{"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":"3370ce00-6373-590d-83da-e3d8bc70c4c2","task_key":"default--test--4970","task_revision_id":"1","upstream_id":"4970","short_description":"A more accurate calibration curve and conversion for radiocarbon dating can be…","config":"default","split":"test","body":"{\"category\":\"history\",\"options\":\"['coins recovered from ancient shipwrecks.', 'dendrochronology.', 'all of the above.', 'ice core sampling.', 'written records.', 'bone dating of ancient human remains.', 'examination of sediment layers.', 'satellite imagery.', 'fossil records.', 'carbon dating of historical buildings.']\",\"question\":\"A more accurate calibration curve and conversion for radiocarbon dating can be derived from:\",\"src\":\"ori_mmlu-prehistory\"}","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":[]}