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

Question Answering on G-bench Novel

58.9Accuracy

G-reasoner

42.57246.81151.0555.289Sep 29, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
58.9
2025.09
58.6
2025.09
56.5
2025.09
56.5
2025.09
56.2
2025.09
56.2
2025.09
51.4
2025.09
50.9
2025.09
45.1
2025.09
44.8
2025.09
43.2