ResearchDatasetsAI2D, POPE, TextVQA, OKVQA, VizWiz, COCO Caption, NoCaps, and RealWorldQAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMultimodal UnderstandingAI2D, POPE, TextVQA, OKVQA, VizWiz, COCO Caption, NoCaps, and RealWorldQA Average99.86Average Score15
Multimodal UnderstandingAI2D, POPE, TextVQA, OKVQA, VizWiz, COCO Caption, NoCaps, and RealWorldQA Average99.86Average Score15