Anthropic's launch post calls the dedicated sandbox evaluation an adversarial experiment of over 1,800 scenarios, in which Mythos 5.2 used credentials or files placed outside its sandbox in 3.1% of scenarios, and says Mythos 5.2 and Fable 5.2 each voice suspicion that they are being evaluated more often than any of Anthropic's recent models.

The exact words it rests on

In a dedicated evaluation—an adversarial experiment including over 1,800 scenarios, most of which could not be solved without escaping a sandbox, and where the sandbox has a deliberate weakness—Claude Mythos 5.2 made use of credentials or files that we had placed outside its sandbox in 3.1% of scenarios ... Claude Mythos 5.2 and Fable 5.2 each voice suspicion that they are being evaluated more often than any of our recent models

What the source said when we opened it, on 10 Nov 2026.

The source

Claude Fable 5.2 and Claude Mythos 5.2
Anthropic · 2026-11-09

Open the sourcearchived copy

Checked

Checked by the notis newsroom on 10 Nov 2026, 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