List your company

Explanation Quality Evaluation on PubMedQA (test)

39.7Reasoning Soundness LossPubMed Reasoner
39.10443.12747.1551.173Mar 28, 2026

Evaluation results

MethodLinks
PubMed Reasoner2026.0339.75.754.63.58440.83.855.43.60139.27.453.43.58438.75.455.93.587
Geminiretrieval=w/o retrieval2026.0354.65.739.73.41655.43.840.83.42153.47.439.23.43855.95.438.73.424