{"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":"761bf817-d199-5f2a-8d41-c4ccc14b8d28","task_key":"default--test--8769","task_revision_id":"1","upstream_id":"8769","short_description":"5.2- II. Evaluate","config":"default","split":"test","body":"{\"category\":\"math\",\"options\":\"['0.3087', '0.2148', '0.0896', '0.3456', '0.0991', '0.1792', '0.1623', '0.1286', '0.2569', '0.2014']\",\"question\":\"5.2- II. Evaluate\\n$$\\n\\\\int_0^{0.4} \\\\frac{\\\\Gamma(7)}{\\\\Gamma(4) \\\\Gamma(3)} y^3(1-y)^2 d y\\n$$\\n(a) Using integration.\",\"src\":\"scibench-stat\"}","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":[]}