ResearchDatasetsSFEFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsScientific Multimodal ReasoningSFE44.06Accuracy10Scientific ReasoningSFE ZH Chinese35.69Score9Scientific ReasoningSFE English36.49Score9STEMSFE61.9Pass@17Scientific ReasoningSFE44.06Accuracy7Scientific Multimodal TasksSFE58.9Score5