Natural Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72.76MMLU (CoT)
19
Feb 26, 2026
83RTE Accuracy
19
Apr 21, 2026
90.2MRPC Accuracy
18
Jun 5, 2026
0.578CoLA Score
18
Jun 2, 2026
52.2EuroEval Score
18
May 27, 2026
51.8EuroEval Score
18
May 27, 2026
56.8EuroEval Score
18
May 27, 2026
0.1EuroEval Score
18
May 27, 2026
0.52CoLA Score
18
May 1, 2026
61.21CoLA (MCC)
18
May 1, 2026
86.33MNLI Accuracy
18
May 19, 2026
88.15Average Score
18
Apr 1, 2026
96SST-2 Accuracy
18
Feb 26, 2026
83.2BoolQ Accuracy
18
Feb 26, 2026
0.97SST-2 Accuracy
18
Feb 26, 2026
91.21Accuracy
17
Apr 6, 2026
97.1SST-2 Accuracy
17
Mar 13, 2026
89.21ReCoRD
17
Feb 26, 2026
88.2CoLA Score
16
Jun 30, 2026
83.9PIQA Accuracy
16
May 21, 2026
86.8Flexible Extract
16
May 11, 2026
86.1Exact Match (EM)
16
May 11, 2026
87.4Fast Accuracy
16
May 11, 2026
85.59MNLI Accuracy
16
May 11, 2026
56MNLI Accuracy
16
Mar 10, 2026