ResearchDatasetsCommonEvalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAudio Question-AnsweringCommonEval91Score12Instruction FollowingCommonEval (ComE)4.08GPT-score9Audio-language generationCommonEval VoiceBench2.94Score2