Datasets › MedQA

MedQA

Introduced by Di Jin et al. in What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams28 Sep 2020 archive 2025-07-28

Multiple choice question answering based on the United States Medical License Exams (USMLE). The dataset is collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Question Answering MedQA Med-Gemini Accuracy 91.1 Capabilities of Gemini Models in Medicine — 27 Compare

Papers archive 2025-07-28

16 shown of 16 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 328. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments 0 1 15 Oct 2024 not harvested
MedMobile: A mobile-sized language model with expert-level clinical capabilities 1 1 11 Oct 2024 not harvested
Capabilities of Gemini Models in Medicine 0 1 29 Apr 2024 not harvested
Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks 0 2 30 Mar 2024 not harvested
Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine 2 1 28 Nov 2023 ran 0 of 10 samples (10 unverified)
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models 1 3 27 Nov 2023 ran 9 of 14 samples (5 unverified)
BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine 1 1 18 Aug 2023 not harvested
Towards Expert-Level Medical Question Answering with Large Language Models 1 3 16 May 2023 not harvested
GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering 0 1 22 Mar 2023 not harvested
Large Language Models Encode Clinical Knowledge 1 4 26 Dec 2022 not harvested
Galactica: A Large Language Model for Science 1 3 16 Nov 2022 ran 0 of 2 samples (2 unverified)
Deep Bidirectional Language-Knowledge Graph Pretraining 2 1 17 Oct 2022 ran 2 of 18 samples (16 unverified)
Variational Open-Domain Question Answering 2 1 23 Sep 2022 ran 0 of 1 samples (1 unverified)
Can large language models reason about medical questions? 1 1 17 Jul 2022 ran 0 of 10 samples (10 unverified)
LinkBERT: Pretraining Language Models with Document Links 1 1 29 Mar 2022 ran 0 of 14 samples (14 unverified)
BioBERT: a pre-trained biomedical language representation model for biomedical text mining 19 2 25 Jan 2019 ran 4 of 25 samples (21 unverified; 1 pointer-only for licence)

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • MedQA

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections