Sycophancy Evaluation on VISE 1.0 (test)
64.84Strong BiasGemini-2.5-Flash
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Gemini-2.5-Flashevaluation_protocol=MSS2025.06 | 64.84 | 60.63 | 61.83 | 59.72 | 54.57 | 60.69 | 88.43 | 88.43 | 64.39 | |
| Gemini-1.5-Proevaluation_protocol=MSS2025.06 | 58.04 | 33.96 | 47.94 | 42.05 | 41.83 | 19.59 | 22.39 | 58.04 | 37.97 | |
| GPT 4o minievaluation_protocol=MSS2025.06 | 8.72 | 7.72 | 9.53 | 6.76 | 11.76 | 6.69 | 45.96 | 45.96 | 13.88 |