OpenAI's new GPT-5.5-Cyber tops Claude Mythos 5 in vulnerability benchmark (opens in new tab)

Covered by Metacurity

OpenAI is rolling out the full, limited-release version of GPT-5.5-Cyber—a specialized AI model that outperforms its predecessors and Claude Mythos 5 in security benchmarks like CyberGym.

Read the original article

Sign in to keep reading the full article.

Sign Up Log In

Covered in 1 article

Metacurity·

Covered in 1 article

Admin accelerates quantum push, advances timeline for quantum-safe security