ResearchTasksMulti-Modal Visual Question Answering (MMVQA)For AI assistantsMarkdownContent indexMulti-Modal Visual Question Answering (MMVQA)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRAD-ChestCT (val)Med3D-R144.99Accuracy57Feb 26, 2026CT-RATE (val)Med3D-R141.92Accuracy57Feb 26, 2026