Natural Language Inference
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.223JSD
9
Feb 26, 2026
0.189JSD
9
Feb 26, 2026
93.1Accuracy
9
Feb 26, 2026
72.5Accuracy
9
Feb 26, 2026
79.4Best-of-K Accuracy
8
Jun 23, 2026
83.45Accuracy
8
Jun 19, 2026
36.4Accuracy (ANLI 1)
8
May 14, 2026
88.83Accuracy
8
May 11, 2026
84.5Macro-F1
8
May 11, 2026
79.15MNLI (m) Accuracy
8
May 8, 2026
97.31Accuracy
8
Apr 28, 2026
100Accuracy
8
Apr 28, 2026
73.53Accuracy
8
Apr 28, 2026
75.93Accuracy
8
Apr 28, 2026
36.42Score
8
Mar 24, 2026
74Best F1
8
Mar 9, 2026
75Best F1 (ANLI)
8
Mar 9, 2026
90.8Accuracy (English)
8
Mar 9, 2026
255Fine-tuning Rounds
8
Mar 6, 2026
131.39VRAM
8
Mar 6, 2026
87.5Best Accuracy
8
Mar 4, 2026
84Accuracy
8
Feb 26, 2026
84Accuracy
8
Feb 26, 2026
47.3Accuracy
8
Feb 26, 2026
87.5Accuracy
8
Feb 26, 2026