List your company

Medical Reasoning on MedBullets

80.8AccuracyMDAgents
20.37636.06351.7567.437Aug 11, 2025

Evaluation results

MethodLinks
MDAgentsBase Model=GPT-4o2025.0880.8
TMA-AllComponBase Model=GPT-4o2025.0878.8
ReConcileBase Model=GPT-4o2025.0875.2
MedAgentsBase Model=GPT-4o2025.0870
DyLANBase Model=GPT-4o2025.0869.5
TMA-AllComponBase Model=MedGemma-4B2025.0848.2
TMA-AllComponBase Model=Gemma-3-4B2025.0846.7
DyLanBase Model=Gemma-3-4B2025.0835.3
Single-Agent BestBase Model=Gemma-3-4B2025.0834.6
TMA-AllComponBase Model=Gemma-3-4B2025.0833.9
MedAgentsBase Model=Gemma-3-4B2025.0833.3
ReConcileBase Model=Gemma-3-4B2025.0829.3
MDAgentsBase Model=Gemma-3-4B2025.0822.7