Audio-Visual QA on AVUT
66.57AccuracyQwen2.5-Omni7B + OutRo
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-Omni7B + OutRoBase Model=Qwen2.5-Omni7B, OutRo=true2026.03 | 66.57 | |
| Qwen2.5-Omni7BBase Model=Qwen2.5-Omni7B, OutRo=false2026.03 | 65.79 | |
| Qwen2.5-Omni3B + OutRoBase Model=Qwen2.5-Omni3B, OutRo=true2026.03 | 62.87 | |
| Qwen2.5-Omni3BBase Model=Qwen2.5-Omni3B, OutRo=false2026.03 | 61.79 | |
| video-SALMONN2+3B + OutRoBase Model=video-SALMONN2+3B, OutRo=true2026.03 | 57.31 | |
| video-SALMONN2+3BBase Model=video-SALMONN2+3B, OutRo=false2026.03 | 56.73 |