Mathematical Reasoning on CMIMC (Pass@1)
23.75Pass@1e3-1.7B + RL
Evaluation Results
| Method | Links | |
|---|---|---|
| e3-1.7B + RLRL Data Size=1216, Evaluation Protocol=8 rollouts avg.2026.01 | 23.75 | |
| e3-1.7B + InT+ RLRL Data Size=64, Evaluation Protocol=8 rollouts avg.2026.01 | 21.88 | |
| e3-1.7B + Distill + RLRL Data Size=1216, Evaluation Protocol=8 rollouts avg.2026.01 | 21.56 |