Audio Question Answering on AudioSet En
44.87Audio QA ScoreGLM-4-Voice
Evaluation Results
| Method | Links | |
|---|---|---|
| GLM-4-VoiceSize=9B2025.09 | 44.87 | |
| VITA-AudioSize=7B2025.09 | 40.2 | |
| LLaMA-OmniSize=8B2025.09 | 39.59 | |
| Pretrain+TtTSize=3B2025.09 | 26.73 | |
| MoshiSize=7B2025.09 | 25.63 | |
| Kimi-AudioSize=7B2025.09 | 19.49 | |
| SLAM-OmniSize=0.5B2025.09 | 17.47 | |
| TtTSize=3B2025.09 | 17.46 | |
| Mini-OmniSize=0.5B2025.09 | 15.73 | |
| Qwen2.5-3B (AR)Size=3B2025.09 | 14.42 | |
| Qwen2.5-3B (NAR)Size=3B2025.09 | 11.31 | |
| SpeechGPTSize=7B2025.09 | 10 |