Multiple-choice Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
66.4Accuracy
21
Feb 26, 2026
86.4Accuracy
21
Jul 2, 2026
78.5Accuracy
21
Apr 2, 2026
67.6Overall Accuracy
20
Jun 11, 2026
56.8Performance
20
May 28, 2026
80.96Task Utility
20
May 12, 2026
97.16Task Utility
20
May 12, 2026
82.8Biology Accuracy
20
Apr 14, 2026
82.29Accuracy (Overall)
20
Mar 20, 2026
80.61Accuracy
19
Jun 29, 2026
56.997Accuracy
19
Apr 28, 2026
95Accuracy
18
Apr 21, 2026
76.2Accuracy
18
Feb 26, 2026
81.2MHQA Accuracy
17
Mar 27, 2026
78.8MC STEM Average Accuracy
17
Feb 26, 2026
76.56Accuracy (ZH)
17
Feb 26, 2026
89.1Accuracy (ZH)
17
Feb 26, 2026
0.819Score
17
Feb 26, 2026
86.1Accuracy
17
Feb 26, 2026
87.8Accuracy
16
May 15, 2026
88.7Accuracy (Clinical knowledge)
16
Feb 27, 2026
90.65Accuracy
15
Jul 7, 2026
87.68Accuracy
15
Jul 7, 2026
82.66Accuracy
15
Jul 7, 2026
64.66Accuracy
15
Apr 24, 2026