Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Geometry Problem Solving on PyGeoX (Hard)
Loading...
51
Accuracy
Proprietary-C
23.96
30.98
38
45.02
Jun 8, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Proprietary-C
Inference=reasoning, E...
2026.06
51
Qwen3-8B-RL
Inference=RL-trained,...
2026.06
41
Proprietary-B
Inference=reasoning, E...
2026.06
38
Proprietary-A
Inference=default, Eva...
2026.06
37
DeepSeek-V3.2
Inference=default, Eva...
2026.06
25
Feedback
Search any
task
Search any
task