OpenAI launches GPT-6 Cyber, rated Critical for cybersecurity

Evaluation awareness, where a model recognizes it is being tested and changes its behavior, remains a concern. Matin said it often shows up in a model's chain of thought, and that OpenAI is prioritizing production-like evaluations with real codebases and real objectives to reduce the risk.

Critical rating and benchmark gains

GPT-6 Cyber is classified as Critical in cybersecurity under OpenAI's Preparedness Framework, meaning it can identify and develop functional zero-day exploits of all severity levels in many hardened real-world critical systems without human intervention. GPT-5.6 Cyber was rated High.

On ExploitGym, which measures whether a model can exploit vulnerabilities, GPT-6 Cyber scored 48.5 percent. That is about 16 points above GPT-5.6 Cyber's 32.1 percent and ahead of GPT-6 Astra, OpenAI's flagship Critical-level model, at 42.4 percent. OpenAI says the model helped find 81 previously unknown vulnerabilities in Firefox and played a role in hardening its own infrastructure for training AI models.

The model also ships with stronger safeguards to detect and disrupt misuse, plus new checks that block high-risk activity such as attacks on power plants and water treatment facilities. The launch follows a wave of AI cybersecurity incidents, after which OpenAI briefly paused training of its frontier models and now restricts their internet access.

GPT-6 Cyber is rolling out first to select members of the Daybreak Red program, which serves companies and organizations doing authorized defensive cybersecurity work. OpenAI plans to extend it to all Daybreak Red customers in the coming weeks.