{"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":"qwen3.5-2b","collected":26,"contributing":23,"admittedWithoutWeight":0,"excluded":3}],"observations":[{"id":"a7c022f322decc2d18aacdf5","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--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":"340251b326024b7a69c3bf39","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6189f1ea70832a412f06340","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98ea8b4e38a123443727892b","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d62f734d7f7d727dff607f0b","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d4a80b838db126050c276e6","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1dc539f5096fa85e6092c50a","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1efb5443137143050e7ed17e","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"248d8fef7e7a90ae0e4e2295","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bd48532b9a85b06d476758b","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67088604dbeb65c302440afb","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a54f47fe6f74069debb77e36","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dfcabb11e935b9d77c34307","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f426f85b359f8e2fe9579751","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0aba9d436f02774f10805fd1","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4ebd8fc4a160d868162f9b65","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"05ae862b6429e595ff8d2b84","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30a8a589ff73daf9b30088ef","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60624d170a81e918f4879de3","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f24913e7ca1a2f286dbdce8","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"20c954bf67b034614b5f10b0","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"050daa4bef2d46ebbccd176d","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"84335a8349dd1b9d4fa8d0d2","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31afa3a5ee4f8ddeb7c59185","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-QeVP4X52JBDZBdeefZjEmb","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-mmlu-pro-qwen3.5-2b-df03094a9acf","modelId":"qwen3.5-2b","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"}]}