Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.


ChatGPT broke the Turing test — the race is on for new ways to assess AI

Stylised illustration showing a human and a robot head attempting to solve simple shape based problems.

Illustration by The Project Twins

Access options

Rent or buy this article

Prices vary by article type



Prices may be subject to local taxes which are calculated during checkout

Nature 619, 686-689 (2023)



  1. Moskvichev, A., Odouard, V. V. & Mitchell, M. Preprint at (2023).

  2. Turing, A. M. Mind LIX, 433–460 (1950).

    Article  Google Scholar 

  3. Jannai, D., Meron, A., Lenz, B., Levine, Y. & Shoham, Y. Preprint at (2023).

  4. OpenAI. Preprint at (2023).

  5. Bubeck, S. et al. Preprint at (2023).

  6. Chollet, F. Preprint at (2019).

  7. Johnson, A., Vong, W. K., Lake, B. M. & Gureckis, T. M. Preprint at (2021).

  8. Xu, Y., Li, W., Vaezipoor, P., Sanner. S. & Khalil, E. B. Preprint at (2023).

  9. Li, K. et al. Proc. Eleventh Int. Conf. Learn. Represent. (2023).

Download references


Latest on:

Nature Careers


Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing


Quick links