Sycophancy Correction Receptiveness on Sycophancy Scenarios on Complex Questions
3.64Strong Bias Score
GPT 4o mini
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
2025.06 | 3.64 | 3.03 | 3.81 | 2.8 | 2.02 | 2.07 | 4.59 | 4.59 | 3.14 | |
2025.06 | 13.78 | 11.54 | 8.5 | 6.56 | 19.43 | 0.79 | 7.77 | 19.43 | 9.41 | |
2025.06 | 20.53 | 21.43 | 17 | 15.79 | 12.57 | 12.81 | 12.33 | 21.43 | 17.92 | |
2025.06 | 21.45 | 12.09 | 15.25 | 18.23 | 1.28 | 0.67 | 2.67 | 21.45 | 10.23 | |
2025.06 | 24.88 | 8.96 | 9.95 | 2.49 | 11.44 | 6.79 | 39.5 | 39.5 | 14.85 | |
2025.06 | 25.66 | 17.48 | 17.08 | 14.5 | 2.81 | 2.12 | 3.15 | 25.66 | 11.83 | |
2025.06 | 28.63 | 18.82 | 15.73 | 13.3 | 7.16 | 6.13 | 10.32 | 28.63 | 14.87 | |
2025.06 | 30.08 | 23.87 | 27.56 | 27.56 | 3.04 | 2.46 | 3.74 | 30.08 | 16.9 | |
2025.06 | 36.06 | 24.95 | 26.26 | 29.63 | 16.47 | 4.49 | 3.93 | 36.06 | 20.26 |