaa21a3fe020a5f","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4S4GXbkRhLz8wWP97jYG57","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-EDFusDaaFkh5n2MqKNxMBD","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-FQ3Suh2vKacz7UNqJybTWk","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--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-Kk4oLoTLyDuqfnbqjPSvgZ","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mKhVMEicZeGjdvJdTRd7mK","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--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-TqFmiGvqozt7TSZYmhgF8m","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-WYs83xB6NwrkMNyQJtuMcQ","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","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-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","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-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","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-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","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-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","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-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","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-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-deepseek-1138","modelId":"deepseek-v4-flash","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-1139","modelId":"deepseek-v4-flash","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-1149","modelId":"deepseek-v4-flash","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-1155","modelId":"deepseek-v4-flash","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-1159","modelId":"deepseek-v4-flash","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-1164","modelId":"deepseek-v4-flash","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-1170","modelId":"deepseek-v4-flash","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-1176","modelId":"deepseek-v4-flash","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-1181","modelId":"deepseek-v4-flash","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-1187","modelId":"deepseek-v4-flash","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-1193","modelId":"deepseek-v4-flash","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":"s-deepswe-deepseek-v4-flash-eb88d1c756c0","modelId":"deepseek-v4-flash","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-lmarena-deepseek-v4-flash-465fe8c26c46","modelId":"deepseek-v4-flash","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"}]}