List your company
ResearchFormerly WizWand

Clinical NLP Tasks on CASI AE (GPT-4 score)

3.72GPT-4 ScoreGPT-3.5-turbo
1.29681.92592.5553.1841Sep 1, 2023
Updated 8mo ago

Evaluation results

MethodLinks
GPT-3.5-turboModel Size=175B, Sample Size=1002023.093.72
AsclepiusModel Size=13B, Sample Size=1002023.093.36
Asclepius-RModel Size=13B, Sample Size=1002023.093.36
Asclepius-RModel Size=7B, Sample Size=1002023.093.17
Clinical-CamelModel Size=13B, Sample Size=1002023.093.15
AsclepiusModel Size=7B, Sample Size=1002023.092.97
VicunaModel Size=13B, Sample Size=1002023.092.89
ChatDoctorModel Size=7B, Sample Size=1002023.091.94
AlpacaModel Size=7B, Sample Size=1002023.091.86
MedAlpacaModel Size=7B, Sample Size=1002023.091.39