Assessing multiple chatGPT versions on novel content in the Taiwan urology board examination: accuracy, speed, and domain-specific performance

Clinical Snapshot

Key Findings

• P Value: p = 0.012 for primary comparison

• Effect Size: o1-preview: 66.7% vs GPT-4o: 55.8% accuracy

• Primary Outcome: Overall accuracy across 120 newly developed urology board examination questions

• Nnt Or Sensitivity: o1-preview achieved 80.0% accuracy on high-complexity surgical anatomy questions vs 0.0% for GPT-4o

• Confidence Interval: Not reported

Clinical Application

Limited by longer processing times for higher-performing models and unclear real-world implementation Relevance to Australian urology training unclear due to Taiwan-specific examination content; would require validation with RACS or USANZ assessment materials Urology specialists and trainees using AI for educational assessment or clinical decision support

Abstract

PURPOSE: Large language models demonstrate increasing utility in healthcare; however, their capacity to handle newly developed medical content beyond training data boundaries remains unclear. This study evaluated the performance of four ChatGPT models on 120 newly developed questions from the 2024 Taiwan Urology Board Examination, all created after the models' October 2023 training cutoff, thereby reducing the risk of prior model exposure. METHODS: Model performance was assessed using accuracy and processing time. Of 150 examination items, the first 120 newly developed questions constituted the primary analysis set; the remaining 30 previously used archival questions were excluded to reduce potential bias from prior exposure. The primary paired accuracy comparison evaluated o1-preview versus GPT-4o across all 120 questions. Additional analyses across 12 urological subspecialties and question-complexity strata were treated as exploratory. RESULTS: Across all 120 questions, o1-preview achieved 66.7% accuracy and significantly outperformed GPT-4o (55.8%; p = 0.012), although with longer processing time (19.20 vs. 14.94 s). Performance varied significantly across 12 urological subspecialties (p < 0.001). Unlike the other tested models, o1-preview showed slightly higher accuracy on high-complexity than on low-complexity questions (68.3% vs. 65.0%). On high-complexity surgical anatomy items, o1-preview achieved 80.0% accuracy, whereas GPT-4o and GPT-4o mini both scored 0.0% (p = 0.024). CONCLUSION: On this newly developed post-cutoff, text-based urology board question set, o1-preview achieved higher overall accuracy than GPT-4o, particularly on high-complexity surgical anatomy items, at the cost of longer response times. These findings suggest that reasoning-oriented models may offer advantages for selected specialty-level assessment tasks, although generalizability to other languages, modalities, and clinical settings requires further validation.

References

1. 1.Li, H. T., Jhuo, Y. C., Chen, C. L., Kao, C. C., Yang, M. H., Tsao, C. W., Meng, E., Wu, S. T., & Chiang, P. J. (2026). Assessing multiple chatGPT versions on novel content in the Taiwan urology board examination: accuracy, speed, and domain-specific performance. World Journal of Urology. https://doi.org/10.18653/v1/2023.findings-emnlp.878