Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Reasoning on AI2D (Accuracy)
Loading...
62.53
Accuracy
ESC
50.778
53.829
56.88
59.931
Jul 1, 2026
Accuracy
Updated 23d ago
Evaluation Results
Method
Method
Links
Accuracy
ESC
Model=Qwen2 [92]
2026.07
62.53
Baseline
Model=Qwen2 [92]
2026.07
60.98
ESC
Model=LLaVA [50]
2026.07
53.72
Baseline
Model=LLaVA [50]
2026.07
51.23
Feedback
Search any
task
Search any
task
