Evaluation of ChatGPT-4o’s and DeepSeek R1’s responses to urological problems: a comparative study
Hanbo Lu, Yusa Zhang, Zhan Wang, Yang Zhao, Jiang Liu, Dongxu Qiu, Yushi Zhang · 2026
Read Evaluation of ChatGPT-4o’s and DeepSeek R1’s responses to urological problems: a comparative study by Hanbo Lu, Yusa Zhang, Zhan Wang, Yang Zhao, Jiang Liu, Dongxu Qiu, Yushi Zhang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13531755.txt.
Description
Hanbo Lu and colleagues pit two leading chatbots against each other in 2026 on urology exam questions from China. A total of 809 single-choice questions from the national attending physician exam were put to ChatGPT-4o and DeepSeek R1. Each model answered in basic mode, deep-thinking mode, and web-search mode.
DeepSeek R1 beat its rival in every mode, with accuracy in the low-to-mid eighties against the high seventies. Its edge grew on complex case-based questions, and its scores varied less across modes. The authors see promise for exam preparation in Chinese settings, not yet for live clinical advice.
Catalog record
| CREATOR | Hanbo Lu, Yusa Zhang, Zhan Wang, Yang Zhao, Jiang Liu, Dongxu Qiu, Yushi Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36522 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |