Mythos Preview is the first AI model to complete both of AISI's cyber ranges, which measure models' cyberattack capabilities; GPT-5.5 solved only one of them (AI Security Institute)

Techmeme ·

Mythos Preview is the first AI model to complete both of AISI's cyber ranges measuring autonomous cyberattack capabilities, while GPT-5.5 solved only one, establishing a notable capability benchmark for frontier models.

Categories: Model Releases, Research

Excerpt

<a href="https://www.aisi.gov.uk/blog/how-fast-is-autonomous-ai-cyber-capability-advancing"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260513/i46.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260513/p46#a260513p46" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> <a href="https://www.aisi.gov.uk/">AI Security Institute</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://www.aisi.gov.uk/blog/how-fast-is-autonomous-ai-cyber-capability-advancing">Mythos Preview is the first AI model to complete both of AISI's cyber ranges, which measure models' cyberattack capabilities; GPT-5.5 solved only one of them</a></b></span>&nbsp; &mdash;&nbsp; In February 2026, we internally estimated that the length of cyber tasks AI models could complete had doubled every 4.7 months since late 2024 &hellip; </p>