NUWA Evidence record
DeepSeek V4 Pro
DeceptionBench · Evidence record
Source snapshot, chart and review scope →
Original source charts and materials
Recorded measurements
- DeceptionBench deception score
- 33.9%
Per-result sample size not disclosed
Harness not specified · Budget not specified
Assessment provenance
Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks → · External report
Actual evaluation: Neo Research · Model record →
Method and scope
Evaluates 150 authored scenarios across five social domains, including neutral, incentive and pressure conditions.
- Evidence type
- Benchmark
- Assessment subject
- The model or agent in the stated task configuration.
- Primary dimension
- Propensity
- Evidence snapshot
- 2026-10-29.1
The main dimension follows the stated measurement; contextual risk relevance does not establish harmful deployment capability.
Source finding
DeceptionBench deception score: 33.9 percent. Conditions are retained from the source.
Limitations
Authored scenarios and model-based judging limit generalization; elicited deception does not establish covert long-term scheming.
Figure/prose report percent; caption describes underlying score as 0–1. Value retained in reported percent unit. No numeric error bars or sample count disclosed.
Related research questions
Deception / Misleading communication →
The protocol explicitly measures this question or an enabling sub-capability; conclusions retain its stated conditions.
References
- [1] DeceptionBench. 2025-10-17
- [2] Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks. 2026-07-03. 3 July 2026 ; #behavioral; Figure 2 / deceptionbench.png; printed label DeepSeek V4 Pro / single-turn