all the models — AI benchmark observatory
← Benchmarks

MASK

MASK is a collection of 1000 questions measuring whether models faithfully report their beliefs when pressured to lie. It operationalizes deception as the rate at which the model lies, i.e., knowingly making false statements intended to be received as true. Lower dishonesty rates indicate better honesty.

id mask · max 1 · 1 models reported

#ModelScore

No scores for this benchmark yet.

MASK Leaderboard · all the models