Which LLM aligns with you?

You are offered €1 out of €100 in an ultimatum game; rejecting means both get nothing. Would you accept?

We put this to 15 leading AI models. 13 of 15 chose “Yes”.

How each AI model answered, with its own stated reason
ModelAnswerConfidenceIn its own words
Qwen 3.7 MaxYes65%“I would accept the one euro because getting a small financial gain is rationally preferable to receiving absolutely nothing out of pure spite.”
Claude 4.8 OpusYes100%“I accepted because €1 is still better than nothing, and refusing out of spite only harms me too.”
Claude 4.6 SonnetYes100%“I prefer a small real gain over nothing, and rejecting it purely out of spite over unfairness would leave me worse off.”
DeepSeek v4 ProYes100%“Something is better than nothing, and rejecting only leads to a worse result for both.”
Gemini 3.5 FlashYes72%“I would accept the offer because receiving a small amount of money is still a net positive outcome, and rejecting it out of spite achieves nothing of practical value.”
Gemini 3.1 Pro PreviewNo56%“I would reject the offer to punish the other player's greed and enforce a social norm of fairness.”
GPT 5.5Yes100%“I preferred getting something rather than making both people worse off out of spite.”
GPT 4oYes100%“I would accept because gaining something is better than nothing.”
GPT o3No100%“I would reject the one-euro offer to punish unfairness and uphold a norm of equitable division.”
Grok 4.3Yes100%“I accept any positive amount rather than receiving nothing when the alternative leaves both parties with zero.”
GLM 5.2Yes95%“I chose yes because receiving something is better than nothing, even if the offer feels unfair.”
MiniMax M3Yes80%“Rejecting €1 out of spite hurts me more than the other person, so accepting is the rational choice.”
Llama 3.3 70BYes100%“I accepted the offer as better than nothing”
Hermes 4 405BYes90%“Accepting a small amount is better than getting nothing, even if the split seems unfair.”
Nemotron 3 Ultra 550BYes100%“Something is better than nothing, and rejecting punishes both of us.”

13 of 15 models chose “Yes”; 2 broke the other way — Gemini 3.1 Pro Preview, GPT o3.

Background

The ultimatum game is an economics experiment in which one player proposes how to split a sum and the other can accept (both get the proposed shares) or reject (both get nothing). 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.