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

Structural Bias Evaluation on HANS

99.6Accuracy

C2PO

49.26462.33275.488.468Dec 29, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
99.6
2025.12
99
2025.12
97.7
2025.12
96.9
2025.12
95.9
2025.12
86.8
2025.12
86.1
2025.12
85.7
2025.12
77.9
2025.12
66.6
2025.12
57.9
2025.12
54.2
2025.12
53.6
2025.12
51.2