ResearchTasksSpeech-to-Text Reply QualitySpeech-to-Text Reply QualityFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedVoiceBench AlpacaEvalGPT-4o-Audio4.78Quality Score6Jun 9, 2026