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

Winograd Schema Challenge on WinoGrande

76.56Accuracy

GPTAQ

64.65267.743570.83573.9265May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
76.56
2026.05
76.4
2026.05
76.24
2026.05
76.24
2026.05
75.93
2026.05
75.93
2026.05
75.93
2026.05
75.45
2026.05
75.37
2026.05
75.06
2026.05
74.74
2026.05
73.88
2026.05
73.56
2026.05
73.56
2026.05
73.09
2026.05
72.85
2026.05
72.53
2026.05
72.22
2026.05
71.74
2026.05
71.67
2026.05
71.43
2026.05
71.43
2026.05
71.27
2026.05
70.88
2026.05
70.17
2026.05
70.17
2026.05
70.09
2026.05
69.77
2026.05
69.69
2026.05
69.38
2026.05
68.82
2026.05
68.59
2026.05
68.51
2026.05
68.35
2026.05
68.19
2026.05
67.88
2026.05
67.64
2026.05
67.17
2026.05
65.11