Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.6Accuracy
844
May 12, 2026
90MMLU Accuracy
307
Jun 29, 2026
73.81Average Accuracy
173
Apr 9, 2026
88MMLU Average Accuracy
167
May 29, 2026
90.58Accuracy
160
Jun 26, 2026
74.2Accuracy
149
Apr 23, 2026
87.56MMLU Accuracy
144
Jun 19, 2026
80.6Accuracy
130
Jun 30, 2026
70.46Accuracy
119
Jun 1, 2026
73.02MMLU Score
98
Mar 9, 2026
88.6MMLU Score
70
Apr 6, 2026
83.56Accuracy
67
Jun 5, 2026
74.5Score
66
Apr 28, 2026
90.1Accuracy
65
Jun 5, 2026
72.8MMLU-Pro Accuracy
60
May 25, 2026
69.84Average Performance
53
Apr 14, 2026
71.91Average Accuracy
50
Mar 4, 2026
81.4MMLU-Pro Score
44
Jul 7, 2026
82.1Accuracy
43
May 26, 2026
77.6Accuracy
42
Feb 26, 2026
69MMLU Score
40
May 29, 2026
80.82Accuracy
38
May 21, 2026
96.1SST-2 Accuracy
36
Jun 11, 2026
85.75Accuracy
33
Jun 25, 2026
68.6Humanities Avg
33
Feb 26, 2026