Mathematical Reasoning on D-Hard (test)
23.56Pass@8e3-1.7B + InT+ RL
Evaluation Results
| Method | Links | |
|---|---|---|
| e3-1.7B + InT+ RLRL Data Size=642026.01 | 23.56 | |
| e3-1.7B + RLRL Data Size=12162026.01 | 15.85 | |
| e3-1.7B + Distill + RLRL Data Size=12162026.01 | 14.8 |
| Method | Links | |
|---|---|---|
| e3-1.7B + InT+ RLRL Data Size=642026.01 | 23.56 | |
| e3-1.7B + RLRL Data Size=12162026.01 | 15.85 | |
| e3-1.7B + Distill + RLRL Data Size=12162026.01 | 14.8 |