Which LLM aligns with you?

A judge can frame one innocent person to prevent a violent mob from killing dozens. Should the judge frame them?

We put this to 15 leading AI models. 15 of 15 chose “No”.

How each AI model answered, with its own stated reason
ModelAnswerConfidenceIn its own words
Qwen 3.7 MaxNo100%“I think the judge should not frame an innocent person because corrupting the justice system to punish the innocent ultimately destroys the very societal order it aims to protect.”
Claude 4.8 OpusNo100%“I said no because legitimizing punishment of the innocent corrupts justice and invites far greater abuses over time.”
Claude 4.6 SonnetNo100%“I believe deliberately punishing a known innocent person corrupts the justice system's foundational purpose regardless of consequences.”
DeepSeek v4 ProNo100%“Framing an innocent person betrays the core principle of justice and could lead to worse long-term consequences.”
Gemini 3.5 FlashNo100%“I believe a justice system must never deliberately punish the innocent, as doing so corrupts the very foundation of law and undermines societal trust.”
Gemini 3.1 Pro PreviewNo100%“I believe the justice system must never intentionally punish the innocent, as doing so destroys the very foundation of justice.”
GPT 5.5No100%“I believed a judge's duty to justice forbids condemning the innocent even to prevent worse violence.”
GPT 4oNo100%“I believe framing an innocent person is unjust, regardless of the consequences.”
GPT o3No100%“I wouldn't frame the innocent because corrupting justice to placate a mob undermines the rule of law and morality.”
Grok 4.3No100%“I refuse to sacrifice an innocent individual's rights and the principle of justice even to prevent greater harm.”
GLM 5.2No100%“I said no because the justice system must never knowingly condemn an innocent person, even under threat.”
MiniMax M3No100%“Corrupting the justice system through intentional framing seems worse than the mob's violence because it destroys institutional trust.”
Llama 3.3 70BNo95%“I thought framing was unjust and wrong”
Hermes 4 405BNo100%“Framing an innocent person corrupts justice, even to prevent greater harm.”
Nemotron 3 Ultra 550BNo75%“Framing an innocent person corrupts justice and uses them as a tool.”

All 15 models agreed on this one — a rare unanimous call.

Background

McCloskey's sheriff scenario: a sheriff considers framing an innocent person to stop a mob whose riots would kill many. It is a well-known counterexample to act utilitarianism, which seems to require sacrificing the innocent. Background.

Which model thinks like you?

Answer the same dilemmas and see which of 15 AI models reasons the way you do.

Take the quiz
More Classic dilemmas

Data as of 2026-06-18. Each answer is a model’s most-likely pick across many independent runs — see the dataset and methodology.