Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Document Understanding on CharXiv (Reasoning Questions)
Loading...
54.1
Score
Metis
36.94
41.395
45.85
50.305
Apr 9, 2026
Score
Updated 8d ago
Evaluation Results
Method
Method
Links
Score
Metis
Backbone=Qwen3-VL-8B-I...
2026.04
54.1
DeepEyesV2
Model Category=Agentic...
2026.04
48.9
Qwen2.5-VL-32B-Instruct
Model Category=Open-So...
2026.04
48
Qwen3-VL-8B-Instruct
Model Category=Open-So...
2026.04
46.3
Qwen2.5-VL-7B-Instruct
Model Category=Open-So...
2026.04
40.2
InternVL3-8B
Model Category=Open-So...
2026.04
37.6
Feedback
Search any
task
Search any
task