Audio Understanding on ClothoAQA
87.17AccuracyQwen2.5-Omni-7B + CoAT
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-Omni-7B + CoATBackbone=Qwen2.5-Omni-7B, Method=CoAT2026.06 | 87.17 | |
| Audio Flamingo 3 + CoATBackbone=Audio Flamingo 3, Method=CoAT2026.06 | 85.3 | |
| Qwen2.5-Omni-7BBackbone=Qwen2.5-Omni-7B, Method=Baseline2026.06 | 84.67 | |
| Audio Flamingo 3Backbone=Audio Flamingo 3, Method=Baseline2026.06 | 80.1 | |
| Qwen2-Audio + CoATBackbone=Qwen2-Audio, Method=CoAT2026.06 | 79.96 | |
| Qwen2-AudioBackbone=Qwen2-Audio, Method=Baseline2026.06 | 75.52 | |
| Qwen3-Omni-Instruct2026.02 | 75.16 | |
| Qwen3-Omni-A3B-InstructVariant=Omni-A3B-Instruct2026.03 | 75.16 | |
| Gemini-3-Pro2026.02 | 74.41 | |
| ERNIE 5.02026.02 | 73.68 | |
| LongCat-Next2026.03 | 73.45 | |
| LongCat-Flash-Omni2026.02 | 72.83 | |
| Kimi Audio2026.02 | 72.21 | |
| Kimi-Audio2026.03 | 72.21 | |
| MiMo-Audio2026.03 | 68.85 | |
| Step-Audio-2-miniVersion=2-mini2026.03 | 68.39 | |
| ERNIE 5.0-Base2026.02 | 65.7 | |
| Gemini-2.5-Flash-Lite-previewVersion=2.5, Tier=Flash-Lite-preview2026.03 | 63.27 | |
| GPT-4o-Audio2026.02 | 61.87 | |
| Gemini-3.1-Flash-Lite-previewVersion=3.1, Tier=Flash-Lite-preview2026.03 | 60.53 |