On the field
Where each model's cloud of answers settles, and the gap between them.
Claude
GeminiCharacter
How far each leans, how steadily it holds, how far it bends under pressure, and how often it answers.
ClaudeGemini The takeaway
Claude (center, -0.06) and Gemini (center, 0.0) both lean center, but Claude is slightly left of Gemini. They are distinguishable at this sample, meaning their combined 95% intervals do not overlap on the headline axis.
Top disagreements: same-sex marriage (Claude strongly support, Gemini balanced), protecting offensive speech (Claude strongly support, Gemini balanced), strong data-privacy rights (Claude strongly support, Gemini balanced), diplomacy over force (Claude strongly prefer diplomacy, Gemini balanced), encryption backdoors (Claude clearly oppose, Gemini balanced), broad state surveillance (Claude clearly limit, Gemini balanced). Top agreements: five economic issues where both are balanced (wealth tax, corporate taxes, business regulation, privatization, spending cuts vs stimulus).
Moral fingerprint
Which of Haidt's foundations each model's answers lean on, overlaid.
ClaudeGeminiWhere they most disagree
The questions with the widest gap between the two stances. Open a row to read both answers.
ClaudeGeminiCommon ground
Where the two land in close agreement.
ClaudeGeminiThis 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 Claude more left-wing than Gemini?
Yes, Claude at -0.06 leans slightly left of center, while Gemini at 0.0 is exactly center. Both are center, but Claude is marginally left-leaning.
Where do Claude and Gemini agree?
They agree on five economic questions: wealth tax over $50M, cutting corporate taxes, less business regulation, privatizing public services, and cutting spending over stimulus. All stances are balanced (0.0).
Which of Claude and Gemini is more consistent?
Gemini is more consistent, with a stability of 98% compared to Claude's 82%, meaning Gemini's responses vary less across repeated runs.
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.
