List your company

Medical Question Answering on MedXpertQA (test)

8.49ETS ScoreGPT4o
5.32846.14926.977.7908Dec 5, 2025

Evaluation results

MethodLinks
GPT4ocategory=Base Model2025.128.498.268.348.36
o3category=Base Model2025.128.378.188.528.42
MedTutor-R1category=Final Model2025.128.338.418.268.35
MedTutor-R1simulation_variation=w/o Specialist2025.128.328.297.818.14
MedTutor-R1training_variation=w/o reward veto2025.128.38.396.927.87
MedTutor-R1training_variation=w/o CS reward2025.128.288.387.558.07
MedTutor-R1simulation_variation=w/o Supervisor2025.128.198.437.738.08
MedTutor-R1training_variation=w/ LLaVA-based2025.128.138.167.858.05
DeepSeek-R1category=Base Model2025.128.127.848.078.01
MedTutor-R1training_variation=w/o AQ reward2025.128.127.458.227.93
MedTutor-R1training_variation=w/ Vanilla reward2025.128.057.98.078.01
MedTutor-R1training_variation=w/o IS reward2025.127.958.328.28.16
MedTutor-R1simulation_variation=w/o Patient2025.127.918.167.887.98
MedTutor-R1training_variation=w/o Thinking2025.127.828.067.937.94
MedTutor-R1training_variation=w/o RL2025.127.587.837.657.69
MedTutor-R1simulation_variation=w One-Student2025.127.587.698.217.86
TutorRLcategory=Agent for Medical Education2025.127.57.497.267.42
Med-SocraticLMcategory=Agent for Medical Education2025.127.267.337.647.41
Qwen2.5VLcategory=Base Model2025.127.077.046.786.96
DRLTutorcategory=Agent for Medical Education2025.126.987.587.437.32
EduChat-R1category=Agent for Medical Education2025.126.886.957.377.07
InternVL-3.5category=Base Model2025.126.826.656.836.77
LLaVA-V1.6category=Base Model2025.125.456.156.025.87