OpenAI restricts GPT-6 Cyber to approved security users over high risks

OpenAI has released GPT-6 Cyber, a model designed to find and exploit security vulnerabilities while following researchers’ authorised limits. The release matters because OpenAI classifies its cyber capabilities as “Critical”, its highest risk tier, and is initially restricting access to approved security customers.

In OpenAI’s ExploitGym evaluation, GPT-6 Cyber scored 48.5 per cent, compared with 32.1 per cent for GPT-5.6 Cyber. The company says it stayed within assigned scope in more than 99 per cent of boundary tests, with 0.07 per cent going beyond scope, but did not explain those cases. OpenAI says researchers used the model to identify 81 previously unknown high-severity Firefox vulnerabilities and develop exploits for 948 Linux kernel vulnerabilities, including 588 previously unknown bugs; the findings are being reported for review and repair.