{"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":"0d21d4ae-5e4e-5969-bcfa-85811c5f0776","task_key":"default--test--757","task_revision_id":"1","upstream_id":"757","short_description":"These goods are bought infrequently, used repeatedly, and involve a reasonably…","config":"default","split":"test","body":"{\"category\":\"business\",\"options\":\"['Staple goods.', 'Specialty goods.', 'Luxury goods.', 'Perishable goods.', 'Impulse goods.', 'Durable goods.', 'Non-durable goods.', 'Services.', 'Unsought goods.', 'Complementary goods.']\",\"question\":\"These goods are bought infrequently, used repeatedly, and involve a reasonably high level of consumer risk:\",\"src\":\"ori_mmlu-marketing\"}","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":[]}