{"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":"6ac1ff4c-1997-5e04-8778-9ea582e666d0","task_key":"default--test--2258","task_revision_id":"1","upstream_id":"2258","short_description":"\"Rosenhan’s research involving “pseudopatients\"\" who were admitted to…","config":"default","split":"test","body":"{\"category\":\"psychology\",\"options\":\"[\\\"showed that the environment influences how a person's behavior is perceived.\\\", 'demonstrated that all hospitals treat mental health patients in the same way.', 'showed that pseudopatients were treated better than regular patients.', 'proved that psychiatric treatment methods are ineffective.', '\\\"showed that “central traits\\\"\\\" have a greater impact than other traits on impression formation.\\\"', 'indicated that the majority of psychiatrists can easily distinguish between real and pseudopatients.', 'revealed that pseudopatients were always recognized by hospital staff.']\",\"question\":\"\\\"Rosenhan’s research involving “pseudopatients\\\"\\\" who were admitted to psychiatric hospitals:\\\"\",\"src\":\"ori_mmlu-professional_psychology\"}","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":[]}