{"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":"3e79738b-a8d9-5a26-bbe7-ec83adc6e9b0","task_key":"default--test--2148","task_revision_id":"1","upstream_id":"2148","short_description":"The first standardized measure of assessment was:","config":"default","split":"test","body":"{\"category\":\"psychology\",\"options\":\"['Thematic Apperception Test', 'Wechsler Adult Intelligence Scale', 'Stanford Binet', 'Holtzman Inkblot Test', 'Raven’s Progressive Matrices', 'Binet–Simon Scale', 'Rorschach Inkblot Test', 'Minnesota Clerical Test', 'Minnesota Multiphasic Personality Inventory', 'Woodcock–Johnson Tests of Cognitive Abilities']\",\"question\":\"The first standardized measure of assessment was:\",\"src\":\"ori_mmlu-professional_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":[]}