List your company

Video Text Visual Question Answering on M4-ViteVQA Task1Split1 1.0 (val)

71.59AccuracyVTAgent
13.589228.647143.70558.7629May 6, 2026

Evaluation results

MethodLinks
VTAgentYear=-2026.0571.5978.69
Qwen3-VL-8BYear=20252026.0561.9570.21
SFAYear=20252026.0560.9868.62
Qwen2.5-VL-7BYear=20252026.0558.3567.08
Qwen3-VL-8B-ThinkingYear=20252026.0556.8765.99
InternVideo2.5-8BYear=20252026.0539.8348.55
GAT-LargeYear=20252026.0538.0147.53
NVILAYear=20252026.0537.8947.67
TEA-LargeYear=20252026.0537.4946.38
Qwen2-VL-7BYear=20242026.0536.7746.56
GAT-BaseYear=20252026.0535.3144.64
TEA-BaseYear=20252026.0534.4542.91
ToMYear=20262026.0527.1235.5
T5-ViteVQAYear=20222026.0523.1730.1
VideoLLaMA2Year=20242026.0520.0421.73
Video-LLaVAYear=20242026.0515.8217.77