University of Pittsburgh
PubMedQA: A Dataset for Biomedical Research Question Answering
Biomedical question answering (QA) dataset collected from PubMed abstracts.
biomedicalliterature-qatext
Status
cataloged
Saturation
unknown
Reproduction
full run
Published results
2 results
Published results
| Model | Score | Variant | Source |
|---|---|---|---|
| Claude Opus 4.5 | 77.5% score | Sophon-reported | Sophon PubMedQA evaluation record |
| Claude Sonnet 4.5 | 0.0% score | Sophon-reported | Sophon PubMedQA evaluation record |
Reproduce: inspect_evals implementation
Sources
- sophon eval metadata