{"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":"2afab91f-229b-554b-8303-d222289019a8","task_key":"default--test--8799","task_revision_id":"1","upstream_id":"8799","short_description":"Which statement is false?","config":"default","split":"test","body":"{\"category\":\"math\",\"options\":\"['5 > 3', '10 < 20', '−3 > −5', '3 < 5', '-10 < -5', '0 > -1', '−5 > −3']\",\"question\":\"Which statement is false?\",\"src\":\"ori_mmlu-elementary_mathematics\"}","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":[]}