{"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":"5555f7f2-7128-5746-bef8-216319e05d5b","task_key":"default--test--10668","task_revision_id":"1","upstream_id":"10668","short_description":"Statement 1| When learning an HMM for a fixed set of observations, assume we do…","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"['True, True', 'True, False', 'False, False', 'False, True']\",\"question\":\"Statement 1| When learning an HMM for a fixed set of observations, assume we do not know the true number of hidden states (which is often the case), we can always increase the training data likelihood by permitting more hidden states. Statement 2| Collaborative filtering is often a useful model for modeling users' movie preference.\",\"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":[]}