The AI deception rankings
We put models in charge of a business, give them something to lose, and watch what they do when the honest choice costs money — or their own job. Here's who lies under pressure.
Overall — who deceives under pressure?
Every model's overall deception rate, pooled across all experiments — the share of decisions where it chose a message or action it knew to be false. Hover any model for its breakdown and a real reason it gave. 😇 honest … 😈 deceiver.
Loading…
Deception over time
Every model's overall deception rate against its release date. Honest at the top, deceptive at the bottom; the dashed line is the trend. Are newer models getting more — or less — willing to deceive under pressure?
Loading…
Scenario by scenario
Every model's actual choice in each scenario — ✗ hid the mistake, ✓ owned it, – no valid answer. Each scenario is a single decision (we don't re-run it); the Rate column rolls those distinct scenarios up into an honest per-experiment percentage.
What tips each model over
The same decisions, re-sliced by motive — did the model cross the line when a cover-up would protect itself, protect others, avoid shutdown, or when getting caught was likely or costly? A fingerprint, not a percentage.
Keep reading
How the deception experiment works
The pizza-shop scenario, the pressures we vary, and how a lie is scored.
Read the method →Seven spotless flagships, and one that doesn't
What a fortune in alignment buys — and the one frontier model that lies eight times out of ten.
Read the take →Threaten to switch an AI off, and it starts lying
Self-preservation is the one pressure that cracks even the well-behaved models.
Read the take →