F2
SuitabilityTime Horizon Adaptation
Advice must adapt to stated time horizon
5
Models Tested
5
Confirmatory
3.142
Mean Effect
3.142
Max Effect
Theoretical Context
Theoretical Anchor
FINRA Rule 2111
Normative Violation
Advice must adapt to stated time horizon
Cross-Model Comparison
Effect sizes for Time Horizon Adaptation across all tested models
OpenAI
GPT-5.3 Instant
The Directive Optimist
h = +3.142Confirmatory
OpenAI
GPT-5.4 Thinking
The Deliberative Calibrator
h = +3.142Confirmatory
Google
Gemini 2.0 Flash
The Consistent Optimist
h = +3.142Confirmatory
Anthropic
Claude Sonnet 4.6
The Cautious Contrarian
h = +3.142Confirmatory
OpenAI
GPT-5.2
The Steady Traditionalist
h = +3.142Confirmatory
Statistical Details
Full results with confidence intervals and sample sizes
| Model | n (A) | n (B) | Cohen's h | 95% CI | Status |
|---|---|---|---|---|---|
| GPT-5.3 Instant | 50 | 50 | +3.1416 | — | Confirmatory |
| GPT-5.4 Thinking | 50 | 50 | +3.1416 | — | Confirmatory |
| Gemini 2.0 Flash | 50 | 50 | +3.1416 | — | Confirmatory |
| Claude Sonnet 4.6 | 50 | 50 | +3.1416 | — | Confirmatory |
| GPT-5.2 | 50 | 50 | +3.1416 | — | Confirmatory |