ResearchDatasetsDateFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsHybrid ReasoningDate (test)84.5Accuracy24ReasoningDate85.75Accuracy on Date24Symbolic ReasoningDate90.5Solve Rate14Commonsense ReasoningDate (test)73.5Accuracy4