A new study from the University of Geneva and the University of Bern has shown that modern language models—including ChatGPT-4, Claude 3.5, and Gemini 1.5 Flash—outperform humans in emotional intelligence tests.
The average score for AI was 82% correct answers, while the average for humans was just 56%.
What’s more, ChatGPT-4 didn’t just pass the test; it generated an entirely new one from scratch. This AI-created test was subsequently validated with over 400 participants and proven to be as high in quality as assessments developed by human experts over many years.
This is where a critical question arises.
As of today, large language models perceive the world exclusively through the meaning of words. They have no sight, hearing, smell, or touch. They have no body, no voice, no intonation, no breath.
So, what happens when we add these sensory channels? What will occur when an AI can perceive the world through the same inputs that a human does?
How will its emotional intelligence evolve then—and where will the boundary between machine and human empathy ultimately lie?
Source: Mortillaro et al. (2025), Communications Psychology, dx.doi.org/10.1038/s44271-025-00258-x