Audio Understanding on VocalSound
94.85AccuracyKimi-Audio
Evaluation Results
| Method | Links | |
|---|---|---|
| Kimi-Audio2026.03 | 94.85 | |
| Qwen3-Omni-A3B-InstructVariant=Omni-A3B-Instruct2026.03 | 91.59 | |
| MiMo-Audio2026.03 | 87.94 | |
| Step-Audio-2-miniVersion=2-mini2026.03 | 87.58 | |
| LongCat-Next2026.03 | 85.91 | |
| Gemini-3.1-Flash-Lite-previewVersion=3.1, Tier=Flash-Lite-preview2026.03 | 69.81 | |
| Gemini-2.5-Flash-Lite-previewVersion=2.5, Tier=Flash-Lite-preview2026.03 | 57.67 |