{"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-distill-llama-70b","collected":15,"contributing":12,"admittedWithoutWeight":0,"excluded":3}],"observations":[{"id":"243c60a86656d1595c85745b","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dd78fb19901b64635db44f7","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2db469a257b0c3f2f9b40bfd","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6222d4f378654bfa05436ac","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17ee47efdbcf843333a4b243","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae831c640f2a28b64b82e0c4","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9505e9c34edbb45f0c1117f","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6fc19818675129310568bb8b","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01313163168fd0c915717c34","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8e893e3e38807fa7c5bc79c","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2f9d19dbc5ed104d40cdfb95","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b37220933b4b948d9b751ff","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63f152f6d7e4690aaad8b67a","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-89zcekqEYnE8zhwG4pR5Nu","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-f6pnAATjxmrFJS353EjQKi","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"}]}