Performance of ChatGPT Across Different Versions in Medical Licensing Examinations Worldwide: Systematic Review and Meta-Analysis
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Background: Over the past 2 years, researchers have used various medical licensing examinations to test whether ChatGPT (OpenAI) possesses accurate medical knowledge. The performance of each version of ChatGPT on the medical licensing examination in multiple environments showed remarkable differences. At this stage, there is still a lack of a comprehensive understanding of the variability in ChatGPT’s performance on different medical licensing examinations. Objective: In this study, we reviewed all studies on ChatGPT performance in medical licensing examinations up to March 2024. This review aims to contribute to the evolving discourse on artificial intelligence (AI) in medical education by providing a comprehensive analysis of the performance of ChatGPT in various environments. The insights gained from this systematic review will guide educators, policymakers, and technical experts to effectively and judiciously use AI in medical education. Methods: We searched the literature published between January 1, 2022, and March 29, 2024, by searching query strings in Web of Science, PubMed, and Scopus. Two authors screened the literature according to the inclusion and exclusion criteria, extracted data, and independently assessed the quality of the literature concerning Quality Assessment of Diagnostic Accuracy Studies-2. We conducted both qualitative and quantitative analyses. Results: A total of 45 studies on the performance of different versions of ChatGPT in medical licensing examinations were included in this study. GPT-4 achieved an overall accuracy rate of 81% (95% CI 78-84; P<.01), significantly surpassing the 58% (95% CI 53-63; P<.01) accuracy rate of GPT-3.5. GPT-4 passed the medical examinations in 26 of 29 cases, outperforming the average scores of medical students in 13 of 17 cases. Translating the examination questions into English improved GPT-3.5’s performance but did not affect GPT-4. GPT-3.5 showed no difference in performance between examinations from English-speaking and non–English-speaking countries (P=.72), but GPT-4 performed better on examinations from English-speaking countries significantly (P=.02). Any type of prompt could significantly improve GPT-3.5’s (P=.03) and GPT-4’s (P<.01) performance. GPT-3.5 performed better on short-text questions than on long-text questions. The difficulty of the questions affected the performance of GPT-3.5 and GPT-4. In image-based multiple-choice questions (MCQs), ChatGPT’s accuracy rate ranges from 13.1% to 100%. ChatGPT performed significantly worse on open-ended questions than on MCQs. Conclusions: GPT-4 demonstrates considerable potential for future use in medical education. However, due to its insufficient accuracy, inconsistent performance, and the challenges posed by differing medical policies and knowledge across countries, GPT-4 is not yet suitable for use in medical education. Trial Registration: PROSPERO CRD42024506687; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=506687
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Rayyan-a web and mobile app for systematic reviews.
Ouzzani, M., Hammady, H., Fedorowicz, Z., & Elmagarmid, A. (2016) · Systematic Reviews · doi:10.1186/s13643-016-0384-4 · Cited by 26,092
QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies
Whiting, P. F., Rutjes, A. W. S., Westwood, M. E., Mallett, S., Deeks, J. J., Reitsma, J. B., Leeflang, M. M. G., Sterne, J. A. C., Bossuyt, P. M. M., & the QUADAS-2 Group* (2011) · Annals of Internal Medicine · doi:10.7326/0003-4819-155-8-201110180-00009 · Cited by 14,199
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115 · cited 2×
“Regarding the accuracy of ChatGPT on MCQs, while 2 previous studies conducted meta-analyses that yielded accuracy rates of 61% and 56%, respectively, we noted that these accuracy rates reflected the performance of all versions of ChatGPT without differentiation by version [54,56].”
Kung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
McInnes, M. D. F., Moher, D., Thombs, B. D., McGrath, T. A., Bossuyt, P. M., and the PRISMA-DTA Group, Clifford, T., Cohen, J. F., Deeks, J. J., Gatsonis, C., et al. (2018) · JAMA · doi:10.1001/jama.2017.19163 · Cited by 3,210
Gilson, A., Safranek, C. W., Huang, T., Socrates, V., Chi, L., Taylor, R. A., & Chartash, D. (2023) · JMIR Medical Education · doi:10.2196/45312 · Cited by 2,078
ChatGPT for Education and Research: Opportunities, Threats, and Strategies
Rahman, M. M., & Watanobe, Y. (2023) · Applied Sciences · doi:10.3390/app13095783 · Cited by 1,080
Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions
Abd-alrazaq, A., AlSaad, R., Alhuwail, D., Ahmed, A., Healy, P. M., Latifi, S., Aziz, S., Damseh, R., Alabed Alrazak, S., & Sheikh, J. (2023) · JMIR Medical Education · doi:10.2196/48291 · Cited by 722
The rise of ChatGPT : Exploring its potential in medical education
Lee, H. (2024) · Anatomical Sciences Education · doi:10.1002/ase.2270 · Cited by 596 · cited 1×
“Second, in medical licensing examinations comprising multiple-choice questions (MCQs), ChatGPT can act as an “AI teaching assistant,” providing insights for each question, analyzing common errors, and reinforcing concepts interactively [12].”
Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health
Tian, S., Jin, Q., Yeganova, L., Lai, P.-T., Zhu, Q., Chen, X., Yang, Y., Chen, Q., Kim, W., Comeau, D. C., et al. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad493 · Cited by 359
Performance of GPT-3.5 and GPT-4 on the Japanese Medical Licensing Examination: Comparison Study
Takagi, S., Watari, T., Erabi, A., & Sakaguchi, K. (2023) · JMIR Medical Education · doi:10.2196/48002 · Cited by 271 · cited 5×
“5 performed worse on difficult questions than easier ones [21,23,30,33,41,44,49].”
InfluentialThe Potential and Concerns of Using AI in Scientific Research: ChatGPT Performance Evaluation
Khlaif, Z. N., Mousa, A., Hattab, M. K., Itmazi, J., Hassan, A. A., Sanmugam, M., & Ayyoub, A. (2023) · JMIR Medical Education · doi:10.2196/47049 · Cited by 205 · cited 1×
“ChatGPT has been extensively applied across various domains, including programming, education, business, and law, with notable success in each [2-5].”
Zong, H., Li, J., Wu, E., Wu, R., Lu, J., & Shen, B. (2024) · BMC Medical Education · doi:10.1186/s12909-024-05125-7 · Cited by 114
Meyer, A., Riese, J., & Streichert, T. (2024) · JMIR Medical Education · doi:10.2196/50965 · Cited by 110 · cited 1×
“5 [33,36,41,44,47], it did not pass the Japanese medical licensing examination [49].”
ChatGPT failed Taiwan’s Family Medicine Board Exam
Weng, T.-L., Wang, Y.-M., Chang, S., Chen, T.-J., & Hwang, S.-J. (2023) · Journal of the Chinese Medical Association · doi:10.1097/jcma.0000000000000946 · Cited by 100
Roos, J., Kasapovic, A., Jansen, T., & Kaczmarczyk, R. (2023) · JMIR Medical Education · doi:10.2196/46482 · Cited by 98 · cited 1×
“However, the fatal issue with ChatGPT is that, owing to the nature of AI language models, it can provide detailed and logically sound explanations for incorrect answers [24,40,44].”
Guillen-Grima, F., Guillen-Aguinaga, S., Guillen-Aguinaga, L., Alas-Brun, R., Onambele, L., Ortega, W., Montejo, R., Aguinaga-Ontoso, E., Barach, P., & Aguinaga-Ontoso, I. (2023) · Clinics and Practice · doi:10.3390/clinpract13060130 · Cited by 72
Evaluating the performance of ChatGPT-4 on the United Kingdom Medical Licensing Assessment
Lai, U. H., Wu, K. S., Hsu, T.-Y., & Kan, J. K. C. (2023) · Frontiers in Medicine · doi:10.3389/fmed.2023.1240915 · Cited by 67
Sumbal, A., Sumbal, R., & Amir, A. (2024) · Journal of Medical Education and Curricular Development · doi:10.1177/23821205241238641 · Cited by 63 · cited 1×
“5 in various medical licensing examinations worldwide [59].”
Leveraging generative AI for clinical evidence synthesis needs to ensure trustworthiness
Zhang, G., Jin, Q., Jered McInerney, D., Chen, Y., Wang, F., Cole, C. L., Yang, Q., Wang, Y., Malin, B. A., Peleg, M., et al. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104640 · Cited by 40
Cited by
Liu, M., Okuhara, T., Dai, Z., Huang, W., Gu, L., Okada, H., Furukawa, E., & Kiuchi, T. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105673 · Cited by 73
Self-citationChen, Y., Huang, X., Yang, F., Lin, H., Lin, H., Zheng, Z., Liang, Q., Zhang, J., & Li, X. (2024) · BMC Medical Education · doi:10.1186/s12909-024-06309-x · Cited by 50
The Impact of ChatGPT on Students' Academic Achievement: A Meta‐Analysis
Liu, Z., Zuo, H., & Lu, Y. (2025) · Journal of Computer Assisted Learning · doi:10.1111/jcal.70096 · Cited by 44
Huang, S., Wen, C., Bai, X., Li, S., Wang, S., Wang, X., & Yang, D. (2025) · Journal of Medical Internet Research · doi:10.2196/68538 · Cited by 33
“In addition, ChatGPT provides real-time feedback and answers to student queries, thereby enhancing the efficiency of the learning process [34].”
Lin, Y., Luo, Z., Ye, Z., Zhong, N., Zhao, L., Zhang, L., Li, X., Chen, Z., & Chen, Y. (2025) · JMIR Medical Education · doi:10.2196/71125 · Cited by 58
“GPT-4 scored 86% (95% CI 82% ‐ 89%; P <0.01) in English-speaking countries versus 80% (95% CI 76% ‐ 83%; P <.01) in non-English-speaking countries ( P =.02), demonstrating the adaptability issues of GAI models across different linguistic and regional contexts [116].”
Influential
Metadata
- Authors
- Liu, M., Okuhara, T., Chang, X., Shirabe, R., Nishiie, Y., Okada, H., & Kiuchi, T.
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2024-07-25
- Volume
- 26
- Pages
- e60807
- ISSN
- 1438-8871 (ISSN-L)
- OpenAlex
- W4399701665
- Cited by
- 217
- References
- 20
- FWCI
- 6.33
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.