List your company

Medical Question Answering Accuracy on MMLU

91.9MMLU Anatomy Accuracyo3
52.58862.7947383.206Jul 7, 2025

Evaluation results

MethodLinks
o3Size category=Large Models2025.0791.994.798.690.21009656
DeepSeek R1Size category=Large Models2025.0791.191.798.690.89995.656
Gemini 2.5 FlashSize category=Large Models2025.0791.191.798.687.9979659.6
Gemini 2.5 ProSize category=Large Models2025.0791.191.798.6899696.356
GPT-4oSize category=Large Models2025.0786.789.494.486.7989358.4
OpenBioLLM 70BSize category=Large Models2025.0783.992.993.885.793.293.8—
MedGemma 27BSize category=Small Models, test-time scaling=true2025.0783.78696.586.19793.453.6
Gemma 3 27BSize category=Small Models2025.0774.88693.878.69185.751.2
IQVIA Med-R1 8BSize category=Small Models2025.0772.678.588.272.88784.9—
JSL-MedLlama 3 8B v2.0Size category=Small Models2025.0771.978.182.671.18378.7—
OpenBioLLM 8BSize category=Small Models2025.0769.876.184.26886.178.2—
MedGemma 4BSize category=Small Models2025.0759.371.370.865.38376.853
BioMistral DARE 7BSize category=Small Models2025.0755.862.366.9586761.4—
Gemma 3 4BSize category=Small Models2025.0754.169.877.8637465.442.8