ResearchDatasetsAIR-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsOpen-Ended Audio UnderstandingAIR-Bench chat6.8AIR-Bench Chat Score3General Safety / Red-TeamingAIR-Bench—Primary metric0Page 2 of 2PreviousNext