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

Common Sense Reasoning on WinoGrande 2021 (Acc_norm)

78.06Normalized Accuracy

Baseline

49.82457.154564.48571.8155Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
78.06
2026.06
73.72
2026.06
73.32
2026.06
70.8
2026.06
70.64
2026.06
69.85
2026.06
67.17
2026.06
65.98
2026.06
65.9
2026.06
65.82
2026.06
64.09
2026.06
63.3
2026.06
62.43
2026.06
62.12
2026.06
60.85
2026.06
60.06
2026.06
59.98
2026.06
59.27
2026.06
59.19
2026.06
55.17
2026.06
54.85
2026.06
54.38
2026.06
51.85
2026.06
51.78
2026.06
51.14
2026.06
50.91