← Back to archive

GPT-4.5 passes the Turing test in new study

That's it! GPT-4.5 passed the Turing test. In the classic three-party Turing test setup, GPT-4.5 was judged to be more human than actual humans in 73% of cases across two populations. Meanwhile, LLaMa 3.1, when given a persona prompt, also performed well with a 56% win rate, but did not significantly outperform humans. Without a persona prompt, both GPT-4.5 and the LLaMa models performed significantly worse, with win rates of around 36–38%.

GPT-4.5 passes the Turing test in new study

Originally posted on X

PS: I'm pretty active on 𝕏 if you'd like to follow along

Archive

2026

2025

2024

2018