Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Multimodal Document Reasoning on SCIMDR-Eval
Loading...
49.9
Accuracy
GPT-5.2
18.596
26.723
34.85
42.977
Mar 12, 2026
Accuracy
Updated 4mo ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-5.2
2026.03
49.9
Qwen2.5-VL-7B + SCIMDR
Fine-tuned=true, Train...
2026.03
49.1
GPT-5.1
2026.03
47.2
GPT-4o
2026.03
24.7
Qwen2.5-VL-7B
2026.03
19.8
Feedback
Search any
task
Search any
task