Audio Understanding & Reasoning on ABF Speech
75.99AccuracyQwen2.5-Omni-7B + CoAT
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-Omni-7B + CoATBackbone=Qwen2.5-Omni-7B, Method=CoAT2026.06 | 75.99 | |
| Audio Flamingo 3 + CoATBackbone=Audio Flamingo 3, Method=CoAT2026.06 | 71.24 | |
| Qwen2-Audio + CoATBackbone=Qwen2-Audio, Method=CoAT2026.06 | 70.98 | |
| Qwen2.5-Omni-7BBackbone=Qwen2.5-Omni-7B, Method=Baseline2026.06 | 67.33 | |
| Audio Flamingo 3Backbone=Audio Flamingo 3, Method=Baseline2026.06 | 62.99 | |
| Qwen2-AudioBackbone=Qwen2-Audio, Method=Baseline2026.06 | 50.16 |