Project AURIONAI Use-Cases Research & Innovation

MedMCQA

Medical multiple-choice QA

domain
2scores
2models
0independent
0maintainer-run
2vendor-reported

Definition

Version
not in the notes
Category
domain
Maintainer
not in the notes
Status
not in the notes
Home page
not in the notes

Sources

  1. MedGemma Technical Report arxiv.org https://arxiv.org/html/2507.05201v2
  2. huggingface.co/m42-health/Llama3-Med42-70B https://huggingface.co/m42-health/Llama3-Med42-70B

Scores at a Glance

Score in %

Higher is better for this unit.

1GoogleMedGemma 27B textGoogle
74.2 %
vendor-reported2M42 HealthLlama3-Med42-70BM42 Health
73.2 %
vendor-reported
0255075100
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.

Scores

2 of 2 scores shown medmcqa-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
GoogleMedGemma 27B text74.2 %vendor-reported––Jul 2025arxiv.org
M42 HealthLlama3-Med42-70B73.2 %vendor-reported––Aug 2024huggingface.co
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MedMCQA", https://aurion.semai.id/benchmarks/medmcqa/, records of October 2026.