SAT Reasoning on SATURN 2.6k Difficulty 3,5,5 (test)
70.3Pass@1SATURN-1.5B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| SATURN-1.5BIteration=22025.05 | 70.3 | 95.9 | 99 | 99.7 | 99.9 | |
| SATURN-1.5BIteration=12025.05 | 59.7 | 90.4 | 97.1 | 99.1 | 99.8 | |
| DeepSeek-R1-Distill-Qwen-1.5B2025.05 | 36.7 | 71.7 | 85.4 | 91.7 | 96.2 |