Commonsense Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73.2Accuracy
4
Jun 11, 2026
97.03S_Com Score
4
Jun 4, 2026
61.1Accuracy (%)
4
May 26, 2026
75.82ARC-c Accuracy
4
May 26, 2026
63.84Average Accuracy
4
May 18, 2026
83.8PIQA PQ
4
May 12, 2026
62.84Accuracy
4
May 4, 2026
32.98Accuracy
4
May 4, 2026
0.061Delta
4
May 15, 2026
62.12Accuracy
4
Apr 16, 2026
33.9HellaSwag Accuracy
4
Apr 15, 2026
26.54Arc-c
4
Mar 26, 2026
79.4PIQA Accuracy
4
Mar 19, 2026
159.89Throughput (Tokens/s)
4
Mar 12, 2026
82.1Score (%)
4
Mar 6, 2026
80.79Accuracy (0-shot)
4
Mar 6, 2026
94.6EM
4
Feb 26, 2026
65.69Accuracy
4
Feb 26, 2026
99.31Language Democratization
4
Feb 27, 2026
73.5Accuracy
4
Feb 26, 2026
95.57H-SWAG Accuracy
4
Feb 26, 2026
71.3Accuracy
4
Feb 26, 2026
73.3Accuracy
4
Feb 26, 2026
72.47Accuracy
4
Feb 26, 2026
79.24Accuracy
4
Feb 26, 2026