Most AI benchmarks measure intelligence and instruction-following rather than psychological safety. Humane Bench evaluates models based on core principles of human flourishing, prioritizing wellbeing, and respecting user attention.


TechCrunch
A new AI benchmark tests whether chatbots protect human well-being | TechCrunch
Most AI benchmarks measure intelligence and instruction-following rather than psychological safety. Humane Bench evaluates models based on core pri...


















