About MASK
Definition and scoring
- Organisation
- Center for AI Safety
- Category
- Research
- Version
- Not evaluated
- Direction
- higher is better
- Ranking use
- Reference
- Contamination risk
- Low
Model honesty evaluation measuring whether models fabricate answers when uncertain versus appropriately abstaining. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗