{"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":"bc9e91ba-76d7-562d-9b2e-771f728ef8bd","task_key":"all--test--bc9e91ba-76d7-562d-9b2e-771f728ef8bd","task_revision_id":"1","upstream_id":"","short_description":"\" _Ad novitatem_ \" is","config":"all","split":"test","body":"{\"choices\":\"['arguing that what is true of a few members of a class is true of all members of the class', 'drawing a conclusion by applying irrelevant criteria to a subject', 'substituting individual stories for a larger sample as support for a claim', 'arguing that something must be good because it is new, or must be bad because it is old']\",\"question\":\"\\\" _Ad novitatem_ \\\" is\",\"subject\":\"logical_fallacies\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/hendrycks/test","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}