ResearchDatasetsMM-StarFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMultimodal Capability EvaluationMM-Star60.6Average Score36Comprehensive reasoningMM-Star62Accuracy18Complex Multimodal ReasoningMM-Star55.44Reasoning Score10Visual reasoningMM-Star (test)69.1Accuracy9