{"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":"f9603e19-4199-58bb-be43-334007fb92b6","task_key":"default--test--10420","task_revision_id":"1","upstream_id":"10420","short_description":"Statement 1| Layer Normalization is used in the original ResNet paper, not Batch…","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"[\\\"Statement 2 is True, but it's not clear about Statement 1\\\", 'Statement 1 and 2 are both partially true and partially false', \\\"Statement 1 is False, but it's not clear about Statement 2\\\", 'False, True', \\\"Statement 1 is True, but it's not clear about Statement 2\\\", 'True, True', \\\"Statement 2 is False, but it's not clear about Statement 1\\\", 'True, False', 'Both Statements are unclear', 'False, False']\",\"question\":\"Statement 1| Layer Normalization is used in the original ResNet paper, not Batch Normalization. Statement 2| DCGANs use self-attention to stabilize training.\",\"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":[]}