{"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":"97108923-aaaf-594e-8913-b11a13688ff9","task_key":"all--test--97108923-aaaf-594e-8913-b11a13688ff9","task_revision_id":"1","upstream_id":"","short_description":"A research project compared the performance of learning disabled and of normal…","config":"all","split":"test","body":"{\"choices\":\"['usually offers greater protection against Type Il error', 'does not require multiple-comparison follow-up tests in order to interpret significant effects', 'usually offers greater protection against a Type I error', 'is conceptually and computationally a simpler and more efficient approach']\",\"question\":\"A research project compared the performance of learning disabled and of normal students on ten scales of the Wechsler Intelligence Scale for Children ~ Revised (WISC-R). Ten univariate analyses of variance (ANOVAs) were run to test for differences between the two groups, but use of a multivariate analysis of variance (MANOVA) would have been more desirable because MANOVA\",\"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":[]}