Natural Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
90.65MNLI Accuracy
9
Apr 21, 2026
83.4MNLI Accuracy
9
Apr 15, 2026
72.5Average Accuracy
9
Mar 26, 2026
69.9RTE Accuracy
9
Mar 20, 2026
94.4SST-2 Accuracy
9
Mar 17, 2026
94.1SST-2 Score
9
Mar 12, 2026
89.1Accuracy
9
Mar 20, 2026
95.64SST-2
9
Feb 26, 2026
96.22SST-2 Accuracy
9
Feb 26, 2026
89.8STS-B Score
9
Feb 26, 2026
95.47CLS-books Accuracy
9
Feb 26, 2026
94.9SST-2 Accuracy
9
Feb 26, 2026
4.52Overall Accuracy
8
Jun 25, 2026
69.7CoLA Score
8
Jun 16, 2026
81.06QNLI Accuracy
8
May 8, 2026
58.21CoLA Acc
8
Apr 21, 2026
68.29Performance Score
8
May 21, 2026
39.93QQP Accuracy
8
Apr 2, 2026
88.15MNLI Accuracy
8
Mar 17, 2026
83.5MNLI Accuracy
8
Mar 12, 2026
91.51SST-2 Accuracy
8
Mar 10, 2026
85.78SST-2 Accuracy
8
Mar 10, 2026
88.92SST-2 Accuracy
8
Mar 10, 2026
32.38NPM
8
Mar 5, 2026
40.28NPM
8
Mar 5, 2026