List your company

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

67.17AccuracyVTAgent
13.360427.330241.355.2698May 6, 2026

Evaluation results

MethodLinks
VTAgentYear=-2026.0567.1775.18
Qwen3-VL-8BYear=20252026.0557.9666.43
SFAYear=20252026.0557.0565.44
Qwen2.5-VL-7BYear=20252026.0556.1164.77
Qwen3-VL-8B-ThinkingYear=20252026.0553.5762.73
InternVideo2.5-8BYear=20252026.054048.79
GAT-LargeYear=20252026.0538.348.23
NVILAYear=20252026.0537.7347.23
GAT-BaseYear=20252026.0535.5645.21
Qwen2-VL-7BYear=20242026.0535.2245.84
TEA-LargeYear=20252026.0534.7843.71
TEA-BaseYear=20252026.0531.740.24
ToMYear=20262026.0526.8735.4
T5-ViteVQAYear=20222026.0522.1729.1
VideoLLaMA2Year=20242026.0520.7623.55
Video-LLaVAYear=20242026.0515.4317.15