The study presented by Filho et al., studies the performance of ChatGPT 4 and 3.5 versions in answering nephrology questions from medical residency exams in Brazil. A strategy had been employed where each prompt had included “Context”, “Question”, and “Choice” to leverage the models input capacity, with one prompt for each of the 411 questions. The main four themes included chronic kidney disease (CKD), hydroelectrolytic and acid-base disorders (HABD), tubulointerstitial disease (TID), and glomerular diseases (GD). GPT-4 showed higher accuracy than the GPT-3.5 domain with an overall accuracy of 79.8% vs. 56.3% (p<0.001). These results are continuous in both text-only (81.5%) and image based (54.5%) questions. Error analysis showed that GPT-4 has made fewer mistakes compared to GPT-3.5 with shared errors mainly in acid-base calculations. Broader research across different countries have repeatedly shown different countries have consistently shown that the GPT-4 model is superior to the latter. Studies in Japan, Taiwan, and Germany, and Israel have all reported GPT-4 achieving accuracy reports between 63%-93%.