Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Commonsense Reasoning on WinoGrande (val)

73.88Accuracy

FP16

47.443254.306661.1768.0334May 7, 2024Aug 23, 2024Dec 9, 2024Mar 28, 2025Jul 14, 2025Oct 30, 2025Feb 16, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2024.05
73.88
2024.05
73.88
2024.05
73.72
2024.05
73.48
2024.05
73.4
2024.05
72.69
2024.05
72.61
2024.05
72.53
2024.05
72.45
2024.05
72.3
2024.05
71.98
2024.05
71.59
2024.05
71.43
2024.05
70.8
2024.05
70.72
2024.05
70.72
2024.05
70.4
2024.05
70.17
2024.05
69.93
2024.05
69.53
2024.05
69.38
2024.05
69.06
2024.05
68.9
2024.07
68.74
2024.05
68.67
2024.05
68.27
2024.05
68.03
2024.05
67.96
2024.05
67.64
2024.05
67.48
2024.05
66.45
2024.05
65.27
2026.02
64
2024.05
63.93
2024.07
63.77
2026.02
63.6
2024.05
63.46
2026.02
63
2024.05
62.98
2026.02
62.6
2026.02
61.6
2024.05
61.56
2024.05
61.01
2024.05
60.46
2024.05
59.35
2026.02
59.2
2024.05
59.19
2024.07
59.1
2024.05
58.25
2024.05
58.17
2024.07
58.01
2024.07
57.85
2024.05
57.77
2024.07
57.62
2024.07
57.38
2024.05
57.3
2024.05
57.14
2024.07
57.14
2024.07
56.98
2024.07
56.75
2024.05
56.67
2024.05
56.51
2024.07
56.2
2024.07
55.72
2024.07
55.49
2024.07
55.25
2024.05
55.01
2024.07
54.46
2024.07
54.4
2024.07
53.91
2024.05
53.59
2024.07
53.3
2024.07
52.6
2024.07
52.1
2024.07
51.9
2024.07
51.9
2024.07
51.8
2024.05
51.7
2024.07
51.7
2024.05
51.3
2024.05
50.91
2024.07
50.7
2024.05
50.51
2024.07
50.4
2024.05
49.8
2024.05
49.41
2024.05
48.46