ResearchDatasetsUNLIFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsIntrinsic ReasoningUNLI0.813Spearman Correlation9Scalar probability judgmentUNLI0.057MSE9UMUI Judgment CalibrationUNLI (full)0.057MSE9