{"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":"8d02984b-f0e2-5e30-9c91-e7942e9bf1e8","task_key":"default--test--10634","task_revision_id":"1","upstream_id":"10634","short_description":"Which of the following is false?","config":"default","split":"test","body":"{\"category\":\"computer science\",\"options\":\"['Semantic segmentation models predict the class of each pixel, while multiclass image classifiers predict the class of entire image.', 'A bounding box with an IoU (intersection over union) equal to $96\\\\\\\\%$ would likely be considered at true positive.', 'When a predicted bounding box does not correspond to any object in the scene, it is considered a false positive.', 'A bounding box with an IoU (intersection over union) equal to $3\\\\\\\\%$ would likely be considered at false negative.']\",\"question\":\"Which of the following is false?\",\"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":[]}