{"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":"ec890dee-a411-5358-bdd3-6a7f51c1ad4e","task_key":"default--test--8886","task_revision_id":"1","upstream_id":"8886","short_description":"What is the probability of a Type II error when a hypothesis test is being…","config":"default","split":"test","body":"{\"category\":\"math\",\"options\":\"['0.80', '0.01', '0.50', '0.20', '1.00', '0.001', 'There is insufficient information to answer this question.', '0.05', '0.90', '0.10']\",\"question\":\"What is the probability of a Type II error when a hypothesis test is being conducted at the 10% significance level (α = 0.10)?\",\"src\":\"ori_mmlu-high_school_statistics\"}","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":[]}