{"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":"03678be5-9a75-50f6-8085-2030154dd8a2","task_key":"default--test--11106","task_revision_id":"1","upstream_id":"11106","short_description":"\" _Ad lazarum_ \" is a specific kind of","config":"default","split":"test","body":"{\"category\":\"philosophy\",\"options\":\"['Fallacy of composition', 'Complex cause', 'Red herring', 'False sign', 'Hasty generalization', 'Anecdotal evidence', 'False criteria', 'Slippery slope argument', 'Straw man argument', 'Informal fallacy']\",\"question\":\"\\\" _Ad lazarum_ \\\" is a specific kind of\",\"src\":\"ori_mmlu-logical_fallacies\"}","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":[]}