{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmmu-pro","formal_name":"MMMU-Pro","introduction":"MMMU-Pro evaluates multimodal understanding across academic disciplines using images and text. The official card lists 1,730 questions per setting, separating four-option and ten-option standard settings from the vision setting.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://mmmu-benchmark.github.io/","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":"3e6c3810-6dcd-5dde-be28-1b38d6a483c5","task_key":"standard~20~2810~20options~29--test--test~5fMath~5f11","task_revision_id":"4","upstream_id":"test_Math_11","short_description":"<image 1> shows the results from looking at the diagnostic accuracy of a new…","config":"standard (10 options)","split":"test","body":"{\"img_type\":\"['Tables']\",\"options\":\"['0.950', '0.985', '0.975', '0.970', '0.990', '0.980', '0.965', '0.960', '0.995']\",\"question\":\"<image 1> shows the results from looking at the diagnostic accuracy of a new rapid test for HIV in 100,000 subjects, compared to the Reference standard ELISA test. The rows of the table represent the test result and the columns the true disease status (as confirmed by ELISA). What is the Sensitivity of the new rapid test for HIV? Report the answer to 3 decimal places.\",\"subject\":\"Math\"}","display_format":"text","language":"","answer_status":"published","assets":[{"kind":"file","reference_id":"task:3e6c3810-6dcd-5dde-be28-1b38d6a483c5:4:image_1.png","filename":"image_1.png","media_type":"image/png","alt":""}],"source_url":"https://mmmu-benchmark.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}