Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Advanced Mathematical Problem Solving on Olympiad Bench (N=112)
Loading...
89.3
Top-1 Accuracy
Draw2Think BL
10.364
30.857
51.35
71.843
May 20, 2026
Top-1 Accuracy
Updated 13d ago
Evaluation Results
Method
Method
Links
Top-1 Accuracy
Draw2Think BL
Backbone=gemini-3-flas...
2026.05
89.3
Draw2Think CT
Backbone=gemini-3-flas...
2026.05
89.3
OpenAI-o3
Protocol=Zero-shot, Re...
2026.05
77.7
Gemini-2.5-Pro
Protocol=Zero-shot, Re...
2026.05
75
GPT-4o
Protocol=Zero-shot, Re...
2026.05
13.4
Feedback
Search any
task
Search any
task