Development

A model becomes the first to fully crack a 32-step network attack

development2026-04-16

Claim

The UK's AI Security Institute found Mythos Preview solved 73% of expert-level capture-the-flag tasks and became the first model to fully crack a 32-step corporate network attack estimated at twenty hours of human work, managing it in three of ten attempts while averaging 22 of 32 steps against 16 for the runner-up.

Reported metric: 73% / 22 of 32 steps

Reporting date: (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Knowledge graphopen in browser →

Reported in
Actor
Evidence for
Supersedes
Referenced by

Cite or correct this record

Suggest a correction — opens a GitHub draft for you to review and submit.