Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73.7CR (%)
5
May 8, 2026
91.8Accuracy (pass@1)
5
May 7, 2026
59.2Accuracy
5
Apr 23, 2026
59.1Accuracy
5
Apr 23, 2026
43.1Accuracy
5
Apr 23, 2026
27.7Accuracy
5
Apr 23, 2026
75.2Aggregate Accuracy
5
Apr 21, 2026
79ARC-E Accuracy
5
Mar 4, 2026
72Score
5
Feb 26, 2026
59.2Score
5
Feb 26, 2026
63.3CoLA Score
4
Jun 29, 2026
59.39MMLU Score
4
Apr 24, 2026
1.698Macro Rank
4
Apr 23, 2026
76.37Accuracy
4
Mar 18, 2026
42.4Normalized Log Accuracy
4
Mar 18, 2026
69.8Normalized Log Accuracy
4
Mar 18, 2026
69.7Normalized Log Accuracy
4
Mar 18, 2026
99Accuracy
4
Mar 10, 2026
77.63Accuracy
4
Mar 9, 2026
40Accuracy
4
Mar 4, 2026
86Accuracy
4
Mar 4, 2026
92.5Exact Match
4
Feb 26, 2026
88.3Exact Match
4
Feb 26, 2026
57.6Comp. Acc
4
Feb 26, 2026
58.4MMLU Knowledge Score
4
Feb 26, 2026