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

Language Understanding on WinoGrande

80.82Accuracy

DuQ

66.124869.939973.75577.5701May 19, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.05
80.8279.85
2026.05
79.4878.97
2026.05
79.3278.85
2026.05
79.3278.85
2026.05
79.0878.82
2026.05
78.8578.64
2026.05
74.1170.85
2026.05
73.7272.84
2026.05
73.5672.81
2026.05
73.3273.24
2026.05
73.2472.63
2026.05
73.1672.75
2026.05
73.0972.85
2026.05
73.0972.85
2026.05
73.0972.77
2026.05
72.2270.44
2026.05
71.8270.73
2026.05
71.8270.73
2026.05
71.8269.58
2026.05
71.1969.69
2026.05
70.469.45
2026.05
70.2468.81
2026.05
70.2468.81
2026.05
70.0967.84
2026.05
70.0967.84
2026.05
70.0169.03
2026.05
69.9368.73
2026.05
69.8568.85
2026.05
69.6168.77
2026.05
69.5367.6
2026.05
69.4667.7
2026.05
69.0667.37
2026.05
68.3568.71
2026.05
68.2766.89
2026.05
67.8862.25
2026.05
67.8862.25
2026.05
67.4867.16
2026.05
66.6962.09