Natural Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72.03CoLA Score
13
May 13, 2026
95.4SST-2 Accuracy
13
May 13, 2026
93.3BoolQ Score
13
Apr 15, 2026
81.2RTE Accuracy
13
Mar 20, 2026
94.6SST-2 Accuracy
13
Feb 26, 2026
57.94ARC
13
Feb 26, 2026
27.6OAI Sum
13
Feb 26, 2026
90.8MNLI
13
Feb 26, 2026
66.2CSQA Accuracy
12
Jul 9, 2026
84.5MRPC Accuracy
12
Jul 7, 2026
59.36BoolQ Accuracy
12
Jul 3, 2026
85.15Average Score
12
Jun 17, 2026
66.62CoLA Score
12
Jun 9, 2026
60.8RTE Accuracy
12
Jun 4, 2026
51.6MNLI Score
12
Jun 4, 2026
60.2CoLA Score
12
May 25, 2026
36.81ARC-Easy Accuracy
12
May 18, 2026
96SST-2 Accuracy
12
May 12, 2026
57.18HellaSwag
12
May 8, 2026
59.9Exact Match
12
May 6, 2026
97.99SST-2 Accuracy
12
Apr 28, 2026
87.73CoLA Accuracy
12
Feb 26, 2026
56.14ARC-c
12
Feb 26, 2026
84.3GLUE Macro Score
12
Feb 26, 2026
92.4QNLI Accuracy
12
Feb 26, 2026