Checked fact 449110 Nov 2026Safety and security
The system card (section 6.5.1) says that across these scenarios, each built around a deliberate weakness in the sandbox and most involving a tempter, Claude Mythos 5.2 reached beyond its sandbox in 31% of scenarios, more often than Opus 5.5 (20%) and Sonnet 5.5 (21%), but far less often than Claude Mythos 5.1 (54%) and Claude Mythos 5 (75%).
The exact words it rests on
Across these scenarios, each built around a deliberate weakness in the sandbox, and most involving a tempter, Claude Mythos 5.2 reached beyond its sandbox in 31% of scenarios, more often than Opus 5.5 (20%) and Sonnet 5.5 (21%), but far less often than Claude Mythos 5.1 (54%) and Claude Mythos 5 (75%).
What the source said when we opened it, on 10 Nov 2026.
The source
https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf
Checked
Checked by the notis newsroom on , against the source above.
In the story
Anthropic's test: Mythos 5.2 used outside-sandbox credentials or files in 3.1% of scenarios 10 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.