{"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":"9f6e2973-9fe6-56ed-8725-8266a48f45e3","task_key":"default--test--2452","task_revision_id":"1","upstream_id":"2452","short_description":"A score of 50 on the Beck Depression Inventory-II suggests:","config":"default","split":"test","body":"{\"category\":\"psychology\",\"options\":\"['moderate depression.', 'extremely severe depression.', 'mild to moderate depression.', 'depression with anxiety disorder.', 'mild depression.', 'severe anxiety, not depression.', 'depression with psychotic features.', 'borderline clinical depression.', 'no or minimal depression.', 'severe depression.']\",\"question\":\"A score of 50 on the Beck Depression Inventory-II suggests:\",\"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":[]}