List your company

Video Text Visual Question Answering on M4-ViteVQA Task2 (val)

80.45AccuracyVTAgent
8.107626.888845.6764.4512May 6, 2026

Evaluation results

MethodLinks
VTAgentYear=-2026.0580.4584.86
SFAYear=20252026.0570.3476.6
Qwen3-VL-8BYear=20252026.0569.8275.26
Qwen3-VL-8B-ThinkingYear=20252026.0569.1675.79
Qwen2.5-VL-7BYear=20252026.0566.473.28
InternVideo2.5-8BYear=20252026.0548.0357.98
GAT-LargeYear=20252026.0524.5433.3
NVILAYear=20252026.0523.7932.89
Qwen2-VL-7BYear=20242026.0522.9532.65
TEA-LargeYear=20252026.0522.8330.21
GAT-BaseYear=20252026.0521.6530.88
ToMYear=20262026.0521.5325.2
TEA-BaseYear=20252026.0520.7328.18
VideoLLaMA2Year=20242026.0519.6823.62
T5-ViteVQAYear=20222026.0512.316.1
Video-LLaVAYear=20242026.0510.8913.23