Natural Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
92.43SST-2 Accuracy
6
Apr 14, 2026
86.89MNLI Accuracy
6
Apr 1, 2026
91.17SST-2 Accuracy
6
Feb 26, 2026
87.67MNLI
6
Feb 26, 2026
60.7RTE Score
6
Feb 26, 2026
71.9RTE
6
Feb 26, 2026
90.4Accuracy (SST-2)
6
Feb 26, 2026
82.1SST2 Accuracy
6
Feb 26, 2026
65.56Belebele-bul
6
Feb 26, 2026
70.36Polemo2-in Acc
6
Feb 26, 2026
88.74Assin2 RTE
6
Feb 26, 2026
91.6SST-2 Score
6
Feb 26, 2026
50.21NLI Accuracy
6
Feb 26, 2026
89.9BoolQ Accuracy
6
Feb 26, 2026
92.59Accuracy
6
Feb 26, 2026
0.698CoLA Score
5
May 15, 2026
91.55MNLI Score
5
May 12, 2026
85.71MNLI-m Accuracy
5
May 11, 2026
72.89MNLI-m Accuracy
5
May 11, 2026
62.33CoLA Score
5
Apr 7, 2026
57.2WG Score
5
Mar 30, 2026
73.5BoolQ Accuracy
5
Mar 26, 2026
86.8MRPC Score
5
Mar 4, 2026
57.11SST-2 Accuracy
5
Feb 26, 2026
92.9SST-2 Accuracy
5
Feb 26, 2026