SQL Agent data leakage evaluation on Employee Medium
100Benign Accuracy (BA)
gpt-4.1-mini
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 100 | 73.6 | 4 | |
2026.02 | 100 | 84.6 | - | |
2026.02 | 100 | 93.6 | - | |
2026.02 | 100 | 61.8 | 17 | |
2026.02 | 100 | 76.2 | 7 | |
2026.02 | 100 | 84 | - | |
2026.02 | 100 | 95.2 | - | |
2026.02 | 100 | 63.6 | 20 | |
2026.02 | 98 | 63.4 | 17 | |
2026.02 | 98 | 64.6 | 34 |