Natural Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73.4CoLA Mcc
32
Mar 12, 2026
3.06SST-2 Speedup
32
Feb 26, 2026
82.2MNLI Score
30
May 19, 2026
100Average GLUE Score
30
Jun 2, 2026
91.91MRPC Score
30
May 26, 2026
59Accuracy
30
May 19, 2026
93.8MRPC Score
30
Feb 26, 2026
97.5SST-2 Acc
28
Feb 26, 2026
81.37Macro F1
28
Feb 26, 2026
99.29Intent Acc
27
Feb 26, 2026
92.31QNLI Score
26
Feb 26, 2026
76.9WSC Score
25
May 15, 2026
61.58MNLI Accuracy
24
Mar 5, 2026
88.08MNLI Accuracy
24
Mar 5, 2026
81.96RTE Accuracy
24
Jun 29, 2026
96.2Accuracy (SST-2)
22
Apr 23, 2026
75.9MultiRC Score
22
Apr 14, 2026
90.57MNLI Accuracy
22
Feb 26, 2026
71.6Ag_news Accuracy
22
Feb 26, 2026
92.4QQP
21
May 13, 2026
96.56SST2 Accuracy
20
Apr 23, 2026
36.46NLU Score
20
Apr 10, 2026
40.33Alast Score
20
Mar 10, 2026
78.24Alast
20
Mar 10, 2026
87.84MNLI-m Accuracy
20
Mar 10, 2026