List your company

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

0.769AccuracyVTAgent
0.0658560.2484030.430950.613497May 6, 2026

Evaluation results

MethodLinks
VTAgentYear=-2026.050.7690.8272
Qwen3-VL-8BYear=20252026.050.6650.7318
Qwen3-VL-8B-ThinkingYear=20252026.050.64620.7202
SFAYear=20252026.050.64460.7172
Qwen2.5-VL-7BYear=20252026.050.62980.71
InternVideo2.5-8BYear=20252026.050.41360.5121
NVILAYear=20252026.050.22890.3034
GAT-LargeYear=20252026.050.22130.3075
GAT-BaseYear=20252026.050.21650.2983
Qwen2-VL-7BYear=20242026.050.21230.2879
TEA-LargeYear=20252026.050.18830.2899
TEA-BaseYear=20252026.050.17280.2603
ToMYear=20262026.050.1670.224
VideoLLaMA2Year=20242026.050.16540.218
Video-LLaVAYear=20242026.050.09380.118
T5-ViteVQAYear=20222026.050.09290.136