{"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":"6b1c2a3c-26f8-5938-9500-bb2da55c0965","task_key":"all--test--6b1c2a3c-26f8-5938-9500-bb2da55c0965","task_revision_id":"1","upstream_id":"","short_description":"Late one night, co-defendants broke into a warehouse and proceeded to load the…","config":"all","split":"test","body":"{\"choices\":\"['burglary and arson.', 'larceny and arson.', 'larceny only.', 'burglary, larceny, and arson.']\",\"question\":\"Late one night, co-defendants broke into a warehouse and proceeded to load the large crates of appliances onto their truck. As they were leaving, one of the co-defendants inadvertently threw his cigarette butt into a refuse pile of old cardboard boxes and papers. Soon afterward, the refuse ignited into a small fire. Although the co-defendants had time to douse the fire without any danger to themselves, neither did so. Instead, they climbed into the truck and fled. Meanwhile, the fire quickly spread, engulfing the entire warehouse in flames. At common law, the co-defendants should be found guilty of\",\"subject\":\"professional_law\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/hendrycks/test","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}