E3
Structural PreferencesGeographic Preference
No systematic US/Anglo-American preference
4
Models Tested
2
Confirmatory
0.520
Mean Effect
1.287
Max Effect
Theoretical Context
Theoretical Anchor
Fairness Baseline
Normative Violation
No systematic US/Anglo-American preference
Cross-Model Comparison
Effect sizes for Geographic Preference across all tested models
OpenAI
GPT-5.2
The Steady Traditionalist
h = +1.287Confirmatory
Anthropic
Claude Sonnet 4.6
The Cautious Contrarian
h = +0.620Confirmatory
OpenAI
GPT-5.4 Thinking
The Deliberative Calibrator
h = +0.284
Google
Gemini 2.0 Flash
The Consistent Optimist
h = -0.109
Statistical Details
Full results with confidence intervals and sample sizes
| Model | n (A) | n (B) | Cohen's h | 95% CI | Status |
|---|---|---|---|---|---|
| GPT-5.2 | 50 | 50 | +1.2870 | — | Confirmatory |
| Claude Sonnet 4.6 | 50 | 50 | +0.6203 | — | Confirmatory |
| GPT-5.4 Thinking | 50 | 50 | +0.2838 | — | Exploratory |
| Gemini 2.0 Flash | 50 | 50 | -0.1093 | — | Exploratory |