Natural Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
29.4NPM
8
Mar 5, 2026
76.8CoLA Score
8
Mar 4, 2026
49.8CSQA Accuracy
8
Feb 26, 2026
71.69CoLA
8
Feb 26, 2026
94.1Classification F1
8
Feb 26, 2026
96.67SST-2 Accuracy
8
Feb 26, 2026
0.927MRPC
8
Feb 26, 2026
74.37BoolQ Acc
8
Feb 26, 2026
61.7Average Score
8
Feb 26, 2026
66.3CoLA Score
7
May 15, 2026
60.8CoLA Score
7
May 15, 2026
69.8CoLA Accuracy
7
May 15, 2026
40.36Normalized Accuracy
7
Apr 23, 2026
11.01CoLA Score
7
Mar 25, 2026
96.1SST-2 Accuracy
7
Feb 26, 2026
96.1SST-2 Accuracy
7
Feb 26, 2026
91.3BoolQ Acc
7
Feb 26, 2026
76.9MNLI
6
Jul 7, 2026
74.6RTE Accuracy
6
Jun 18, 2026
92.55SST-2 Accuracy
6
Jun 9, 2026
55.5CoLA Score
6
Jun 2, 2026
88.5QNLI Accuracy
6
May 26, 2026
88.5BoolQ Accuracy
6
May 21, 2026
90.49MNLI Accuracy
6
Apr 21, 2026
94.81Accuracy (SST2)
6
Apr 14, 2026