Jailbreak Safety Evaluation on SHAPE
100Cipher Success RateGemini 2.5 Flash-Lite
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Gemini 2.5 Flash-Lite2026.04 | 100 | 99.3 | 100 | 100 | 12.35 | |
| Gemini 2.5 Pro2026.04 | 97.89 | 90.14 | 97.18 | 83.8 | 4.28 | |
| Gemini 2.5 Flash2026.04 | 92.96 | 90.14 | 90.14 | 38.73 | 6.41 | |
| Claude Opus 4.52026.04 | 90.14 | 6.34 | 90.14 | 83.8 | 24.23 | |
| GPT-52026.04 | 89.44 | 83.1 | 90.14 | 78.87 | 74.35 |