{"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":"7c0e232c-b619-5279-bd14-70fcf529ab4f","task_key":"default--test--8552","task_revision_id":"1","upstream_id":"8552","short_description":"Which of the following is notrequired in a binomial setting?","config":"default","split":"test","body":"{\"category\":\"math\",\"options\":\"['There is a fixed number of trials.', 'The probability of success is constant from trial to trial.', 'The value of the random variable of interest is the number of trials until the first success occurs.', 'The value of the random variable of interest is the number of successful trials.', 'Each trial is considered either a success or a failure.', 'Each trial is independent.']\",\"question\":\"Which of the following is notrequired in a binomial setting?\",\"src\":\"ori_mmlu-high_school_statistics\"}","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":[]}