Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Spoken-MQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Spoken Question AnsweringSpoken-MQA
Accuracy83.95
8
Streaming Voice-Agent Interaction EfficiencySpoken-MQA
NFE1.96
5
Showing 2 of 2 rows