CoChat

Examining ChatGPT Performance on USMLE Sample Items and Implications for Assessment

Open access
Yaneva, Victoria, Baldwin, Peter, Jurich, Daniel P, Swygert, Kimberly, Clauser, Brian E · 2024 · Academic Medicine
Cited by 60

The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.

Abstract

Purpose: In late 2022 and early 2023, reports that ChatGPT could pass the United States Medical Licensing Examination (USMLE) generated considerable excitement, and media response suggested ChatGPT has credible medical knowledge. This report analyzes the extent to which an artificial intelligence (AI) agent’s performance on these sample items can generalize to performance on an actual USMLE examination and an illustration is given using ChatGPT. Method: As with earlier investigations, analyses were based on publicly available USMLE sample items. Each item was submitted to ChatGPT (version 3.5) 3 times to evaluate stability. Responses were scored following rules that match operational practice, and a preliminary analysis explored the characteristics of items that ChatGPT answered correctly. The study was conducted between February and March 2023. Results: For the full sample of items, ChatGPT scored above 60% correct except for one replication for Step 3. Response success varied across replications for 76 items (20%). There was a modest correspondence with item difficulty wherein ChatGPT was more likely to respond correctly to items found easier by examinees. ChatGPT performed significantly worse (P < .001) on items relating to practice-based learning. Conclusions: Achieving 60% accuracy is an approximate indicator of meeting the passing standard, requiring statistical adjustments for comparison. Hence, this assessment can only suggest consistency with the passing standards for Steps 1 and 2 Clinical Knowledge, with further limitations in extrapolating this inference to Step 3. These limitations are due to variances in item difficulty and exclusion of the simulation component of Step 3 from the evaluation—limitations that would apply to any AI system evaluated on the Step 3 sample items. It is crucial to note that responses from large language models exhibit notable variations when faced with repeated inquiries, underscoring the need for expert validation to ensure their utility as a learning tool.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1097/acm.0000000000005549

Cites

11 of 11 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 11 references

Cited by

See all 60

Metadata

Authors
Yaneva, V., Baldwin, P., Jurich, D. P., Swygert, K., & Clauser, B. E.
Venue
Academic Medicine
Published
2023-11-07
Volume
99
Issue
2
Pages
192-197
ISSN
  • 1040-2446 (ISSN-L)
  • 1938-808X
OpenAlex
W4388500499
Cited by
60
References
11
FWCI
2.08
Type
journal article
Language
en
Open access
hybrid

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Examining ChatGPT Performance on USMLE Sample Items and Implications for Assessment. https://app.cochat.ai/papers/10.1097/acm.0000000000005549
The paper
Yaneva, V., Baldwin, P., Jurich, D. P., Swygert, K., & Clauser, B. E. (2024). Examining ChatGPT Performance on USMLE Sample Items and Implications for Assessment. Academic Medicine. https://doi.org/10.1097/acm.0000000000005549

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.