Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Medical Question Answering Accuracy on MMLU

91.9MMLU Anatomy Accuracy

o3

52.58862.7947383.206Jul 7, 2025
Updated 11d ago

Evaluation Results

MethodLinks
2025.07
91.994.798.690.21009656
2025.07
91.191.798.690.89995.656
2025.07
91.191.798.687.9979659.6
2025.07
91.191.798.6899696.356
2025.07
86.789.494.486.7989358.4
2025.07
83.992.993.885.793.293.8-
2025.07
83.78696.586.19793.453.6
2025.07
74.88693.878.69185.751.2
2025.07
72.678.588.272.88784.9-
2025.07
71.978.182.671.18378.7-
2025.07
69.876.184.26886.178.2-
2025.07
59.371.370.865.38376.853
2025.07
55.862.366.9586761.4-
2025.07
54.169.877.8637465.442.8