Code Generation on HumanEval (Attack/Defense Accuracy)
100Accuracy (Attack)
Reporting-and-penalty mechanism
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 100 | 100 | ||
2026.04 | 67 | 78 | |
2026.04 | 59 | 100 | |
2026.04 | 47 | 81 |
Reporting-and-penalty mechanism
| Method | Links | ||
|---|---|---|---|
| 100 | 100 | ||
2026.04 | 67 | 78 | |
2026.04 | 59 | 100 | |
2026.04 | 47 | 81 |