{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmmu-pro","formal_name":"MMMU-Pro","introduction":"多様な学問分野の画像とテキストを組み合わせ、マルチモーダル理解を評価するベンチマークです。公式データカードでは各設定に1,730問があり、4択・10択の標準設定と画像のみの設定を区別します。\n\nMMMU-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":"noindex"},"task_id":"15c35de9-ca78-5493-b04a-397c7f1713cd","task_key":"standard~20~2810~20options~29--test--validation~5fMath~5f28","task_revision_id":"1","upstream_id":"validation_Math_28","short_description":"Is <image 1> a Cayley diagram?","config":"standard (10 options)","split":"test","body":"{\"img_type\":\"['Diagrams']\",\"options\":\"['Uncertain', 'Maybe', 'Unlikely', 'Probably not', 'No', 'Likely', 'Yes', 'Possibly']\",\"question\":\"Is <image 1> a Cayley diagram?\",\"subject\":\"Math\"}","display_format":"text","language":"","answer_status":"published","assets":[{"kind":"file","reference_id":"task:15c35de9-ca78-5493-b04a-397c7f1713cd:1:image_1.png","filename":"image_1.png","media_type":"image/png","alt":""}],"source_url":"https://mmmu-benchmark.github.io/","history":"initial import","indexing_mode":"noindex","subproblems":[],"grids":[]}