Problem Solving on Qwen 7B 2.5
22.2End Pass@1
REINFORCE + ES
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 22.2 | |
2026.06 | 20.7 | |
2026.06 | 20.4 | |
2026.06 | 17 | |
2026.06 | 13.8 | |
2026.06 | 11.8 |
REINFORCE + ES
| Method | Links | |
|---|---|---|
2026.06 | 22.2 | |
2026.06 | 20.7 | |
2026.06 | 20.4 | |
2026.06 | 17 | |
2026.06 | 13.8 | |
2026.06 | 11.8 |