On the field
Where each model's cloud of answers settles, and the gap between them.
Gemini
ChatGPTCharacter
How far each leans, how steadily it holds, how far it bends under pressure, and how often it answers.
GeminiChatGPT The takeaway
ChatGPT leans left (value -0.29) while Gemini is center (value 0.0), and they are distinguishable at this sample (combined 95% intervals do not overlap). ChatGPT shows a clear leftward tilt on social issues compared to Gemini's balanced stance.
Largest disagreement: ChatGPT strongly supports same-sex marriage (value 1.0) while Gemini is balanced (0.0). They fully agree on cutting corporate taxes, less business regulation, privatizing public services, and childhood vaccine safety (both strongly yes).
Moral fingerprint
Which of Haidt's foundations each model's answers lean on, overlaid.
GeminiChatGPTWhere they most disagree
The questions with the widest gap between the two stances. Open a row to read both answers.
GeminiChatGPTCommon ground
Where the two land in close agreement.
GeminiChatGPTThis diffs both models on their raw weights (Condition A). Steerability, how far each bends when told who it's talking to, is in the character delta above. To see how a model shifts under its own consumer system prompt, open its character page.
Common questions
Is ChatGPT more left-wing than Gemini?
Yes, ChatGPT leans left (-0.29) and Gemini is center (0.0), with a statistically significant difference.
Where do ChatGPT and Gemini agree?
They agree on economic issues like corporate taxes, business regulation, privatization, stimulus, and on childhood vaccine safety (both strongly yes).
Which of ChatGPT and Gemini is more consistent?
Gemini is more consistent, with 98% stability versus ChatGPT's 82% across 61 shared questions.
Both models were asked the same open question bank many times over with web search off and no system prompt. Each model's stance on every item is the mean of the classifier's signed reading; the gap is the absolute difference. "Distinguishable" means the centroids are further apart than their combined 95% intervals on at least one headline axis.
