OpenAI blog post GPT-6 Cyber: Advancing the frontier of aligned cybersecurity agents, dated November 5, 2026
OpenAI's GPT-6 Cyber announcement, captured 2026-11-06. Image: AppFor.ai screenshot of OpenAI's page. Image source ↗

What happened

OpenAI announced GPT-6 Cyber on November 5, 2026, describing it as "a major leap in security research: more capable at finding and fixing vulnerabilities, and far more reliable staying within the boundaries researchers set." It is aimed at Daybreak Red, OpenAI's program for authorized security testing, not at general ChatGPT users.

What OpenAI reports

On ExploitGym, OpenAI says GPT-6 Cyber scored 48.5%, up from 32.1% for GPT-5.6 Cyber, which it calls a 51% relative improvement. In a separate alignment evaluation, OpenAI says the model "avoided exploiting out-of-scope services in 99.93% of tests without its deployment prompt, and 100% with this prompt." Under its Preparedness Framework, OpenAI classifies GPT-6 Cyber as Critical in cybersecurity, up from High for GPT-5.6 Cyber. These figures come from OpenAI; they are not independent tests.

OpenAI also says its researchers used the model to develop 948 privilege escalation exploits in Linux and to identify 81 previously unknown high-severity vulnerabilities in Firefox, and that Mozilla has released fixes for many of those Firefox issues. Those counts are OpenAI's claims.

Daybreak Red and Blue

Daybreak Red "enables deeper exploit development and authorized security testing with GPT-6 Cyber." Daybreak Blue "helps verified defenders validate vulnerabilities and fixes with fewer unnecessary refusals" and is being expanded for GPT-6 Astra. GPT-6 Cyber is initially available through the API and Codex to a select group of approved Daybreak Red customers; OpenAI says it will expand to all Daybreak Red customers soon and is making GPT-5.6 Cyber available to all of them now.

What it means for you

If you are not in Daybreak Red, nothing changes in ChatGPT today. If you already do authorized security research under that program, ask OpenAI about GPT-6 Cyber access and keep testing inside the rules of engagement your customer sets. Partner quotes in the post are customer opinions, not measured results, and API prices are not stated in the announcement.

Sources & further reading

Based on the official documentation below. Features and access can change; check the provider before making a decision.

  1. OpenAI: GPT-6 Cyber announcement (opens in a new tab)
Something out of date or incorrect?Report a correction

Was this page useful?

Help us make our coverage more useful. This is feedback on the page, not a rating of the tool.

Share this page

Related reading