{"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":"5a8ef637-f75c-5e7a-8a12-052700d4ef79","task_key":"default--test--10462","task_revision_id":"1","upstream_id":"10462","short_description":"How many labeled graphs with a score of (6, 2, 2, 2, 2, 2, 2) are there?","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"['35', '20', '25', '18', '30', '24', '40', '12', '15', '10']\",\"question\":\"How many labeled graphs with a score of (6, 2, 2, 2, 2, 2, 2) are there?\",\"src\":\"theoremQA-EECS\"}","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":[]}