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

Commonsense Reasoning on WinoGrande (0-shot, test)

73.95Accuracy

FP16

54.408459.481764.55569.6283Dec 19, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
73.95
2025.12
70.24
2025.12
69.14
2025.12
69.06
2025.12
68.75
2025.12
68.75
2025.12
60.54
2025.12
58.96
2025.12
58.25
2025.12
55.16