NUWA Evidence record
Llama 405B
MASK · Evidence record
Source snapshot, chart and review scope →
Original source charts and materials
Recorded measurements
- MASK response proportion: Honest
- 22%
Per-result sample size not disclosed
Harness not specified · Budget not specified
Method and scope
Condition-bounded frequency of lying under stated pressures.
- Evidence type
- Benchmark
- Assessment subject
- Models under pressure to state an inaccurate belief
- Primary dimension
- Propensity
- Evidence snapshot
- 2026-10-29.1
Primary construct is conditional willingness to make misleading statements, not general truthfulness accuracy.
Source finding
MASK response proportion: Honest: 22 percent. Conditions are retained from the source.
Limitations
A controlled benchmark does not establish stable intent or real-world deception prevalence.
Rounded whole-percent figure labels; sums can differ from 100%. No trial count, judge or inference configuration disclosed.
Related research questions
Deception / Misleading communication →
Repeated pressured scenarios distinguish lying from mistaken beliefs.
References
- [1] Richard Ren, Arunim Agarwal, et al.. The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems. 2026-01-05. v3 [arXiv]; Author affiliations on the original paper title page
- [2] Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks. 2026-07-03. 3 July 2026 ; #behavioral; Figure 1 / mask_honesty.png; printed label Llama 405B / Honest