Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Task on TextVQA (Accuracy Only)
Loading...
43.83
Accuracy
CoM-PT
43.05
43.2525
43.455
43.6575
Apr 14, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
CoM-PT
Backbone=ViT-L/16, PT...
2026.04
43.83
Baseline
Backbone=ViT-L/16, PT...
2026.04
43.64
CoM-PT
Backbone=ViT-B/16, PT...
2026.04
43.21
Baseline
Backbone=ViT-B/16, PT...
2026.04
43.08
Feedback
Search any
task
Search any
task