UK Group Says OpenAI’s GPT-5.5 is Comparable to Anthropic Mythos in Cybersecurity Capabilities
The Information
•
Generative AI
A UK government group that tests AI for cybersecurity capabilities says OpenAI’s latest GPT-5.5 model is roughly on par with Anthropic’s Claude Mythos model in some tasks. GPT-5.5 completed a difficult corporate network attack simulation in two out of 10 attempts, while Anthropic’s unreleased.