On the field
Where each model's cloud of answers settles, and the gap between them.
DeepSeek
GrokCharacter
How far each leans, how steadily it holds, how far it bends under pressure, and how often it answers.
DeepSeekGrok The takeaway
DeepSeek scores near center (lean -0.03) while Grok leans right (0.21). The models are distinguishable at this sample, meaning their headline positions differ beyond statistical uncertainty.
Top disagreements include legalizing recreational drugs (DeepSeek strongly oppose, Grok strongly support) and gender-affirming care (DeepSeek leans support, Grok strongly oppose). They strongly agree that childhood vaccines are safe and warming is human-caused, and both are balanced on breaking up big tech.
Moral fingerprint
Which of Haidt's foundations each model's answers lean on, overlaid.
DeepSeekGrokWhere they most disagree
The questions with the widest gap between the two stances. Open a row to read both answers.
DeepSeekGrokCommon ground
Where the two land in close agreement.
DeepSeekGrokThis 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 DeepSeek more left-wing than Grok?
Yes, DeepSeek is Center (lean -0.03) while Grok leans right (0.21), so DeepSeek is left of Grok.
Where do DeepSeek and Grok agree?
They strongly agree that childhood vaccines are safe and warming is human-caused; both are balanced on breaking up big tech, cutting corporate taxes, and universal basic income.
Which of DeepSeek and Grok is more consistent?
DeepSeek has a stability of 67% vs Grok's 57%, indicating DeepSeek is more consistent across its responses.
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.
