{"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":"613ca202-9071-5573-8975-9a0dcf0b5bf2","task_key":"default--test--10455","task_revision_id":"1","upstream_id":"10455","short_description":"K-fold cross-validation is","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"['logarithmic in K', 'exponential in K', 'square root in K', 'sine in K', 'cubic in K', 'factorial in K', 'quadratic in K', 'linear in K', 'constant in K', 'cosine in K']\",\"question\":\"K-fold cross-validation is\",\"src\":\"ori_mmlu-machine_learning\"}","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":[]}