{"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":"51331389-ad2c-5adf-82b6-d8c798f56b92","task_key":"default--test--2334","task_revision_id":"1","upstream_id":"2334","short_description":"The principal effect of the current concern co improve the employment…","config":"default","split":"test","body":"{\"category\":\"psychology\",\"options\":\"['intelligence quotient tests', 'norm-referenced test', 'tests that assess physical abilities', 'work-sample types of tests', 'timed tests of a narrow range of abilities', 'personality assessment tests', 'tests based solely on academic performance', 'tests based on social skills']\",\"question\":\"The principal effect of the current concern co improve the employment opportunities of the educationally or socially disadvantaged has been to encourage the use in employment testing of\",\"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":[]}