{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmlu","formal_name":"MMLU","introduction":"MMLU asks four-way multiple-choice questions across 57 subjects, from elementary material to professional-level examinations. Since 2020 it has been the most widely cited single reference point for general capability.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://github.com/hendrycks/test","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":"eeab2f92-8193-52fe-9f1c-4ee09a35d0d7","task_key":"all--test--eeab2f92-8193-52fe-9f1c-4ee09a35d0d7","task_revision_id":"1","upstream_id":"","short_description":"In ethics, the terms \"right\" and \"wrong\" are used primarily to evaluate the…","config":"all","split":"test","body":"{\"choices\":\"['persons.', 'actions.', 'consequences.', 'concrete objects.']\",\"question\":\" In ethics, the terms \\\"right\\\" and \\\"wrong\\\" are used primarily to evaluate the morality of\",\"subject\":\"moral_disputes\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/hendrycks/test","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}