{"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":"6591394f-df53-5e86-8855-ecf278309300","task_key":"default--test--2503","task_revision_id":"1","upstream_id":"2503","short_description":"The items for 2 machinist proficiency test have been based on 2 job analysis of…","config":"default","split":"test","body":"{\"category\":\"psychology\",\"options\":\"['face validity', 'concurrent validity', 'internal validity', 'criterion validity', 'convergent validity', 'construct validity', 'empirical validity', 'predictive validity', 'discriminant validity', 'content validity']\",\"question\":\"The items for 2 machinist proficiency test have been based on 2 job analysis of machinists in 50 plants, each employing five or more machinists doing comparable work. Such 2 procedure would contribute directly to the test's\",\"src\":\"ori_mmlu-professional_psychology\"}","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":[]}