List your company

Explanation Quality Evaluation on MMLU-CK (test)

44Reasoning Soundness Loss (%)PubMed Reasoner
43.95244.27644.644.924Mar 28, 2026

Evaluation results

MethodLinks
PubMed Reasoner2026.034410.845.23.69925.211.764.13.59534.42045.63.73235.315.948.83.712
Geminiretrieval=w/o retrieval2026.0345.210.8443.30764.111.725.23.20945.62034.43.52548.815.935.33.386