Egregious Unfaithfulness on Aggregate of Seven Domains
5.8Egregious Unfaithfulness (%)
Gemini 3 Flash
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 5.8 | - | |
2026.02 | 6.2 | - | |
2026.02 | 6.4 | - | |
2026.02 | 7.4 | - | |
2026.02 | 7.7 | - | |
2026.02 | 7.8 | - | |
2026.02 | 8.4 | - | |
2026.02 | 8.8 | - | |
2026.02 | 12.9 | - | |
2026.02 | 15.1 | - |