ResearchDatasetsVitaminCFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsComplex reasoningVitaminC (test)78.4Macro-F137Fact VerificationVitaminC54Accuracy (%)12global fact consistency verificationVitaminC0.984Precision10Fact VerificationVitaminC92.62Accuracy8Complex reasoningVitaminC (val)69.99Macro F1 Score4