{"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":"qwen3.5-0.8b","collected":25,"contributing":22,"admittedWithoutWeight":0,"excluded":3}],"observations":[{"id":"c79f005bd2c96b3dfac33ffa","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--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":"6526c4eb6102f766c4c1062f","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0bdc890c6710da451dc8600","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60b7d90d07f72044a849d7a4","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07ef03c305071784ff828680","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"694b1c4ba5beca31bc0eb98e","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f1ad55633cc7a58851cd2c9","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cf0f7313bdb3bb306cf325b","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00910596b4c53cfe534ac0eb","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c91f30bb30bc36833d46e2a","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dedc8bed9daad7fda2892e8f","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b20cc339a7f979c41b1c036d","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6fa5f20a494fa9ecedcc7ee","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8aad14fd7116de2c2cfdeeef","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f04c11d1b1e78ba49a626d3e","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"937ba73b35a8ad5eb48af2c0","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"aff956fbf6dee32a521c6a67","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9eb4731b4ea4ea831d5585e4","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c43d78ed5ec033460060cf6c","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ced6927af98788f28fec7064","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe58f57624f6bfd77e4a529b","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f848e97ce77653c8903415bd","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0557d91e1328599eddeedaa0","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c477d7a9ed5f790dea8bffe","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"s-mmlu-pro-qwen3.5-0.8b-df03094a9acf","modelId":"qwen3.5-0.8b","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"}]}