ResearchDatasetsUltraEval-AudioUltraEval-AudioFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsSpoken Question AnsweringUltraEval-Audio WebQ55.95S2T Score (Task Correctness)9Spoken Question AnsweringUltraEval-Audio LLaMA-QA83S2T Score9Spoken Question AnsweringUltraEval-Audio S2S0.734AlpacaEval Score9