Mathematical Reasoning on MATH 500 (Reasoning Performance)
93.4Reasoning PerformanceImproved CoT
Evaluation Results
| Method | Links | |
|---|---|---|
| Improved CoTModel Series=32B Models, Safety Training Data=10002025.05 | 93.4 | |
| RealSafe-R1-7BModel Series=7B Models, Safety Training Data=150002025.05 | 92 | |
| RealSafe-R1-32BModel Series=32B Models, Safety Training Data=150002025.05 | 91.6 | |
| STAR1-R1-Distill-7BModel Series=7B Models, Safety Training Data=10002025.05 | 90.4 | |
| Improved CoTModel Series=7B Models, Safety Training Data=10002025.05 | 90.2 | |
| STAR1-R1-Distill-32BModel Series=32B Models, Safety Training Data=10002025.05 | 89.4 |