VoiceBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| General Audio Understanding | VoiceBench | AlpacaEval Score4.78 | 16 | |
| Speech-to-Text | VoiceBench | AlpacaEval Score4.78 | 15 | |
| Speech-to-text reasoning and semantic understanding | VoiceBench (test) | Alpaca Eval4.8 | 13 | |
| Reasoning | VoiceBench | MMSU Accuracy (Audio)72.9 | 13 | |
| Speech-to-Text Spoken Question Answering | VoiceBench S2T (test) | AlpacaEval4.8 | 7 | |
| Voice Chatting | VoiceBench | AlpacaEval4.94 | 7 | |
| Spoken Question Answering | VoiceBench S2T | AlpacaEval4.94 | 4 |
Showing 7 of 7 rows