{"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":"6bd28935-d09c-53ac-b4c8-d5bbcbc138f0","task_key":"all--test--6bd28935-d09c-53ac-b4c8-d5bbcbc138f0","task_revision_id":"1","upstream_id":"","short_description":"Which of these is the best description of a P-value?","config":"all","split":"test","body":"{\"choices\":\"['The probability of making a Type I error.', 'The probability of making a Type II error.', 'The probability of rejecting the null hypothesis if it is, in fact, false.', 'The probability of getting a test statistic at least as extreme as the observed test statistic, if the null hypothesis is true.']\",\"question\":\"Which of these is the best description of a P-value?\",\"subject\":\"high_school_statistics\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/hendrycks/test","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}