Multiple-Choice QA
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72.1MC Avg
49
Mar 20, 2026
68.39PIQA Accuracy
16
Apr 23, 2026
81.8AUROC
9
Apr 3, 2026
37.1Accuracy
8
Mar 24, 2026
84.8Accuracy
8
Feb 26, 2026
81Accuracy
6
Apr 2, 2026