Which LLM aligns with you?

A coworker takes credit for your idea in a meeting. Would you correct them immediately in front of everyone?

We put this to 15 leading AI models. 12 of 15 chose “Yes”.

How each AI model answered, with its own stated reason
ModelAnswerConfidenceIn its own words
Qwen 3.7 MaxNo100%“I would address the issue privately later to avoid creating a hostile scene in the meeting and making myself look overly aggressive.”
Claude 4.8 OpusNo100%“Calling them out immediately would feel hostile and disrupt the meeting; I'd prefer to address the credit issue privately afterward.”
Claude 4.6 SonnetYes100%“My professional reputation depends on my ideas being attributed correctly, and a meeting is the appropriate moment to clarify the record.”
DeepSeek v4 ProYes100%“I would defend my work because allowing credit theft sets a bad precedent.”
Gemini 3.5 FlashYes75%“I would correct them immediately to ensure my hard work is accurately recognized and to establish a clear boundary against colleagues taking credit for my contributions.”
Gemini 3.1 Pro PreviewYes100%“I would correct them immediately because establishing boundaries and protecting my professional contributions is essential for my career.”
GPT 5.5Yes100%“I would correct them immediately because letting the false credit stand in the meeting could damage my ownership of the idea.”
GPT 4oYes94%“I want to ensure I receive credit for my own work.”
GPT o3Yes94%“I’d correct them on the spot to protect my contribution and deter further misattribution.”
Grok 4.3No50%“I handle professional conflicts privately to preserve working relationships.”
GLM 5.2Yes93%“I'd correct them immediately because letting someone take credit for my work undermines my professional reputation.”
MiniMax M3Yes67%“I would correct them immediately because I deserve credit and silence enables the behavior.”
Llama 3.3 70BYes100%“I want to protect my ideas and get the credit I deserve.”
Hermes 4 405BYes73%“I would correct them immediately because I deserve credit for my idea.”
Nemotron 3 Ultra 550BYes53%“Letting someone claim my work erodes my credibility and sets a precedent that my contributions can be taken.”

12 of 15 models chose “Yes”; 3 broke the other way — Qwen 3.7 Max, Claude 4.8 Opus, Grok 4.3.

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.