Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific QA on CharXiv
Loading...
95.2
CharXiv-D Score
GPT-5.2
49.128
61.089
73.05
85.011
Mar 12, 2026
CharXiv-D Score
CharXiv-R Score
Updated 4mo ago
Evaluation Results
Method
Method
Links
CharXiv-D Score
CharXiv-R Score
GPT-5.2
Model=GPT-5.2
2026.03
95.2
73.1
GPT-5.1
Model=GPT-5.1
2026.03
90.9
58.3
Qwen2.5-VL-7B + SCIMDR
Model=Qwen2.5-VL-7B, T...
2026.03
75.6
37.9
Qwen-3-VL-8B
Model=Qwen-3-VL-8B
2026.03
74.2
40.1
InternVL-3-8B
Model=InternVL-3-8B
2026.03
66.7
34.6
LLaVA-OV-1.5-8B
Model=LLaVA-OV-1.5-8B
2026.03
66.3
32.9
Qwen2.5-VL-7B
Model=Qwen2.5-VL-7B, T...
2026.03
65
37.7
Qwen2.5-VL-7B + SPIQA
Model=Qwen2.5-VL-7B, T...
2026.03
50.9
33.3
Feedback
Search any
task
Search any
task