Multitask Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.5Accuracy
17
Jun 8, 2026
3,777Score
17
Feb 26, 2026
71.4Accuracy
16
Jul 3, 2026
69.62Accuracy
16
Apr 7, 2026
51.2Accuracy (C-MMLU)
16
Mar 10, 2026
70.9Accuracy
16
Feb 26, 2026
77.4Accuracy
16
Feb 26, 2026
72.5Accuracy
16
Feb 26, 2026
59.33RA
16
Feb 26, 2026
62MMLU Score
15
Jun 16, 2026
63.34Accuracy
14
Jun 16, 2026
65.1Accuracy
14
May 11, 2026
37Accuracy
14
Mar 5, 2026
77Accuracy
14
Apr 23, 2026
73.1Score
14
Feb 26, 2026
80.6Overall Score
14
Feb 26, 2026
30.07Accuracy (MMLU-c)
12
Apr 23, 2026
73.5Accuracy
12
Feb 26, 2026
67Accuracy
12
Feb 26, 2026
72Accuracy
12
Feb 26, 2026
73Mean Accuracy (MA)
12
Feb 26, 2026
50.12Accuracy
11
May 15, 2026
87.21MMLU Score
11
Feb 26, 2026
72MMLU
11
Feb 26, 2026
76Accuracy
11
Feb 26, 2026