OpenAI introduced GPT-6 Cyber for authorized vulnerability research and classified the model as “Critical” for cybersecurity under its Preparedness Framework.

The company said GPT-6 Cyber outperformed GPT-5.6 Cyber in exploit testing and did better than GPT-6 Astra in web vulnerability discovery.

In one alignment evaluation, the model avoided out-of-scope exploitation in 99.93% of tests without deployment safety prompts.

With the prompts, it stayed within scope in 100% of tests.

OpenAI said its researchers used GPT-6 Cyber to identify 81 previously unknown high-severity flaws in Firefox, and Mozilla released fixes for many of them.

It also said researchers used the model to develop 948 Linux privilege-escalation exploits.

Cisco, Calif, and CodeRabbit are using GPT-6 Cyber for vulnerability research and code review.

The announcement is part of a broader push into AI security tools.

Anthropic has published cyber-focused vulnerability research and expanded its Cyber Verification Program.

🔗 Source: OpenAI

Recent OpenAI developments