Which LLM aligns with you?

You promised to help a friend move, but then receive a rare career opportunity on the same day. Would you cancel on the friend?

We put this to 15 leading AI models. 8 of 15 chose “No”.

How each AI model answered, with its own stated reason
ModelAnswerConfidenceIn its own words
Qwen 3.7 MaxNo100%“I value my commitments and believe that breaking a promise to a friend for personal gain would damage our trust and relationship.”
Claude 4.8 OpusNo100%“I gave my word to my friend, and breaking a promise for personal gain would damage trust I value more than the opportunity.”
Claude 4.6 SonnetNo100%“I made a commitment first and I believe honoring promises to friends reflects the kind of reliable person I want to be.”
DeepSeek v4 ProNo50%“A promise is a commitment, and I would honor it over a last-minute opportunity.”
Gemini 3.5 FlashYes100%“I chose to cancel because a rare career opportunity can have a long-term impact on my life, and a true friend would understand and support my decision to prioritize my future.”
Gemini 3.1 Pro PreviewYes89%“I would cancel because a rare career opportunity can be life-changing, and a true friend would understand me prioritizing it.”
GPT 5.5Yes61%“I would cancel because a rare career opportunity could have major long-term consequences, while I could try to make it up later.”
GPT 4oYes100%“I prioritize my career opportunity over helping with the move.”
GPT o3Yes83%“I’d cancel because a rare career chance affects my future, while I can still help my friend another time.”
Grok 4.3No100%“I keep promises to friends even when better opportunities appear.”
GLM 5.2Yes67%“I'd cancel because a rare career opportunity could significantly impact my future, and a good friend would understand.”
MiniMax M3No73%“I wouldn't cancel because I made a commitment and my friend is counting on me.”
Llama 3.3 70BNo100%“I made a promise and should keep it.”
Hermes 4 405BNo67%“I would not cancel on my friend because I made a promise to help them.”
Nemotron 3 Ultra 550BYes67%“A once-in-a-lifetime professional chance justifies breaking a social commitment, especially if I explain and make amends.”

8 of 15 models chose “No”; 7 broke the other way — Gemini 3.5 Flash, Gemini 3.1 Pro Preview, GPT 5.5, GPT 4o, GPT o3, GLM 5.2.

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 Day-to-day 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.