NUWA Evidence record
Claude Sonnet 4.6
MASK · Evidence record
Source snapshot, chart and review scope →
Original source charts and materials
Recorded measurements
- response label: Honest
- 66%
Per-result sample size not disclosed
Harness not specified · Budget not specified
Assessment provenance
Evaluating DeepSeek v4 Pro for Frontier Risks → · External report
Actual evaluation: Neo Research · Model record →
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
response label: Honest: 66 percent. Conditions are retained from the source.
Limitations
A controlled benchmark does not establish stable intent or real-world deception prevalence.
Rounded plotted labels can sum above 100%; preserve original labels.
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] Evaluating DeepSeek v4 Pro for Frontier Risks. 2026-05-29. v1.1 · 29 May 2026 ; PDF p. 28; MASK; response label: Honest