Natural Language Inference
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
78Total Transmitted Messages (KB)
6
Feb 26, 2026
88.8Accuracy
6
Feb 26, 2026
87.5Accuracy
6
Feb 26, 2026
86.3Accuracy
6
Feb 26, 2026
90.38Acc_p (Personalized)
6
Feb 26, 2026
97.57Personalized Accuracy (Acc_p)
6
Feb 26, 2026
77.1Accuracy
6
Feb 26, 2026
0.537Macro F1 Score
6
Feb 26, 2026
65.8Macro-F1
6
Feb 26, 2026
53.5Accuracy
6
Feb 26, 2026
-42.1Clean Accuracy Change
6
Feb 26, 2026
92.1SAcc
6
Feb 26, 2026
82.1Acc (0-shot)
6
Feb 26, 2026
57.7Accuracy
6
Feb 26, 2026
89Accuracy
6
Feb 26, 2026
92.3Accuracy
6
Feb 26, 2026
0.84Accuracy
6
Feb 26, 2026
86.5F1 Score
6
Feb 26, 2026
58.7Accuracy
6
Feb 26, 2026
0.945Accuracy
6
Feb 27, 2026
81.01Accuracy
5
Jul 3, 2026
85.27Accuracy
5
Jun 8, 2026
68.27AUROC
5
Jun 5, 2026
73.77Clean Accuracy
5
Apr 28, 2026
81.6Accuracy
5
Apr 24, 2026