List your company

Video Text Visual Question Answering on M4-ViteVQA Task1Split2 1.0 (val)

70.43AccuracyVTAgent
10.848426.316741.78557.2533May 6, 2026

Evaluation results

MethodLinks
VTAgentYear=-2026.0570.4378.29
Qwen3-VL-8BYear=20252026.0558.768.05
SFAYear=20252026.0557.5366.21
Qwen2.5-VL-7BYear=20252026.0554.6963.47
Qwen3-VL-8B-ThinkingYear=20252026.0552.9663.63
InternVideo2.5-8BYear=20252026.0541.652.49
GAT-LargeYear=20252026.0531.3541.33
NVILAYear=20252026.0530.2540.58
GAT-BaseYear=20252026.0529.0739.26
Qwen2-VL-7BYear=20242026.0528.5539.34
TEA-LargeYear=20252026.0528.2736.32
TEA-BaseYear=20252026.0526.6636.61
ToMYear=20262026.0521.2428.71
VideoLLaMA2Year=20242026.0518.319.63
T5-ViteVQAYear=20222026.0517.5923.1
Video-LLaVAYear=20242026.0513.1414.29