ResearchDatasetsVLMEvalKitFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMultimodal Visual Question AnsweringVLMEvalKit Image Benchmarks46.8HallBench Accuracy13Reasoning and MathVLMEvalKit (test)73.4MathVista Accuracy13