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

Zero-shot Common Sense Reasoning on BoolQ

81.28Accuracy

FP16

39.492850.341461.1972.0386Jul 30, 2025Aug 14, 2025Aug 29, 2025Sep 14, 2025Sep 29, 2025Oct 14, 2025Oct 30, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.07
81.28
2025.07
80.02
2025.07
78.67
2025.07
78.59
2025.07
77.39
2025.07
76.83
2025.07
76.06
2025.07
75.77
2025.07
75.64
2025.07
74.59
2025.07
74.55
2025.07
74.2
2025.07
74.01
2025.07
73.03
2025.07
73
2025.07
72.48
2025.07
70.85
2025.07
68.07
2025.07
67.67
2025.07
66.57
2025.07
65.47
2025.07
63.89
2025.10
63.21
2025.10
62.11
2025.10
61.55
2025.07
61.19
2025.10
61.13
2025.10
60.39
2025.10
60.24
2025.10
60.13
2025.10
59.27
2025.07
58.73
2025.10
57.09
2025.10
56.66
2025.10
55.29
2025.10
54.68
2025.07
43.82
2025.07
41.1
2025.07
41.1