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

Medical Question Answering on MedXpertQA (test)

8.49ETS Score

GPT4o

5.32846.14926.977.7908Dec 5, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
8.498.268.348.36
2025.12
8.378.188.528.42
2025.12
8.338.418.268.35
2025.12
8.328.297.818.14
2025.12
8.38.396.927.87
2025.12
8.288.387.558.07
2025.12
8.198.437.738.08
2025.12
8.138.167.858.05
2025.12
8.127.848.078.01
2025.12
8.127.458.227.93
2025.12
8.057.98.078.01
2025.12
7.958.328.28.16
2025.12
7.918.167.887.98
2025.12
7.828.067.937.94
2025.12
7.587.837.657.69
2025.12
7.587.698.217.86
2025.12
7.57.497.267.42
2025.12
7.267.337.647.41
2025.12
7.077.046.786.96
2025.12
6.987.587.437.32
2025.12
6.886.957.377.07
2025.12
6.826.656.836.77
2025.12
5.456.156.025.87