{"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":"0aee4b91-9392-51db-aa85-df527b9acabc","task_key":"default--test--7864","task_revision_id":"1","upstream_id":"7864","short_description":"An ordinary deck of cards containing 26 red cards and 26 black cards is shuffled…","config":"default","split":"test","body":"{\"category\":\"math\",\"options\":\"['53.2', '50.2', '47.3', '46.5', '51.5', '50.0', '49.9', '45.6', '48.8', '52']\",\"question\":\"An ordinary deck of cards containing 26 red cards and 26 black cards is shuffled and dealt out one card at a time without replacement. Let $X_i$ be the color of the $i$th card. Compute $H(X_1,X_2,\\\\ldots,X_{52})$ in bits.\",\"src\":\"theoremQA-Math\"}","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":[]}