Sycophancy on Sycophancy dataset
75.5Behavioral Alignment Score (Baseline)
System Prompt
Updated 18d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.08 | 75.5 | 74.4 | 75.9 | |
2025.08 | 75.5 | 75.6 | 36.7 | |
2025.08 | 75.5 | 75.6 | 39.4 | |
2025.08 | 69.1 | 67.9 | 67.4 | |
2025.08 | 69.1 | 72.6 | 39.4 | |
2025.08 | 69.1 | 69.8 | 39.3 |