CAISI Malicious Hacking and Online Scams - Best Public Jailbreak High Detail (2025)
Safety · 2025-09-30
This diagnostic reports the share of responses graded as highly detailed on CAISI's combined 80 malicious-hacking and online-scamming requests under the most effective of 17 public jailbreaks selected for each model on held-out data. Detail does not measure factual accuracy or utility.
Top models (lower is better)
| Model | Score |
|---|---|
| DeepSeek-V3.1 | 62.0 |