{"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":"8f60915a-f3b2-53d6-8852-a5480282593f","task_key":"default--test--8845","task_revision_id":"1","upstream_id":"8845","short_description":"A court is investigating the possible occurrence of an unlikely event T. The…","config":"default","split":"test","body":"{\"category\":\"math\",\"options\":\"['0.120', '0.082', '0.001', '0.025', '0.050', '0.075', '0.100', '0.150', '0.200', '0.010']\",\"question\":\"A court is investigating the possible occurrence of an unlikely event T. The reliability of two independent witnesses called Alf and Bob is known to the court: Alf tells the truth with probability \\\\alpha and Bob with probability \\\\beta, and there is no collusion between the two of them. Let A and B be the events that Alf and Bob assert (respectively) that T occurred, and let \\\\tau=P(T). What is the probability that T occurred given that both Alf and Bob declare that T occurred? Suppose \\\\alpha=\\\\beta=9/10 and \\\\tau=1/1000. Return the answer up to the thousands decimal.\",\"src\":\"theoremQA-Math\"}","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":[]}