Audio-Visual Question Answering on Daily-Omni 1 FPS
70.9Metric 30StreamOV
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| StreamOVAudio=true2026.05 | 70.9 | 67.3 | 65.6 | 71 | 64.3 | 62.8 | 81.2 | 79.4 | 69.3 | |
| Qwen3-Omni-30BAudio=true2026.05 | 70 | 65.3 | 63.5 | 71 | 62.7 | 61.1 | 80.5 | 77.7 | 67.8 | |
| Gemini 2.5 FlashAudio=true2026.05 | 69.9 | 77.1 | 73.8 | 66.4 | 72 | 68 | 78.7 | 81.9 | 73.1 | |
| Gemini 2.0 FlashAudio=true2026.05 | 67.2 | 68.6 | 62.2 | 73.3 | 63.7 | 63.7 | 76.6 | 75.4 | 67.8 | |
| Qwen3-VL-30BAudio=false2026.05 | 57.3 | 57.3 | 47.5 | 68.7 | 52.3 | 55.9 | 67.5 | 61.1 | 57.3 | |
| GPT-4oAudio=false2026.05 | 55.6 | 57.5 | 47.9 | 62.6 | 52.3 | 52.6 | 66.2 | 66.3 | 56.5 | |
| Qwen2.5-Omni-7BAudio=true2026.05 | 48.7 | 51.1 | 34.5 | 58.8 | 47.7 | 49.7 | 63 | 54.9 | 49.8 | |
| Qwen2.5-VL-7BAudio=false2026.05 | 39.3 | 42.4 | 37 | 46.6 | 33.7 | 37.9 | 52 | 44 | 40.7 |