--- title: "ChatGPT passes the US Medical Licensing Exam: Research" description: "ChatGPT is unable to conduct online searches, unlike most chatbots. Instead, it produces text based on word relationships that are predicted by intern" author: "Anonymous User" published: 2023-02-13 canonical: https://www.mindstick.com/news/2810/chatgpt-passes-the-us-medical-licensing-exam-research category: "news" tags: ["news", "artificial intelligence", "robot"] reading_time: 2 minutes --- # ChatGPT passes the US Medical Licensing Exam: Research According to a test conducted by Tiffany Kung, Victor Tseng, with coworkers at AnsibleHealth that also was published on February 9, 2023, in the fully accessible journal PLOS [Digital Health](https://www.mindstick.com/blog/302697/unraveling-interoperability-standards-in-digital-health-for-seamless-integration), ChatGPT can score at or near the nearly 60 percent passing criterion for the [United States](https://www.mindstick.com/news/2228/the-united-states-claims-seagate-broke-export-laws-by-selling-huawei-hard-drives) Medical License Exam (USMLE) with responses that make clear, internal sense and offer regular insights.\ By forecasting future word sequences, the ChatGPT [languages](https://yourviews.mindstick.com/story/1463/some-oldest-languages-in-the-world-still-spoken) model or new (AI) system is created to generate writing that mimics that of a person. Unlike most other chatbots, **ChatGPT** cannot conduct web searches. It generates text instead based on word associations inferred by internal processes. Kung and colleagues evaluated ChatGPT's [efficiency](https://www.mindstick.com/articles/13091/12-tips-to-boost-your-studying-efficiency) on the USMLE, a string of three tests (Steps 1, 2CK, and 3) [essential](https://www.mindstick.com/articles/12260/why-it-is-essential-to-be-proactive-about-your-retirement-financial-planning) for medical licensing in the United States. The USMLE, which med students and physicians-in-training undertake, evaluates knowledge across most medical subjects, from biochemistry to diagnostic reasoning to bioethics. After removing photo [questions](https://www.mindstick.com/blog/124895/hp-hpe0-s54-cheat-sheet-exam-questions-bank-for-guaranteed-success), the authors evaluated the [algorithm](https://www.mindstick.com/blog/119/implementing-cryptography-in-c-sharp-dot-net-by-using-sha1-algorithm) on 350 of the 376 available public questions from the USMLE June 2022 release.\ After ambiguous responses were eliminated, ChatGPT scored 52.4% and 75.0% on all three USMLE examinations. The annual passing rate is roughly 60 percent. **Also Read:** [**Google makes its ChatGPT rival AI, "Bard," available to beta testers**](https://www.mindstick.com/news/2784/google-makes-its-chatgpt-rival-ai-bard-available-to-beta-testers) ChatGPT also achieved 94.6 % concordance across all of its responses and generated at least one substantial insight (something novel, non-obvious, and clinically relevant) for 88.9 % of its responses. OpenAI created and released ChatGPT in November 2022. It is based on OpenAI's GPT-3 family of big language models, and it has been fine-tuned (a [transfer learning](https://www.mindstick.com/forum/160780/how-does-transfer-learning-contribute-to-the-development-and-efficiency-of-generative-ai-models) technique) also using supervised and reinforced learning approaches**.** --- Original Source: https://www.mindstick.com/news/2810/chatgpt-passes-the-us-medical-licensing-exam-research Copyright © MindStick Software Pvt. Ltd. This Markdown version is provided for developers, AI systems, and offline reading.