Multi-turn Dialogue on SpokenWoz
52.09Joint Goal Accuracy (JGA)Gemini2.5-Flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini2.5-FlashModel Category=Proprietary Audio Language Models2025.09 | 52.09 | |
| Qwen2.5-Omni-7BModel Category=Medium Sized Large Audio Language Models, Parameter Count=5B-20B parameters2025.09 | 37.3 | |
| Kimi-AudioModel Category=Medium Sized Large Audio Language Models, Parameter Count=5B-20B parameters2025.09 | 37.3 | |
| Qwen2.5-Omni-3BModel Category=Small-sized Audio Language Models, Parameter Count=<5B parameters2025.09 | 31.3 | |
| Voxtral-Small-24BModel Category=Large Sized Large Audio Language Models, Parameter Count=>20B parameters2025.09 | 29.93 | |
| GPT-4o-mini-audioModel Category=Proprietary Audio Language Models2025.09 | 28.39 | |
| Voxtral-Mini-3BModel Category=Small-sized Audio Language Models, Parameter Count=<5B parameters2025.09 | 24.92 | |
| GPT-4o-transcribe + GPT-4.1-miniModel Category=Cascaded Systems2025.09 | 19.44 | |
| Whisper-Large-v3 + GPT-oSS-20BModel Category=Cascaded Systems2025.09 | 19.02 | |
| Qwen3-Omni-30B-A3B-ThinkingModel Category=Large Sized Large Audio Language Models, Parameter Count=>20B parameters2025.09 | 11.16 | |
| Phi-4-Multi-modalModel Category=Medium Sized Large Audio Language Models, Parameter Count=5B-20B parameters2025.09 | 7.82 |