Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Mathematical Reasoning on WeMath 19
Loading...
61.52
Macro Average Score
Qwen3VL-8B-instruct + GeoSym Hard
59.2424
59.8337
60.425
61.0163
May 10, 2026
Macro Average Score
Angles & Length Accuracy
Plane Calculation Accuracy
Plane Understanding Accuracy
One-step Accuracy
Two-step Accuracy
Three-step Accuracy
Updated 15d ago
Evaluation Results
Method
Method
Links
Macro Average Score
Angles & Length Accuracy
Plane Calculation Accuracy
Plane Understanding Accuracy
One-step Accuracy
Two-step Accuracy
Three-step Accuracy
Qwen3VL-8B-instruct + GeoSym Hard
Base Model=Qwen3-VL, P...
2026.05
61.52
51.75
88.04
83.35
83.62
77.22
75.15
Qwen3VL-8B-instruct + GeoSym Entry
Base Model=Qwen3-VL, P...
2026.05
59.33
43.16
87.37
79.27
82.06
76.11
72.12
Feedback
Search any
task
Search any
task