List your company

Audio-Visual Understanding on AVUT AV-Human

0.7834AccuracyGemini 1.5 Pro
0.2326160.3756080.51860.661592May 30, 2026

Evaluation results

MethodLinks
Gemini 1.5 ProModality=Audio-visual MLLMs2026.050.7834
Qwen2-VL-7BModality=Visual MLLMs2026.050.5838
GPT-4oModality=Visual MLLMs2026.050.5662
LLaVA-Video-7BModality=Visual MLLMs2026.050.5652
V-LynX-0.5BModality=Audio-visual MLLMs2026.050.4691
InternVL2-8BModality=Visual MLLMs2026.050.459
VideoLLaMA2-7BModality=Audio-visual MLLMs2026.050.449
VILA-1.5-8BModality=Visual MLLMs2026.050.4448
video-SALMONN-13BModality=Audio-visual MLLMs2026.050.3833
SALMONN-13BModality=Audio MLLMs2026.050.3648
VideoLLaVA-7BModality=Visual MLLMs2026.050.3314
PandaGPT-13BModality=Audio-visual MLLMs2026.050.2538