ResearchDatasetsEMMAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMulti-modal ReasoningEMMA38.5Accuracy61Complex Scene ReasoningEMMA mini25.25Score17General Multimodal ReasoningEMMA full45.7Accuracy14Multi-discipline reasoningEMMA core24.6Accuracy8STEMEMMA72Pass@17Math ReasoningEMMA29.93Accuracy@15