{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmlu-pro","formal_name":"MMLU-Pro","introduction":"MMLU-Pro rebuilds MMLU with ten answer options instead of four and removes items that no longer separate models. Questions span fourteen academic and professional subjects.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"a20ce2c2-4454-5d1e-9a9b-fa77890527c3","task_key":"default--test--10557","task_revision_id":"1","upstream_id":"10557","short_description":"Another term for out-of-distribution detection is?","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"['precision-recall detection', 'underfitting detection', 'bias-variance tradeoff detection', 'regularization detection', 'one-class detection', 'overfitting detection', 'cross-validation detection', 'background detection', 'train-test mismatch robustness', 'anomaly detection']\",\"question\":\"Another term for out-of-distribution detection is?\",\"src\":\"ori_mmlu-machine_learning\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}