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

Commonsense Reasoning on WNG-L

91.88Accuracy

In-Squeeze

24.404841.922459.4476.9576Feb 11, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
91.88
2026.02
91.58
2026.02
91.41
2026.02
91.07
2026.02
90.94
2026.02
90.73
2026.02
90.69
2026.02
90.6
2026.02
82.44
2026.02
82.02
2026.02
81.97
2026.02
81.8
2026.02
81.38
2026.02
81.29
2026.02
81.16
2026.02
37.67
2026.02
27