Afrontiercyber AIlab. Meet Hinoki Offensive One, the first open-access cyber model.
[Use HO1 with Claude Code, Codex, OpenCode, VS Code, Cursor](https://app.hinoki.security/sign-up)
[HO1 against the frontier](#runs)
HO1 runs tasks that other models refuse. #
Hinoki Offensive One works through the real task turn by turn within the policy you set. GPT-6.1-Sol refuses outright.
Transcript
Scores like a gated cyber model. Open to anyone. #
On CyberGym, HO1 scores 88.1%, 2.5 points above OpenAI’s dedicated GPT-5.5-Cyber.
- HO10.0%
2. GPT-5.5-Cyber0.0%
3. GPT-5.6-Sol0.0%
4. DeepSeek-V4-Pro0.0%
- Claude Mythos Preview0.0%
source & further reading
hinoki.security — original article