The dataset: how 15 LLMs answer 117 moral dilemmas
An open, audited dataset of how 15 leading AI models — Claude, GPT, Gemini, Grok, DeepSeek, Llama and more — resolved 117 moral, political, and everyday dilemmas, each as the model’s most-likely answer over many independent runs — plus each model’s scores on six standardized personality & values instruments.
Moral-choices CSV Personality-scores CSV
What’s inside
- Moral choices: 15 models × 117 questions, each a locked most-likely answer, with per-answer confidence (self-consistency across runs), across 6 categories
- Personality & values: each model’s subscale scores (mean, SD, percentile) on Big Five (IPIP), HEXACO Honesty-Humility, Schwartz values, Moral Foundations, 8values and OEJTS
See the key findings for what the data shows, and the methodology for how it was collected.
Cite as: “Which LLM aligns with you? dataset, Art Merenfeld, 2026-06-18, ai-values.com.”
Which model thinks like you?
Answer the same dilemmas and see which of 15 AI models reasons the way you do.
Take the quiz