Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on MathVista GPS (N=208)
Loading...
97.6
Top-1 Accuracy
Draw2Think CT
52.568
64.259
75.95
87.641
May 20, 2026
Top-1 Accuracy
Updated 13d ago
Evaluation Results
Method
Method
Links
Top-1 Accuracy
Draw2Think CT
Backbone=gemini-3-flas...
2026.05
97.6
Draw2Think BL
Backbone=gemini-3-flas...
2026.05
97.1
MathCanvas
Backbone=bagel-7b, Pro...
2026.05
79.3
GeoGen-SFT
Backbone=qwen2.5-vl-7b...
2026.05
74
SocraticGeo
Backbone=qwen2.5-vl-7b...
2026.05
63.6
Qwen2.5-VL-7B
Protocol=Zero-shot
2026.05
54.3
Feedback
Search any
task
Search any
task