PubMedQA: leaderboard
Biomedical research question-answering benchmark requiring yes/no/maybe answers from PubMed abstracts with expert-labeled and generated splits.
Metric: Accuracy (%). Source: github.com. Source: pubmedqa.github.io. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 | 82 | #438 |
| 2 | GPT-3.5 | 79.6 | #818 |
| 3 | Median Expert | 78 |
Interactive version: theaggregate.ai/benchmark?slug=pubmedqa · How It Works · Data refreshed daily, snapshot 2026-10-20.