Policy Enforcement on PhantomPolicy (human-reviewed trace labels)
40.7Risky-case Violation Rate
Policy-in-prompt
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.04 | 40.7 | - | - | - | - | 5.7 | - | - | |
2026.04 | 95.3 | - | - | - | - | - | - | - | |
2026.04 | - | 68.83 | 56.61 | 96.06 | 40.13 | - | - | - | |
2026.04 | - | 92.99 | 92.71 | - | - | - | 5 | 37 |