{"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":"4f121ee3-39b1-5b19-bc0f-12ec398168d2","task_key":"all--test--4f121ee3-39b1-5b19-bc0f-12ec398168d2","task_revision_id":"1","upstream_id":"","short_description":"Which of the following assessment measures is not used to assess symptom…","config":"all","split":"test","body":"{\"choices\":\"['Test of Memory Malingering', 'The Differential Aptitude Test–5', 'Recognition Memory Test', 'Personality Assessment Inventory']\",\"question\":\"Which of the following assessment measures is not used to assess symptom validity or malingering?\",\"subject\":\"professional_psychology\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/hendrycks/test","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}