Natural Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.61SST-2 Accuracy
5
Feb 26, 2026
92.6STS-B Score
5
Feb 26, 2026
42.1Accuracy
5
Feb 26, 2026
40.2CoLA
5
Feb 26, 2026
87.9QNLI Score
5
Feb 26, 2026
0.747Avg NLU Score
5
Feb 27, 2026
96.1Slot F1
5
Feb 26, 2026
12.4CoLA Score
4
May 26, 2026
94.725SST-2 Accuracy
4
May 6, 2026
72.47BoolQ Accuracy
4
Apr 21, 2026
86.33MNLI Accuracy
4
Apr 21, 2026
62QNLI Accuracy
4
Apr 13, 2026
75.76Success Output
4
Apr 7, 2026
87.5SST-2 Accuracy
4
Apr 3, 2026
78.1Accuracy
4
Mar 10, 2026
74.42Accuracy
4
Mar 10, 2026
89.9HuCOLA Accuracy
4
Feb 26, 2026
84.98MRPC F1
4
Feb 26, 2026
31.5CoLA Score
4
Feb 26, 2026
84.3Accuracy
4
Feb 26, 2026
88.4Average Score
4
Feb 26, 2026
93.3SST-2 Score
4
Feb 26, 2026
64.6CoLA Score
3
May 14, 2026
94.8Accuracy (SST-2)
3
May 6, 2026
91.1SST-2 Accuracy
3
May 4, 2026