Multiple-choice Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
95Accuracy
29
Mar 12, 2026
79.81Accuracy
28
May 15, 2026
76Accuracy (MMLU zero-shot)
27
May 25, 2026
77.8Accuracy (PIQA)
27
Apr 21, 2026
87Accuracy
26
Feb 26, 2026
94.2Accuracy
25
Mar 23, 2026
78Accuracy
25
Feb 26, 2026
76.62Accuracy
24
Feb 26, 2026
95.8Clinical Knowledge Accuracy
24
Feb 26, 2026
54.1Accuracy
22
Jun 29, 2026
75.78Accuracy
22
Mar 31, 2026
69.98Accuracy
22
Mar 31, 2026
66.84Accuracy
22
Mar 31, 2026
66.27Accuracy
22
Mar 31, 2026
63.26Accuracy
22
Mar 31, 2026
74.7MC Avg
22
Mar 11, 2026
98.77Accuracy
22
Feb 26, 2026
100Accuracy
22
Feb 26, 2026
100Accuracy
22
Feb 26, 2026
44.8OBQA Accuracy
21
Jun 9, 2026
67.84Accuracy
21
Apr 21, 2026
71.6Accuracy
21
Apr 21, 2026
64.81Accuracy
21
Apr 21, 2026
0.029ECE
21
Apr 14, 2026
63.83Accuracy
21
May 25, 2026