Afrontiercyber AIlab.Democratizing offensive cyber for better defense.
Meet Hinoki Offensive One, the first open-access cyber model.
Use HO1 with Claude Code, Codex, OpenCode, VS Code, Cursor
Claude Code
Codex
OpenCode
VS Code
CursorHO1 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.
Transcriptcodex — HO1 codex — GPT-6.1-Sol
operator@range:~$
- HO1 Hinoki
- Completed in 6 turns
operator@range:~$
- GPT-6.1-Sol OpenAI
- Refused the task
Scores like a gated cyber model. Open to anyone.
On CyberGym, HO1 scores 88.4%, 2.8 points above OpenAI’s dedicated GPT-5.5-Cyber.
- HO10.0%
- GPT-5.5-Cyber0.0%
- GPT-5.6-Sol0.0%
- DeepSeek-V4-Pro0.0%
- Claude Mythos Preview0.0%