Music Classification on VocalSound
93.59AccuracyQwen2-Audio + CoAT
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2-Audio + CoATBackbone=Qwen2-Audio, Method=CoAT2026.06 | 93.59 | |
| Audio Flamingo 3Backbone=Audio Flamingo 3, Method=Baseline2026.06 | 93.06 | |
| Audio Flamingo 3 + CoATBackbone=Audio Flamingo 3, Method=CoAT2026.06 | 92.39 | |
| Qwen2.5-Omni-7B + CoATBackbone=Qwen2.5-Omni-7B, Method=CoAT2026.06 | 91.7 | |
| Qwen2.5-Omni-7BBackbone=Qwen2.5-Omni-7B, Method=Baseline2026.06 | 91.36 | |
| Qwen2-AudioBackbone=Qwen2-Audio, Method=Baseline2026.06 | 88.1 |