ArticleCureus2025
Investigation of Studies on ChatGPT's Ability to Answer Anatomy Questions: A Self-Evaluation by ChatGPT and Comparison with an Evaluation by Gemini.
Article in Cureus, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
- Performance of Seven Large Language Models on Anatomy Examination Questions.Clinical anatomy (New York, N.Y.) · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
introductionThere is controversy about ChatGPT's (OpenAI, San Francisco, CA) potential to answer anatomy questions and play a significant role in anatomy education. We aimed to assess ChatGPT's ability to locate and summarize literature about its performance in answering anatomy questions. We also aimed to explore Gemini's (Google, Mountain View, CA) ability to perform this task.
methodsWe asked ChatGPT and Gemini to list and summarize five studies: 1) about ChatGPT's ability to answer anatomy questions, 2) comparing ChatGPT with another artificial intelligence (AI) tool in terms of answering anatomy questions, and 3) showing that ChatGPT answered anatomy questions with success lower than 70%. For each query, we measured how many studies were 1) correctly identified and 2) accurately summarized, and we assessed the presence of any bias.
resultsChatGPT performed excellently in the first query (100%/100%), poorly in the second (20%/20%), and moderately in the third query (60%/40%). It conducted a strict self-evaluation and did not hallucinate. Gemini's performance was 100%/40%, 60%/40%, and 80%/60% in the three queries, respectively. It was inflexible in finding a variety of publications, while it often hallucinated and exhibited bias against ChatGPT.
conclusionsChatGPT and Gemini generated reliable responses only when they were simply asked to detect studies about ChatGPT's ability to answer anatomy questions. They particularly struggled to locate and outline comparative studies. While Gemini performed generally better, it hallucinated and exhibited bias against ChatGPT. Ongoing evolution may enhance ChatGPT and Gemini's potential to contribute to anatomical research.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.