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

DiagnosisArena

Benchmarks

Task NameDataset NameSOTA ResultTrend
Interactive Medical DiagnosisDiagnosisArena
ICR73.8
12
Medical DiagnosisDiagnosisArena (test)
Match (LLM-as-a-Judge)31.88
9
DiagnosisDiagnosisArena
Top-1 Accuracy36.36
7
Medical Knowledge EvaluationDiagnosisArena
Accuracy61.11
5
Medical DiagnosisDiagnosisArena
Pass@145.57
4
Showing 5 of 5 rows