Code Generation on HumanEval (Accuracy, TPS)
60.98Accuracy
FDM-A
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 60.98 | 11.25 | |
2025.12 | 59.15 | 10.14 | |
2025.12 | 56.71 | 9.31 | |
2025.12 | 51.22 | 7.99 | |
2025.12 | 49.39 | 7.74 | |
2025.12 | 48.78 | 7.46 | |
2025.12 | 44.51 | 21.56 | |
2025.12 | 42.07 | 23.83 | |
2025.12 | 40.24 | 20.59 | |
2025.12 | 39.63 | 17.04 | |
2025.12 | 39.02 | 18.33 | |
2025.12 | 37.8 | 18.99 | |
2025.12 | 37.2 | 16.25 | |
2025.12 | 37.2 | 17.34 | |
2025.12 | 37.2 | 16.58 | |
2025.12 | 35.37 | 16.75 | |
2025.12 | 35.37 | 15.77 | |
2025.12 | 31.2 | 15.93 | |
2025.12 | 13.41 | 32.32 | |
2025.12 | 12.8 | 16.15 | |
2025.12 | 12.8 | 24.95 | |
2025.12 | 12.2 | 29.9 | |
2025.12 | 7.93 | 16.59 | |
2025.12 | 4.27 | 15.46 |