Zero-shot Common Sense Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72.6Zero-shot Accuracy
148
Jul 9, 2026
82.7PIQA
95
Feb 26, 2026
70.185Avg Accuracy
63
Mar 20, 2026
81.28Accuracy
39
Jun 4, 2026
41.91Accuracy (Zero-shot)
12
Apr 9, 2026
74.2ARC-e Accuracy
8
May 19, 2026