Number Theory Problem Solving on number theory
92.59AccuracyCDS
Evaluation Results
| Method | Links | |
|---|---|---|
| CDSModel=gpt-5.2, Number of demonstrations=322026.05 | 92.59 | |
| CDSModel=gpt-5.2, Number of demonstrations=642026.05 | 92.04 | |
| CDSModel=gpt-5.2, Number of demonstrations=1242026.05 | 91.85 | |
| originModel=gpt-5.2, Number of demonstrations=1242026.05 | 91.48 | |
| CDSbgeModel=gpt-5.2, Number of demonstrations=322026.05 | 91.48 | |
| CDSbgeModel=gpt-5.2, Number of demonstrations=1242026.05 | 91.3 | |
| CDSbgeModel=Qwen3, Number of demonstrations=1242026.05 | 91.3 | |
| originModel=gpt-5.2, Number of demonstrations=322026.05 | 91.11 | |
| originModel=Qwen3, Number of demonstrations=1242026.05 | 90.93 | |
| CDSModel=Qwen3, Number of demonstrations=1242026.05 | 90.74 | |
| originModel=gpt-5.2, Number of demonstrations=162026.05 | 89.63 | |
| CDSModel=gpt-5.2, Number of demonstrations=162026.05 | 89.26 | |
| CDSbgeModel=gpt-5.2, Number of demonstrations=642026.05 | 88.7 | |
| originModel=gpt-5.2, Number of demonstrations=642026.05 | 88.56 | |
| CDSbgeModel=gpt-5.2, Number of demonstrations=162026.05 | 88.15 | |
| originModel=Qwen3, Number of demonstrations=322026.05 | 87.96 | |
| CDSModel=Qwen3, Number of demonstrations=322026.05 | 87.85 | |
| CDSModel=Qwen3, Number of demonstrations=642026.05 | 87.78 | |
| CDSbgeModel=Qwen3, Number of demonstrations=322026.05 | 87.78 | |
| CDSbgeModel=Qwen3, Number of demonstrations=642026.05 | 87.22 | |
| originModel=Qwen3, Number of demonstrations=162026.05 | 86.67 | |
| originModel=Qwen3, Number of demonstrations=642026.05 | 86.3 | |
| CDSModel=Qwen3, Number of demonstrations=162026.05 | 85.56 | |
| CDSbgeModel=Qwen3, Number of demonstrations=162026.05 | 85.37 |