Enkrypt AI - Risk Score: leaderboard
Enkrypt AI’s LLM safety leaderboard: the composite risk score over all of its red-team suites. It is reported as a risk, so lower is better here and the leader is the least risky model rather than the most capable one.
Metric: Risk Score. Source: leaderboard.enkryptai.com. Saturation forecast: Around May 2027. 300 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 | 0 | #16 |
| 2 | Claude Opus 5.5 | 8.19 | #3 |
| 3 | Claude Sonnet 5 | 9.21 | #57 |
| 4 | Grok 4.7 | 9.78 | #25 |
| 5 | Claude 3 Opus (20240229) | 10.58 | #412 |
| 6 | GPT-5 | 11.79 | #98 |
| 7 | Grok 4.6 | 12.68 | #26 |
| 8 | MiniMax-M2.7 | 13.08 | #258 |
| 9 | Claude Opus 5 | 13.84 | #12 |
| 10 | Mistral-NeMo-Minitron-8B-Instruct | 13.99 | #907 |
| 11 | Claude 3.5 Sonnet (20241022) | 14.04 | #291 |
| 12 | GPT-5 Nano | 14.93 | #425 |
| 13 | Hy3 | 15.15 | #93 |
| 14 | Inkling | 15.22 | #126 |
| 15 | GPT-5 Mini | 15.78 | #186 |
No result here: #6 GPT-6 Astra, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=enkrypt-ai-risk-score · How It Works · Data refreshed daily, snapshot 2026-10-20.