{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmlu-pro","formal_name":"MMLU-Pro","introduction":"MMLU-Pro rebuilds MMLU with ten answer options instead of four and removes items that no longer separate models. Questions span fourteen academic and professional subjects.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","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":"b49dad1b-5643-54df-8af0-0eeb8034bdcc","task_key":"default--test--2293","task_revision_id":"1","upstream_id":"2293","short_description":"Standardized tests are","config":"default","split":"test","body":"{\"category\":\"psychology\",\"options\":\"['tests that are used to measure intelligence', 'tests that are given only once a year', 'tests that have no right or wrong answers', \\\"tests for which a person's performance can be compared with a pilot group\\\", 'any examination given by your state or country', 'tests that are only multiple-choice questions', 'tests given by your school district']\",\"question\":\"Standardized tests are\",\"src\":\"ori_mmlu-high_school_psychology\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}