Audio Visual Question Answering on Music-AVQA (Robustness Evaluation)
85.15Music-AVQA Clean AccuracyQwen3-Omni-30B
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Qwen3-Omni-30BModel=Qwen3-Omni-30B2026.04 | 85.15 | 83.23 | — | 9.58 | 15.16 | |
| Qwen2.5-Omni-7BModel=Qwen2.5-Omni-7B2026.04 | 82.99 | 80.91 | — | 18.83 | 18.6 | |
| Gemini-3.1-Flash-Lite-previewModel=Gemini-3.1-Flash-Lite-preview2026.04 | 81.32 | 80.01 | — | 10.54 | 16.12 | |
| Negative Language Modeling LossObjective=L_negLM2026.01 | 80.7 | 74.3 | 6.4 | — | — | |
| Encoder-Based Cosine Similarity LossObjective=L^(cos)2026.01 | 80.7 | 74.7 | 6 | — | — | |
| Vision Attention Suppression LossObjective=L^(visionatt)2026.01 | 80.7 | 77.7 | 3 | — | — | |
| Audio Attention Amplification LossObjective=L^(audioatt)2026.01 | 80.7 | 76.9 | 3.8 | — | — | |
| Attention Randomization LossObjective=L^(randatt)2026.01 | 80.7 | 75.8 | 4.9 | — | — | |
| Hidden-State Similarity LossObjective=L^(hidden-cos)2026.01 | 80.7 | 76.6 | 4.1 | — | — | |
| Combined Loss (SOUNDBREAK)Objective=L^(combined)2026.01 | 80.7 | 75 | 5.7 | — | — | |
| Gemini-2.5-Flash-LiteModel=Gemini-2.5-Flash-Lite2026.04 | 80.68 | 75.4 | — | 11.75 | 19.68 | |
| Gemini-3.1-Flash-Lite-previewModel=Gemini-3.1-Flash-Lite-preview2026.04 | 71.97 | 70.62 | — | 2.14 | 6.84 | |
| Gemini-2.5-Flash-LiteModel=Gemini-2.5-Flash-Lite2026.04 | 68.99 | 67.24 | — | 2.01 | 4.52 | |
| Qwen2.5-Omni-7BModel=Qwen2.5-Omni-7B2026.04 | 66.94 | 56.18 | — | 4.34 | 15.51 | |
| PandaGPTModel=PandaGPT2026.04 | 64.41 | 64.46 | — | 26.73 | 26.96 | |
| Gemini-3.1-Flash-Lite-previewModel=Gemini-3.1-Flash-Lite-preview2026.04 | 62.63 | 49.96 | — | 16.83 | 34.21 | |
| Qwen3-Omni-30BModel=Qwen3-Omni-30B2026.04 | 61.54 | 55.09 | — | 2.15 | 8.11 | |
| Gemini-2.5-Flash-LiteModel=Gemini-2.5-Flash-Lite2026.04 | 60.15 | 47.49 | — | 17.99 | 33.26 | |
| Qwen2.5-Omni-7BModel=Qwen2.5-Omni-7B2026.04 | 57.01 | 43.76 | — | 22.2 | 38.62 | |
| Qwen3-Omni-30BModel=Qwen3-Omni-30B2026.04 | 56.57 | 53.96 | — | 18.48 | 33.33 | |
| ChatBridgeModel=ChatBridge2026.04 | 51.38 | 50 | — | 27.47 | 30.09 | |
| ChatBridgeModel=ChatBridge2026.04 | 39.99 | 34.38 | — | 15.83 | 25.55 | |
| ChatBridgeModel=ChatBridge2026.04 | 37.64 | 35.21 | — | 23.68 | 24.53 | |
| PandaGPTModel=PandaGPT2026.04 | 35.98 | 35.93 | — | 10.04 | 10.98 | |
| PandaGPTModel=PandaGPT2026.04 | 34.93 | 34.93 | — | 29.02 | 29.12 |