General Knowledge Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
83.66MMLU Accuracy
167
Jun 5, 2026
82.25MMMLU General Knowledge Accuracy
29
Feb 26, 2026
85.52Accuracy
23
Jun 8, 2026
88.93Accuracy
15
Jun 16, 2026
34.32Accuracy
15
Apr 23, 2026
70.9Accuracy
13
May 14, 2026
71.8Accuracy
13
Feb 26, 2026
73.8Accuracy
12
Feb 26, 2026
39.79Accuracy
10
Mar 24, 2026
46Accuracy
8
Apr 14, 2026
60.4Accuracy
8
Apr 14, 2026
53.5Accuracy
8
Apr 14, 2026
55.23Accuracy
5
Apr 29, 2026
60.2ARC-C
5
Feb 26, 2026
68.41Utility Score
4
Jun 25, 2026