List your company

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

65.91AccuracyVTAgent
9.001223.775638.5553.3244May 6, 2026

Evaluation results

MethodLinks
VTAgentYear=-2026.0565.9174.46
Qwen3-VL-8BYear=20252026.0555.3564.53
SFAYear=20252026.0555.0264.63
Qwen2.5-VL-7BYear=20252026.0550.9361.14
Qwen3-VL-8B-ThinkingYear=20252026.0550.560.84
InternVideo2.5-8BYear=20252026.0538.9949.36
GAT-LargeYear=20252026.0530.941.81
NVILAYear=20252026.0530.141.52
GAT-BaseYear=20252026.0529.7740.71
TEA-LargeYear=20252026.0528.4338.13
Qwen2-VL-7BYear=20242026.0527.2538.45
TEA-BaseYear=20252026.0526.2936
ToMYear=20262026.0520.3327.5
VideoLLaMA2Year=20242026.0518.3320.45
T5-ViteVQAYear=20222026.0516.6823.8
Video-LLaVAYear=20242026.0511.1912.02