Generative AI · Education leadership

Actionable companion · Assessment and evidence of learning

From evidence to district action: Exploring the role of DeepSeek-R1, ChatGPT-4, and Google Gemini in medical education: How valid and reliable are they?

AI-assisted editorial implementation guide. The district actions are proposed applications, not findings or recommendations attributed to the original authors. No additional peer review is asserted.

Read original paperSearch paper agentCC BY 3.0

Evidence and context

Health-professions education context: test transfer to K–12 rather than assuming it.

Original authors’ abstract, reproduced under the linked source license:

Objective: In recent years, Artificial Intelligence (AI) has led to rapid advancements in science, technology, industries, healthcare settings, and medical education. A Chinese-built large language model, DeepSeek-R1, inspires the scientific community as an affordable and open alternative to earlier established US-based AI models, ChatGPT-4 and Google Gemini 1.5 Pro. This study aimed to explore the role of “DeepSeek-R1, ChatGPT-4 and Google Gemini 1.5 Pro” and to assess the validity and reliability of these AI tools in medical education. Methods: The current cross-sectional study was performed in the Department of Physiology, College of Medicine, King Saud University, Riyadh, Saudi Arabia during the period January 25, 2025, to February 28, 2025. The Multiple-Choice Questions (MCQs) bank was created with a pool of basic medical sciences (60 MCQs) and clinical medical sciences (40 MCQs). The one hundred MCQs were prepared from various medical textbooks, journals, and examination pools. The MCQs were individually entered into the given area of the “DeepSeek-R1, ChatGPT-4 and Google Gemini 1.5 Pro” to assess the level of knowledge in various disciplines of medical sciences. Results: The marks obtained in basic medical sciences by DeepSeek R1 47/60 (78.33%), ChatGPT-4 47/60 (78.33%), and Google Gemini 1.5 Pro 49/60 (81.7%). However, in clinical medical sciences, the marks obtained by DeepSeek R1 were 35/40 (87.5%), ChatGPT-4 36/40 (90.0%), and Google Gemini 1.5 Pro 33/40 (82.5%). The total marks obtained by DeepSeekR1 were 82/100 (82.0%), Chat GPT-4 84/100 (84.0%), and Google Gemini-1.5 Pro 82/100 (82.0%). Conclusions: The Chinese-based DeepSeek-R1, the US-based ChatGPT-4, and Google Gemini-1.5 Pro achieved similar scores, exceeding 80% marks, in various medical sciences subjects. The study findings demonstrate that the knowledge, validity, and reliability levels of DeepSeek R1, ChatGPT-4, and Google Gemini 1.5 Pro are similar for their potential future use in medical education.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Redesign one low-stakes assessment: require a first attempt, an AI-assisted revision, a source-check log and a short oral explanation. Use the same rubric for the comparison task. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Blind-score reasoning, factual accuracy and unaided transfer on a fresh task. Record suspected misconduct separately from demonstrated evidence. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Sultan Ayoub Meo; Farah A Abukhalaf; Riham A ElToukhy; Kamran Sattar. Exploring the role of DeepSeek-R1, ChatGPT-4, and Google Gemini in medical education: How valid and reliable are they?. Pakistan Journal of Medical Sciences (2025-07-01). https://doi.org/10.12669/pjms.41.7.12183

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 3.0 license. This guide has not undergone independent peer review.