Multiple-choice Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
99.7Accuracy
269
Jul 2, 2026
97.5Accuracy
222
Jun 29, 2026
93.59Accuracy
212
Jul 7, 2026
96.5MMLU-Pro Overall Accuracy
138
Jun 4, 2026
74.7Acc
133
May 25, 2026
67.5Accuracy
99
Feb 26, 2026
100Accuracy
91
May 25, 2026
59.6Accuracy
84
Feb 26, 2026
93.2Accuracy
79
Jun 1, 2026
73.4Accuracy
73
Apr 2, 2026
84.1Accuracy
71
Jun 12, 2026
89.1Accuracy
68
Mar 4, 2026
80.5Accuracy
67
Jun 29, 2026
87.1Average Accuracy
66
Jun 2, 2026
98.24Accuracy
64
Jun 1, 2026
91Accuracy
61
May 28, 2026
68.9Accuracy
52
Jun 29, 2026
74.91MMLU Accuracy (Overall)
52
May 19, 2026
84.29Accuracy
51
May 21, 2026
0.887MC Accuracy
50
Jun 29, 2026
30Non-generative Accuracy
48
Apr 27, 2026
78MC Avg
46
Mar 20, 2026
80.1Overall Accuracy
45
Jun 9, 2026
95.2Accuracy (%)
44
Apr 23, 2026
83.21Accuracy
43
Jun 12, 2026