{"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":"17903683-36a4-5620-8759-c3423e971031","task_key":"all--test--17903683-36a4-5620-8759-c3423e971031","task_revision_id":"1","upstream_id":"","short_description":"This operates algorithmically or using a mixture of algorithmic and human input…","config":"all","split":"test","body":"{\"choices\":\"['Banner ads.', 'Pop-up ads.', 'A search engine.', 'Apps.']\",\"question\":\" This operates algorithmically or using a mixture of algorithmic and human input to collect, index, store, and retrieve information on the web (e.g. web pages, images, information, and other types of files). It makes the information available to users in a manageable and meaningful way in response to a search query. This is referred to as:\",\"subject\":\"marketing\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/hendrycks/test","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}