Commonsense Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.953Accuracy
127
Feb 26, 2026
88.9Accuracy
92
May 29, 2026
77.82Accuracy
89
Jun 30, 2026
88.9Accuracy
71
May 15, 2026
94Accuracy
68
May 11, 2026
82.72Accuracy
61
May 19, 2026
77.4BoolQ Accuracy
29
May 5, 2026
89.88Accuracy
29
May 14, 2026
98.9Accuracy
26
Jul 9, 2026
92.25EM
24
Mar 4, 2026
70.7Accuracy
24
Feb 26, 2026
75.7Accuracy
23
Feb 26, 2026
79.3Accuracy
22
Feb 26, 2026
83.24Accuracy
21
May 14, 2026
78.3Accuracy
21
Feb 26, 2026
0.812Accuracy
21
Feb 26, 2026
75.3Accuracy
20
Feb 26, 2026
93.4Accuracy
19
Jun 2, 2026
82Accuracy
18
Mar 4, 2026
84.06PIQA
18
Feb 26, 2026
79.49PIQA Accuracy
17
Jun 2, 2026
72.89Accuracy
15
Jun 4, 2026
84.6Accuracy
14
Feb 26, 2026
68.12Accuracy
13
Jun 24, 2026
61.22Accuracy
13
Jun 24, 2026