Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
OCR-based Visual Question Answering on DocVQA 2021 (val)
Loading...
93.7
Accuracy
Qwen2-VL
84.652
87.001
89.35
91.699
Jan 10, 2025
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2-VL
2025.01
93.7
DeepSeekVL-2-Small
2025.01
92.3
SAIL-VL-8B
2025.01
92.2
InternVL2.5-MPO
2025.01
92.1
InternVL2.5
2025.01
91.8
InternVL2
2025.01
90.8
SAIL-VL
2025.01
89.2
Qwen2-VL
2025.01
88.7
DeepSeekVL-2-Tiny
2025.01
88.6
InternVL2.5-MPO
Training Strategy=MPO
2025.01
87.8
InternVL2.5
2025.01
87.4
InternVL2
2025.01
86
Aquila
2025.01
85
Feedback
Search any
task
Search any
task