{"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":"c05666ef-3518-51db-8c87-1226e31d5400","task_key":"default--test--6340","task_revision_id":"1","upstream_id":"6340","short_description":"We want our measures to be as reliable as possible; reliability refers to","config":"default","split":"test","body":"{\"category\":\"health\",\"options\":\"['Whether our measure is ethical to use', 'Whether our measure has or has not been used before', 'Whether our measure provides new insights', 'Whether our measure is approved by an authority', 'Whether our measure is popular among researchers', 'Whether our measure is consistent in the information it provides', 'Whether our measure is cost-effective', 'Whether our measure really measure anything at all', 'Whether our measure is really measuring what it claims to measure', 'Whether our measure can be easily replicated']\",\"question\":\"We want our measures to be as reliable as possible; reliability refers to\",\"src\":\"ori_mmlu-human_aging\"}","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":[]}