ResearchTasksOOD Generalization TrackingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTruthfulness datasetsMahalanobis Cosine Similarity0.994R^2 (MCS)6Jun 19, 2026General NLP benchmarksMahalanobis Cosine Similarity0.936R^2 (MCS)1Jun 19, 2026Gender classification datasetsMahalanobis Cosine Similarity0.976R^2 (MCS)1Jun 19, 2026