ResearchDatasetsKID-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsKnowledge Conflict ResolutionKID-Bench v297.6Performance (Difficulty A)4Knowledge Conflict ResolutionKID-Bench Category C v278.1Accuracy (C-Light)3Knowledge CombinationKID-Bench Category B v268Accuracy3Novel Knowledge RecallKID-Bench Category A v297.1Accuracy3