ResearchDatasetsAll TasksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Language UnderstandingAll tasks (25 tasks) (val)85.93Overall Accuracy13RetrievalAll tasks Pooled35.5nDCG@104Tool SelectionAll Tasks82Tools Correct4