Natural Language Inference
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
76.4R1 Score
13
Feb 26, 2026
83.09Accuracy
12
Apr 28, 2026
97.56SNLI Accuracy
12
Apr 21, 2026
83.3F1 Score
12
Apr 9, 2026
87.1F1 Score
12
Apr 9, 2026
0.86macro-F1
12
Feb 26, 2026
54.65 Persp Average Score
12
Feb 26, 2026
85.98Accuracy
12
Feb 26, 2026
80.2Accuracy
12
Feb 26, 2026
79.1Accuracy
12
Feb 26, 2026
90.6Accuracy
12
Feb 26, 2026
90.5Accuracy
12
Feb 27, 2026
89.88MNLI Acc
11
Feb 26, 2026
88.05Accuracy
11
Feb 26, 2026
88.4Accuracy
11
Feb 26, 2026
94.6Accuracy (CB Far OOD)
10
Jun 4, 2026
38.67WANLI Accuracy
10
Jun 2, 2026
83.05Correlation Coefficient
10
May 27, 2026
100AR (%)
10
May 21, 2026
33.73Accuracy (Normalized)
10
Apr 23, 2026
88.93Accuracy
10
Apr 21, 2026
89.77Accuracy
10
Apr 21, 2026
88.96Accuracy
10
Apr 21, 2026
92.8Accuracy
10
Apr 21, 2026
93.12Accuracy
10
Apr 21, 2026