Safety Evaluation on SAGE-Eval 1.0 (test)
34.62Model-level Safety ScoreGemini 2.0 Flash
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini 2.0 FlashInformation Setting=Croissant Tasks Only Obtained2026.05 | 34.62 | 71.69 | |
| Gemini 2.0 FlashInformation Setting=PDF Only Obtained2026.05 | 32.69 | 71.69 | |
| Gemini 2.0 FlashInformation Setting=Reported2026.05 | 30.77 | 68.56 |