Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Document Visual Question Answering on DeepForm
Loading...
50.8
Accuracy
Visual-SR1
16.584
25.467
34.35
43.233
Sep 25, 2025
Accuracy
Updated 13d ago
Evaluation Results
Method
Method
Links
Accuracy
Visual-SR1
Backbone=Qwen2.5-VL-7B
2025.09
50.8
DeFacto
Backbone=Qwen2.5-VL-7B
2025.09
45.6
Qwen2.5-VL
Backbone=Qwen2.5-VL-7B
2025.09
27.9
ViCrop
Backbone=LLaVA-1.5 (Vi...
2025.09
20.3
GRIT
Backbone=Qwen2.5-VL-3B
2025.09
17.9
Feedback
Search any
task
Search any
task