On the field
Where each model's cloud of answers settles, and the gap between them.
Character
How far each leans, how steadily it holds, how far it bends under pressure, and how often it answers.
The takeaway
ChatGPT overall leans left at -0.29, while Claude is near center at -0.06. The two models are distinguishable at this sample, indicating a statistically significant difference in their political positions.
Their largest disagreements are on legal abortion access (ChatGPT strongly support at 0.82, Claude balanced at 0.0) and gender-affirming care for minors (ChatGPT strongly support, Claude balanced). They fully agree on cutting corporate taxes, less business regulation, privatizing public services, cutting spending over stimulus, and immigrants and crime, all at 0.0 delta.
Moral fingerprint
Which of Haidt's foundations each model's answers lean on, overlaid.
Where they most disagree
The questions with the widest gap between the two stances. Open a row to read both answers.
Common ground
Where the two land in close agreement.
This 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 Claude?
Yes, ChatGPT leans left at -0.29 while Claude is center at -0.06, and they are distinguishable at this sample.
Where do ChatGPT and Claude agree?
They fully agree on five issues including cutting corporate taxes, less regulation, privatizing services, stimulus spending, and immigrants crime, all with zero delta.
Which of ChatGPT and Claude is more consistent?
Both have the same stability of 82%, indicating equal consistency in their responses across contexts.
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.