Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
66.6Accuracy
16
Jul 3, 2026
86.6Accuracy
16
May 11, 2026
87.8Humanities Accuracy
16
May 11, 2026
87.2Accuracy
16
May 11, 2026
1.2Average Rank
16
May 11, 2026
56.66ARC-C Accuracy
16
Mar 31, 2026
77.37Accuracy
16
May 15, 2026
85.5Accuracy
16
Feb 26, 2026
55.61Accuracy
15
Jun 26, 2026
47.1Accuracy
15
Apr 23, 2026
45.2MMLU Math Score
15
Mar 20, 2026
85.72Overall Score
15
Apr 15, 2026
81.31Accuracy
15
Feb 26, 2026
72.4Accuracy
15
Feb 26, 2026
71Accuracy
15
Feb 26, 2026
73Accuracy
15
Feb 26, 2026
59.19Accuracy
14
Apr 28, 2026
54.78Accuracy
14
Apr 21, 2026
79.18Accuracy
14
Apr 21, 2026
48.5Law/Eth Score
13
May 19, 2026
83.92Other Tasks Score
13
Mar 13, 2026
88.69KLEJ Score
13
Mar 13, 2026
57.93Overall Accuracy
13
Feb 26, 2026
78.58MMLU
13
May 28, 2026
43.8Average Accuracy
12
Jun 11, 2026