Natural Language Understanding
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
29.07Subset Accuracy
3
Apr 28, 2026
42.36Aggregate Normalized Accuracy
3
Apr 23, 2026
38.91Accuracy
3
Apr 23, 2026
56CoLA Score
3
Apr 3, 2026
93.7SST-2 Accuracy
3
Mar 31, 2026
82.44SST-2 Accuracy
3
Mar 10, 2026
47.49CoLA MCC
3
Mar 5, 2026
61.1CoLA MCC
3
Feb 27, 2026
87.8MRPC Accuracy
3
Feb 26, 2026
58.77Rouge-L (Absolute, ID 039)
3
Feb 26, 2026
92.1BoolQ
3
Feb 26, 2026
71.48CoLA Score
3
Feb 26, 2026
92.9SST-2 Accuracy
3
Feb 26, 2026
79RTE Accuracy
3
Feb 26, 2026
87.7MNLI
3
Feb 26, 2026
95SST-2 Accuracy
3
Feb 26, 2026
46.20-shot Score
3
Feb 26, 2026
68.69SST-2 Accuracy
2
Jun 5, 2026
80.46RTE Accuracy
2
May 22, 2026
65.3RTE Accuracy
2
May 18, 2026
19.6QNLI Time (s)
2
Apr 20, 2026
0.605BoolQ Accuracy
2
Feb 26, 2026
66.1CoLA
2
Feb 26, 2026
20.3CoLA MCC
2
Feb 26, 2026
0.272CoLA Score
2
Feb 26, 2026