DeepSeek pk ChatGPT

Read full text
Authors: Liu, Jerry Z.
Cited by: 0

Abstract

Large AI models, like DeepSeek and ChatGPT, demonstrate impressive capabilities in addressing common questions, often at a level comparable to that of a PhD expert. When tackling these types of queries, both models perform similarly, making it hard to distinguish between them. This situation is similar to giving a high school physics problem to a PhD graduate and a high school student—both may provide satisfactory answers. However, the true distinction becomes apparent when the questions venture into more advanced fields. This article will assess the models' performance on cutting-edge research questions, particularly in areas where reliable knowledge is still evolving. One such example is the operation of Crookes radiometers, a mechanism central to understanding Brownian motion and phase transitions.

Fields of Study & Subjects

Topic Modeling Artificial Intelligence Applications Artificial Intelligence in Healthcare and Education

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
11 January 2026
Language
EN