{"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":"52ed9336-1cc5-52e6-b3e6-3f17f858f2ae","task_key":"default--test--10549","task_revision_id":"1","upstream_id":"10549","short_description":"What is the output of \"abc\"[-1] in Python 3?","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"['ab', '\\\"abc\\\"', 'a', '1', '-1', 'b', 'abc', 'Error', 'None', 'c']\",\"question\":\"What is the output of \\\"abc\\\"[-1] in Python 3?\",\"src\":\"ori_mmlu-high_school_computer_science\"}","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":[]}