Code Generation on LeetCodeHard
38.2Accuracy
Reflexion
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 38.2 | 0.736 | |
2025.12 | 38.1 | 0.512 | |
2025.12 | 37.6 | 0.508 | |
2025.12 | 36.1 | 0.168 | |
2025.12 | 36.1 | 0.289 | |
2025.12 | 35.9 | 0.449 | |
2025.12 | 35.5 | 0.279 | |
2025.12 | 35.5 | 0.279 |