{"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":"a3141ebc-f174-52f4-b24e-4ec643273705","task_key":"default--test--10697","task_revision_id":"1","upstream_id":"10697","short_description":"Let $X$ be uniformly distributed over $\\{1, 2, \\ldots, m\\}$. Assume $m=2^n$ . We…","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"['0.3', '0.4', '0.1', '0.0', '0.7', '0.2', '0.5', '1.0', '0.8', '0.6']\",\"question\":\"Let $X$ be uniformly distributed over $\\\\{1, 2, \\\\ldots, m\\\\}$. Assume $m=2^n$ . We ask random questions: Is $X\\\\in S_1$? Is $X\\\\in S_2$? ... until only one integer remains. All $2^m$ subsets of $\\\\{1, 2, \\\\ldots, m\\\\}$ are equally likely. Suppose we ask $n+\\\\sqrt{n}$ random questions. Use Markov's inequality to find the probability of error (one or more wrong objects remaining) when $n$ goes to infinity?\",\"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":[]}