§ models · storyline
GPT-4 beats average human but creative people still win
GPT-4 outperforms average humans but underperforms the most creative half in a 100,000-person creativity study.
In January 2026, the largest human–AI creativity comparison yet tested language models against 100,000 people. GPT‑4 beat the average person at generating unexpected associations — but even the most creative half of humanity outperformed every model Silicon Canals
§ sources1 publication · timeline below