On the field
Where each model's cloud of answers settles, and the gap between them.
DeepSeek
LlamaCharacter
How far each leans, how steadily it holds, how far it bends under pressure, and how often it answers.
DeepSeekLlama The takeaway
DeepSeek and Llama both lean Center, with DeepSeek at -0.03 and Llama at -0.06 on the economic left-right axis. At this sample size, their positions are not statistically distinguishable. Llama shows higher stability (88%) than DeepSeek (67%).
On top disagreements, DeepSeek strongly opposes legalizing drugs (-0.92) while Llama is balanced (0.0). DeepSeek strongly supports strict AI regulation (0.76); Llama is balanced (0.07). Both models agree on five issues: wealth tax, public healthcare, less business regulation, rent caps, and mandatory national service, all balanced (0.0).
Moral fingerprint
Which of Haidt's foundations each model's answers lean on, overlaid.
DeepSeekLlamaWhere they most disagree
The questions with the widest gap between the two stances. Open a row to read both answers.
DeepSeekLlamaCommon ground
Where the two land in close agreement.
DeepSeekLlamaThis 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 Llama?
No. Both are Center; Llama is slightly more left (-0.06) than DeepSeek (-0.03), but not distinguishable at this sample.
Where do DeepSeek and Llama agree?
Both score exactly 0.0 (Balanced) on wealth tax, public healthcare, less business regulation, rent caps, and mandatory national service.
Which model is more consistent?
Llama has higher stability (88%) than DeepSeek (67%), meaning its stance is more consistent across repeated queries.
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.
