DocVQA
Document Visual Question Answering - understanding text in document images. (val split)
Category
Multimodal
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for DocVQA
| Model | Score | Date | Verified |
|---|---|---|---|
| Gemma 3 4B PT |
72.80
|
27.02.2025 | Verified |
| Gemma 3 12B PT |
74.22%
|
27.02.2025 | Verified |
| Gemma 3 27B PT |
100.00%
|
27.02.2025 | Verified |