ResearchDatasetsCOMMON2SENSEFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsThree-way probability rankingCOMMON2SENSE paired76.2F1 (C1)30Binary decisionCOMMON2SENSE95.1Accuracy27Pairwise preference evaluationCommon2sense61Context 1 Preference Score21