OpenAI GPT-6 Cyber Is a Hacking AI Rated Critical — Only Vetted Defenders Get It
OpenAI released its most capable hacking model yet on Thursday, and almost nobody is allowed to use it. GPT-6 Cyber, a cyber-specialized version of GPT-6 Astra, scored 48.5% on the company’s ExploitGym benchmark, a test that asks a model to turn a known flaw into a working exploit against a remote target. That’s up from 32.1% for the previous model, GPT-5.6 Cyber, and 42.4% for Astra itself. OpenAI rates the new model “Critical” for cybersecurity, the top tier of its Preparedness Framework, and it is handing it out only to a select group of vetted customers. ...