AgentClinic
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
AgentClinic_M offline (test)
94.17Accuracy
38
AgentClinic_T offline (test)
68.22Accuracy
38
AgentClinic OOD original (test)
0.684Similarity (Sim)
20
AgentClinic MedQA
53.9ICR
12
AgentClinic MedQA
65.8Accuracy
6