{"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":"d5bfdc72-6aec-56f6-990c-e2766b4032f0","task_key":"default--test--2765","task_revision_id":"1","upstream_id":"2765","short_description":"The Leiter International Performance Scale would be most useful for measuring…","config":"default","split":"test","body":"{\"category\":\"psychology\",\"options\":\"['adults with speech impairments.', 'children under the age of two.', 'adults who are mentally retarded.', 'adults with physical disabilities.', 'children with hearing impairments.', 'children with learning disabilities.', 'children with visual impairments.', 'elderly people with memory loss.', 'teenagers with emotional disorders.', 'adults with visual impairments.']\",\"question\":\"The Leiter International Performance Scale would be most useful for measuring the intelligence of:\",\"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":[]}