Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
84.9Accuracy
31
Feb 26, 2026
82.33RA
31
Feb 26, 2026
37.28Delta Accuracy
30
May 14, 2026
27.4Accuracy
29
Mar 18, 2026
90.8During-task Accuracy
29
Feb 26, 2026
87.7C-Eval Score
29
Apr 30, 2026
90.8MMLU Score
25
May 25, 2026
68.6Overall Accuracy (MMLU-Pro)
24
May 12, 2026
79.7MMLU First-Token Accuracy
24
Apr 6, 2026
89.3PRR
22
Apr 29, 2026
159.215Total Score
22
Feb 26, 2026
73.1Accuracy
21
Jun 1, 2026
62.38Accuracy
21
May 27, 2026
65.81MMLU Score (x100)
21
Mar 12, 2026
64.8Average Score
21
Feb 26, 2026
70.23MMLU (en)
21
Mar 6, 2026
76.9Accuracy
21
Feb 26, 2026
0.678Overall Score
20
May 12, 2026
76.4Accuracy
20
Mar 24, 2026
52.15Accuracy
20
Mar 4, 2026
78.33MMLU 5-shot Accuracy
18
Jul 7, 2026
83.7MMLU AUROC
18
Apr 21, 2026
84.76Accuracy
17
Jul 8, 2026
65.3Accuracy
16
Jul 3, 2026
71.4Accuracy
16
Jul 3, 2026