{"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":"2af75ea1-fe12-5fdb-bafc-52e3455c2e56","task_key":"default--test--10581","task_revision_id":"1","upstream_id":"10581","short_description":"a) 3652_8 × 24_8 b b ) 11.01_2 × 1.01_2 ) 11.01_2 × 1.01_2 c) 5AB_16 × F5A_16","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"['235761_8, 110.1100_2, ABF55C_16', '305214_8, 101.1101_2, 1DF570_16', '172340_8, 111.1101_2, 5AB0F5_16', '987654_8, 101.1010_2, FEDCBA_16', '451236_8, 100.1011_2, 0F5A5B_16', '123456_8, 111.1111_2, ABCDEF_16', '731642_8, 110.1011_2, A55A1F_16', '114510_8, 100.0001_2, 57031D_16', '654321_8, 000.0000_2, 12345F_16', '146253_8, 101.0110_2, F5A0AB_16']\",\"question\":\"a) 3652_8 × 24_8 b b ) 11.01_2 × 1.01_2 ) 11.01_2 × 1.01_2 c) 5AB_16 × F5A_16\",\"src\":\"stemez-ComputerScience\"}","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":[]}