ResearchDatasetsOpenHandsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsFailure predictionOpenHands Transfer (held-out)69.5ROC-AUC4Failure predictionOpenHands (Within corpus)69.7ROC-AUC4Leave-one-corpus-out transferOpenHands0.699AUC3