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

ClinicalBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Consultation Capability EvaluationClinicalBench
Conversation Arrangement4.04
19
Documentation quality evaluationClinicalBench 1.0 (test)
IDEA Score72.78
19
Interactive Medical DiagnosisClinicalBench
ICR0.511
12
Diagnostic PrecisionClinicalBench (CB) (test)
Accuracy76.9
11
Showing 4 of 4 rows