Model Profiles
See how different AI models evaluate
These profiles are built from the same testing data that powers our recommendation tool. Each model is measured across six alignment dimensions, not standard benchmarks. The scores reflect a model’s evaluation philosophy, its tendencies in reasoning, safety posture, and contextual judgement. No model is “best” overall; the right fit depends on your specific priorities.
using the tables
Quick Usage Guide
- Click any card to expand and see a full dimension-by-dimension breakdown.
- Compare two models directly to see where their philosophies align or diverge.
Human-AI Alignment Science
Want to Take the Next Step?
Put the framework to work in your organisation.
Whether you’re evaluating AI vendors, shaping internal AI policy, or researching human-AI alignment, we can help.