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

Commonsense Reasoning on PIQA (Accuracy)

89.99Accuracy

BaLoRA

71.883676.584381.28585.9857Jun 17, 2025Aug 14, 2025Oct 11, 2025Dec 8, 2025Feb 4, 2026Apr 3, 2026May 31, 2026
Updated 21h ago

Evaluation Results

MethodLinks
2026.04
89.99
2026.04
89.7
2026.04
89.3
2026.05
89.23
2026.05
88.9
2026.05
88.03
2026.04
87.43
2025.09
87.25
2025.09
87.2
2025.09
86.69
2025.09
86.57
2025.09
86.53
2025.09
85.47
2026.04
85.4
2025.09
85.2
2026.04
85.2
2025.09
85.05
2025.06
84.94
2026.04
84.93
2025.09
84.71
2026.05
84.44
2026.05
84.11
2026.05
84.06
2026.04
83.7
2026.04
83.35
2026.05
81.28
2026.05
80.96
2025.10
80.9
2026.04
80.79
2025.06
80.71
2026.05
80.69
2025.09
80.62
2025.09
80.59
2026.05
80.5
2026.05
80.3
2025.09
80
2026.05
80
2026.04
79.9
2025.09
79.87
2026.05
79.8
2026.05
79.8
2025.10
79.7
2025.09
79.22
2025.10
79.2
2025.09
79.05
2026.05
79
2025.10
78.9
2025.10
78.8
2025.09
78.78
2026.05
78.73
2026.05
78.6
2025.06
78.47
2025.09
78.45
2026.05
78.4
2025.09
78.32
2026.05
78.1
2025.10
78.1
2026.05
77.7
2026.05
77.6
2026.05
77.5
2026.05
77.5
2026.05
77.37
2026.05
77.3
2026.05
77.2
2026.05
76.8
2026.05
76.7
2026.05
76.6
2026.05
76.6
2026.05
76.55
2026.05
76.39
2026.05
76.39
2026.05
76.01
2026.05
75.9
2026.05
75.79
2026.05
75.6
2025.10
75.6
2026.05
75.6
2026.05
75.41
2026.05
75.4
2026.05
75.4
2026.05
75.2
2026.05
75.1
2025.11
74.92
2026.05
74.9
2025.11
74.81
2026.05
74.7
2025.11
74.59
2026.05
74.48
2026.05
74.32
2025.11
74.32
2025.11
74.32
2026.05
74.2
2025.11
73.78
2025.11
73.78
2025.11
73.56
2026.05
73.5
2026.05
73.39
2026.05
72.91
2026.05
72.63
2026.05
72.58
Showing 100 of 213 rows