List your company

Commonsense Reasoning

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated
99.21Accuracy
Commonsense Reasoning on HellaSwag performance trend
1,896
May 11, 2026
7,364Accuracy
Commonsense Reasoning on WinoGrande performance trend
1,581
Jul 9, 2026
85.3Accuracy
Commonsense Reasoning on Winogrande (accuracy) performance trend
453
May 28, 2026
89.99Accuracy
Commonsense Reasoning on PIQA (Accuracy) performance trend
400
Jul 9, 2026
96Accuracy
Commonsense Reasoning on CSQA performance trend
366
Feb 26, 2026
89.2Accuracy
Commonsense Reasoning on OBQA performance trend
187
May 19, 2026
89.85Accuracy
Commonsense Reasoning on SIQA performance trend
183
Jun 26, 2026
86.55Accuracy
146
May 12, 2026