Natural Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
69.86CoLA Accuracy
16
May 15, 2026
60.18CoLA Score
16
Feb 26, 2026
76.98CoLA
16
Feb 26, 2026
75.61Winogrande Accuracy
16
Feb 26, 2026
95.3Accuracy
16
May 21, 2026
1.02ECE
16
Feb 26, 2026
0.818BoolQ Accuracy
16
Feb 26, 2026
95.8SST-2 Score
15
May 13, 2026
66.7CoLA Accuracy
15
May 7, 2026
84BoolQ Accuracy
15
Feb 26, 2026
48.2ARC-C Accuracy
15
Feb 26, 2026
63.1CoLA Score
15
Feb 26, 2026
95.3SST-2 (Acc)
15
Feb 26, 2026
90STS-B Spearman Correlation
14
Jun 2, 2026
80.15Accuracy (MMLU)
14
Jun 2, 2026
68EuroEval Dutch Score
14
May 27, 2026
54.3EuroEval Score
14
May 27, 2026
65EuroEval Score
14
May 27, 2026
82.5Exact Match
14
May 6, 2026
77.7Exact Match
14
May 6, 2026
96.5SST-2 Accuracy
14
Apr 24, 2026
76.98CoLA
14
Feb 26, 2026
89.46Accuracy
14
Jun 15, 2026
91.9MNLI Accuracy
13
Jul 7, 2026
84.7MNLI-m Accuracy
13
Jun 12, 2026