List your company

Geometry Proof Generation on geometry

81.21AccuracyCDS
64.497268.836173.17577.5139May 13, 2026

Evaluation results

MethodLinks
CDSModel=gpt-5.2, Number of demonstrations=162026.0581.21
CDSModel=gpt-5.2, Number of demonstrations=642026.0580.79
CDSbgeModel=gpt-5.2, Number of demonstrations=162026.0580.37
CDSbgeModel=gpt-5.2, Number of demonstrations=322026.0578.29
CDSModel=gpt-5.2, Number of demonstrations=322026.0578.08
CDSbgeModel=gpt-5.2, Number of demonstrations=642026.0576.83
originModel=gpt-5.2, Number of demonstrations=162026.0575.99
CDSModel=gpt-5.2, Number of demonstrations=1242026.0575.99
originModel=gpt-5.2, Number of demonstrations=1242026.0575.78
originModel=gpt-5.2, Number of demonstrations=642026.0575.37
CDSbgeModel=gpt-5.2, Number of demonstrations=1242026.0575.11
originModel=gpt-5.2, Number of demonstrations=322026.0574.74
CDSbgeModel=Qwen3, Number of demonstrations=1242026.0574.32
CDSModel=Qwen3, Number of demonstrations=1242026.0573.9
originModel=Qwen3, Number of demonstrations=1242026.0573.07
CDSbgeModel=Qwen3, Number of demonstrations=642026.0570.36
CDSModel=Qwen3, Number of demonstrations=642026.0568.89
CDSModel=Qwen3, Number of demonstrations=322026.0568.27
CDSbgeModel=Qwen3, Number of demonstrations=322026.0567.85
CDSbgeModel=Qwen3, Number of demonstrations=162026.0566.6
originModel=Qwen3, Number of demonstrations=162026.0566.18
originModel=Qwen3, Number of demonstrations=322026.0565.76
CDSModel=Qwen3, Number of demonstrations=162026.0565.55
originModel=Qwen3, Number of demonstrations=642026.0565.14