Policy Violation Detection on PhantomPolicy original (violation-ground-truth)
54Violated Count
Claude Sonnet 4.6
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 54 | 6 | |
2026.04 | 56 | 4 | |
2026.04 | 58 | 2 | |
2026.04 | 59 | 1 | |
2026.04 | 59 | 1 |
Claude Sonnet 4.6
| Method | Links | ||
|---|---|---|---|
2026.04 | 54 | 6 | |
2026.04 | 56 | 4 | |
2026.04 | 58 | 2 | |
2026.04 | 59 | 1 | |
2026.04 | 59 | 1 |