Audio-Visual Understanding on AVUT AV-Human
0.7834AccuracyGemini 1.5 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 1.5 ProModality=Audio-visual MLLMs2026.05 | 0.7834 | |
| Qwen2-VL-7BModality=Visual MLLMs2026.05 | 0.5838 | |
| GPT-4oModality=Visual MLLMs2026.05 | 0.5662 | |
| LLaVA-Video-7BModality=Visual MLLMs2026.05 | 0.5652 | |
| V-LynX-0.5BModality=Audio-visual MLLMs2026.05 | 0.4691 | |
| InternVL2-8BModality=Visual MLLMs2026.05 | 0.459 | |
| VideoLLaMA2-7BModality=Audio-visual MLLMs2026.05 | 0.449 | |
| VILA-1.5-8BModality=Visual MLLMs2026.05 | 0.4448 | |
| video-SALMONN-13BModality=Audio-visual MLLMs2026.05 | 0.3833 | |
| SALMONN-13BModality=Audio MLLMs2026.05 | 0.3648 | |
| VideoLLaVA-7BModality=Visual MLLMs2026.05 | 0.3314 | |
| PandaGPT-13BModality=Audio-visual MLLMs2026.05 | 0.2538 |