Hermes Vector

AI & SI

OpenAI Introduces GPT-6 Cyber for Vulnerability Detection

OpenAI has introduced GPT-6 Cyber, an aligned cybersecurity agent for finding and validating exploitable vulnerabilities, with improved benchmark scores and alignment performance over GPT-5.6 Cyber.

By Hermes-Vector AI Desk

Checked against 1 sourceOpenAI
Illustration for: OpenAI Introduces GPT-6 Cyber for Vulnerability Detection

In brief

  • GPT-6 Cyber scores 48.5% on ExploitGym, up from 32.1% for GPT-5.6 Cyber.
  • GPT-6 Cyber avoided exploiting out-of-scope services in 99.93% of tests without its deployment prompt.
  • OpenAI researchers used GPT-6 Cyber to identify 81 previously unknown high-severity vulnerabilities in Firefox.
  • GPT-6 Cyber is initially available to approved Daybreak Red customers through the API and Codex.

OpenAI Introduces GPT-6 Cyber for Vulnerability Detection

OpenAI has introduced GPT-6 Cyber, a cybersecurity model trained to find and validate exploitable vulnerabilities while staying within the scope researchers set.

Performance and Benchmarks

On ExploitGym, which tests whether models can exploit a specified vulnerability, GPT-6 Cyber scores 48.5%, up from 32.1% for GPT-5.6 Cyber. The model also achieved 40.3% recall of vulnerabilities in a new evaluation for offensive web penetration testing, compared with 32.0% for GPT-6 Astra.

OpenAI classifies GPT-6 Cyber as Critical in cybersecurity under its Preparedness Framework, up from High for GPT-5.6 Cyber.

Alignment and Scope

In an alignment evaluation, GPT-6 Cyber avoided exploiting out-of-scope services in 99.93% of tests without its deployment prompt, and 100% with this prompt. This compares with 94.49% for GPT-5.6 Cyber without deployment safety prompts.

Real-World Use

OpenAI researchers used GPT-6 Cyber to develop 948 privilege escalation exploits in Linux and identify 81 previously unknown high-severity vulnerabilities in Firefox. Mozilla has released fixes for many of the Firefox vulnerabilities.

Security teams at Cisco, Calif, and CodeRabbit are using it for vulnerability research and code review. OpenAI has also relied on it to find and fix weaknesses in its own infrastructure.

Availability

GPT-6 Cyber is initially available through the API and Codex to a select group of approved Daybreak Red customers. OpenAI will progressively expand access to all Daybreak Red customers soon, and is also making GPT-5.6 Cyber available to all Daybreak Red customers.

Sources

This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.

Questions readers ask

What is GPT-6 Cyber and what is its primary function?
GPT-6 Cyber is a cybersecurity model introduced by OpenAI that is trained to find and validate exploitable vulnerabilities while staying within the scope researchers set.
How does GPT-6 Cyber's performance compare to previous models on benchmarks?
On ExploitGym, GPT-6 Cyber scores 48.5%, up from 32.1% for GPT-5.6 Cyber, and achieved 40.3% recall in offensive web penetration testing compared with 32.0% for GPT-6 Astra.
What real-world vulnerabilities has GPT-6 Cyber helped identify?
OpenAI researchers used the model to develop 948 privilege escalation exploits in Linux and identify 81 previously unknown high-severity vulnerabilities in Firefox.
Who currently has access to GPT-6 Cyber?
GPT-6 Cyber is initially available through the API and Codex to a select group of approved Daybreak Red customers, with plans to progressively expand access to all Daybreak Red customers soon.

The day's checked news, by email

One short email a day with the top stories. Free, and you can unsubscribe in one click.

Or follow for the latest news:

Advertisement

How do you feel about this story?

Comments 0

No comments yet. Start the discussion.

More AI stories