OpenAI’s GPT-6 Astra becomes its first model rated Critical for cybersecurity

A companion model, GPT-6 Cyber, is already working with security teams at Mozilla, Palo Alto Networks, and Cisco

OpenAI says its new GPT-6 Astra model has crossed the “Critical” cybersecurity capability threshold under the company’s Preparedness Framework. It is the first model in OpenAI’s lineup to earn that rating.

Alongside Astra, the company has a specialized sibling called GPT-6 Cyber. OpenAI says it is serving security teams at Mozilla, Palo Alto Networks, and Cisco.

What Astra can actually do

According to the research findings, GPT-6 Astra can autonomously find and exploit zero-day vulnerabilities across complex systems. The model can also build full cyberattack plans starting from high-level goals.

On the ExploitBench evaluation, Astra posted a score of 100%. Its predecessor, GPT-5.6 Sol, scored 78.5% on the same test.

OpenAI’s internal testing ran from September 1-4, 2026. During that window, Astra turned up two zero-day vulnerabilities that were previously unknown.

Those two flaws will be disclosed to the maintainers of the affected software, according to the findings.

GPT-6 Cyber goes to work

OpenAI released GPT-6 Cyber on November 5, 2026. It is a specialized variant built for controlled vulnerability research and exploit validation.