Audio Classification on VGG-S
80.1Top-1 AccuracyOneEncoder
Evaluation Results
| Method | Links | |
|---|---|---|
| OneEncoder2026.05 | 80.1 | |
| Absolute SOTAAnchor Modality=–2026.04 | 52.5 | |
| AudioCLIPAnchor Modality=–2026.04 | 47.4 | |
| CLAPAnchor Modality=–2026.04 | 46.2 | |
| CodeBind-VL2026.05 | 39.5 | |
| LanguageBind2026.05 | 38.6 | |
| EmergentBridgeAnchor Modality=Image2026.04 | 36.3 | |
| CodeBind-IB2026.05 | 30.5 | |
| EmergentBridgeAnchor Modality=Text2026.04 | 29.3 | |
| LanguageBindAnchor Modality=Text2026.04 | 28.9 | |
| ImageBindAnchor Modality=Image2026.04 | 27.8 | |
| WAV2CLIPAnchor Modality=–2026.04 | 10 |