{"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":"labs-devstral-small-2512","collected":24,"contributing":21,"admittedWithoutWeight":0,"excluded":3}],"observations":[{"id":"7131dec20596d2df6c1be3f2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f0df62b80b8c9fb83b0a81e","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"277826d88691ec9eb915047f","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f649238deb9d8f1ed9c39912","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ccc3445c3156458123a9871","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e7d98632bdb7b424068a7d8","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"148f96724c8bc1918313cee2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5dd89b6fd04dc8216937a0a5","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdb350e52c16cc800f8fdb1a","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0eb124052c0750dd77638fa8","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f3a8b308a46b3d8691e4eb2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f58575e3393fbefc53600c5f","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"81f793d6f2f88bd3529fa166","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"390f00a5572b8173cd2b52e2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c975ec825cce37abe4db74e","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"589703a977c33adb0239d69f","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d79254e334d06a2ca47d4ed","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f52fe8389f1bb8f3ded3aa92","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c90b87546d259a25837a5c2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d988ff2eb76e6caf21e5e2a4","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f111753b1bee273c77e6e9e0","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dac65a9f62774845dbe0cc7","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-mistral-1966","modelId":"labs-devstral-small-2512","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-labs-devstral-small-2512-58c478670eac","modelId":"labs-devstral-small-2512","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"}]}