General Knowledge QA
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
80Accuracy
44
Jun 15, 2026
48Normalized Accuracy
44
Jun 15, 2026
33.6Average Accuracy
18
Apr 23, 2026
69.4Accuracy
18
Apr 23, 2026
84.1Accuracy
18
Apr 23, 2026
69.7MMLU-R Score
12
Feb 26, 2026