Geometry Proof Generation on geometry
81.21AccuracyCDS
Evaluation Results
| Method | Links | |
|---|---|---|
| CDSModel=gpt-5.2, Number of demonstrations=162026.05 | 81.21 | |
| CDSModel=gpt-5.2, Number of demonstrations=642026.05 | 80.79 | |
| CDSbgeModel=gpt-5.2, Number of demonstrations=162026.05 | 80.37 | |
| CDSbgeModel=gpt-5.2, Number of demonstrations=322026.05 | 78.29 | |
| CDSModel=gpt-5.2, Number of demonstrations=322026.05 | 78.08 | |
| CDSbgeModel=gpt-5.2, Number of demonstrations=642026.05 | 76.83 | |
| originModel=gpt-5.2, Number of demonstrations=162026.05 | 75.99 | |
| CDSModel=gpt-5.2, Number of demonstrations=1242026.05 | 75.99 | |
| originModel=gpt-5.2, Number of demonstrations=1242026.05 | 75.78 | |
| originModel=gpt-5.2, Number of demonstrations=642026.05 | 75.37 | |
| CDSbgeModel=gpt-5.2, Number of demonstrations=1242026.05 | 75.11 | |
| originModel=gpt-5.2, Number of demonstrations=322026.05 | 74.74 | |
| CDSbgeModel=Qwen3, Number of demonstrations=1242026.05 | 74.32 | |
| CDSModel=Qwen3, Number of demonstrations=1242026.05 | 73.9 | |
| originModel=Qwen3, Number of demonstrations=1242026.05 | 73.07 | |
| CDSbgeModel=Qwen3, Number of demonstrations=642026.05 | 70.36 | |
| CDSModel=Qwen3, Number of demonstrations=642026.05 | 68.89 | |
| CDSModel=Qwen3, Number of demonstrations=322026.05 | 68.27 | |
| CDSbgeModel=Qwen3, Number of demonstrations=322026.05 | 67.85 | |
| CDSbgeModel=Qwen3, Number of demonstrations=162026.05 | 66.6 | |
| originModel=Qwen3, Number of demonstrations=162026.05 | 66.18 | |
| originModel=Qwen3, Number of demonstrations=322026.05 | 65.76 | |
| CDSModel=Qwen3, Number of demonstrations=162026.05 | 65.55 | |
| originModel=Qwen3, Number of demonstrations=642026.05 | 65.14 |