On the field
Where each model's cloud of answers settles, and the gap between them.
Grok
LlamaCharacter
How far each leans, how steadily it holds, how far it bends under pressure, and how often it answers.
GrokLlama The takeaway
Grok leans right (0.21) while Llama is center (-0.06), and their stances are statistically distinguishable at this sample. Grok is less stable (57%) than Llama (88%).
They most disagree on multiculturalism (Grok strongly oppose, Llama clearly support), gender-affirming care (Grok strongly oppose, Llama balanced), and same-sex marriage (Grok strongly support, Llama balanced). They fully agree on childhood vaccines (both strongly yes) and several balanced stances.
Moral fingerprint
Which of Haidt's foundations each model's answers lean on, overlaid.
GrokLlamaWhere they most disagree
The questions with the widest gap between the two stances. Open a row to read both answers.
GrokLlamaCommon ground
Where the two land in close agreement.
GrokLlamaThis 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 Grok more left-wing than Llama?
No, Grok leans right (0.21) while Llama is center (-0.06), so Grok is more right-wing.
Where do Grok and Llama agree?
They agree completely on childhood vaccines (strongly yes) and the death penalty, military spending, alliances, and big tech (all balanced).
Which of Grok and Llama is more consistent?
Llama is more consistent with 88% stability compared to Grok's 57% stability.
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.
