{"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":"3c188a46-51af-5b2c-89ae-5d06c12e0e28","task_key":"default--test--8229","task_revision_id":"1","upstream_id":"8229","short_description":"An outlier is an observation that","config":"default","split":"test","body":"{\"category\":\"math\",\"options\":\"['is the mode of the data set', 'is the mean of the data set', 'is seen more frequently than the other observations in the data set', 'is always larger than the other observations in the data set', 'is always smaller than the other observations in the data set', 'is seen less frequently than the other observations in the data set', 'is significantly different from the other observations in the data set', 'is an error in the data set', 'is the median of the data set', 'is exactly the same as the other observations in the data set']\",\"question\":\"An outlier is an observation that\",\"src\":\"ori_mmlu-high_school_statistics\"}","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":[]}