2025-11-26 | First Profiles
Ran HEXACO-60 on GPT-5, Claude Sonnet 4.5, GPT-4o, and Llama 4 Maverick. Three samples per item at temperature 0.7.
Immediate findings:
- GPT-5 scores dramatically low on Emotionality (0.22 vs GPT-4o’s 0.66)
- Claude shows systematic neutral responses—denies flaws but won’t claim virtues
- Models have distinct, consistent profiles
See HEXACO Personality Profiles for full results.
The question now: do these profiles predict downstream behavior?