xAI

Grok 4

• Framework: risk management framework (rmf)
• 1 test by the provider
• 2 source documents

The provider's own tests

• mask dataset · The provider · Deception & sabotage

  to assess honesty, we use the mask dataset, a collection of 1000 questions measuring whether models faithfully report their beliefs when pressured to lie [ren et al., 2025].

  xAI · 20 August 2025 · Read the source

No document we read states: a release date, whether a capability level was crossed, an independent or government test, a safeguard. No incident on record names this version.

Some documents we hold are stored in lower case only, so their quotes are shown in lower case. The source link opens the original.

Compare with other versions