Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Document Reasoning on CharXiv
Loading...
83
DQ
Qwen3-VL
63.656
68.678
73.7
78.722
Mar 6, 2026
DQ
RQ
Updated 1mo ago
Evaluation Results
Method
Method
Links
DQ
RQ
Qwen3-VL
Model Size=8B
2026.03
83
46.4
Penguin-VL
Model Size=8B
2026.03
75.7
40
InternVL-3.5
Model Size=8B
2026.03
72.2
44.4
OpenAI GPT-5 nano
Model Size=nano
2026.03
64.4
31.7
Feedback
Search any
task
Search any
task