Share your thoughts, 1 month free Claude Pro on usSee more

Medical Error Detection on MEDEC

69.13Accuracy

BLUEmed

Updated 5d ago

Evaluation Results

Method	Links
BLUEmed 2026.04		69.13	68.28	73.33	63.87	74.45	72.44
BLUEmed 2026.04		67.67	66.67	72.01	62.05	70.24	68.88
RAG-Single (WebMD) 2026.04		58.96	43.16	77.5	29.9	50	50
RAG-Single (MayoClinic) 2026.04		58.63	59.44	60.74	58.2	50	50
RAG-Single (WebMD) 2026.04		57.79	60.5	59.02	62.06	62.93	50
RAG-Single (MayoClinic) 2026.04		57.29	40.56	73.73	27.97	50	50
LLM-Debate 2026.04		55.89	65.55	55.42	80.2	58.56	58.7
LLM-Debate 2026.04		55.28	66.91	54.44	86.82	59.51	59.47