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

Question Answering on G-bench Medical

73.3Accuracy

G-reasoner

44.07651.66359.2566.837Sep 29, 2025
Updated 3mo ago

Evaluation Results

MethodLinks
2025.09
73.3
2025.09
72.2
2025.09
71.8
2025.09
70.4
2025.09
68.7
2025.09
67.1
2025.09
64.9
2025.09
63.9
2025.09
59.1
2025.09
57.1
2025.09
45.2