Natural Language Inference
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.8Accuracy
7
Apr 21, 2026
90.06Accuracy
7
Apr 21, 2026
55.2Accuracy (Xho)
7
Mar 24, 2026
91.7Accuracy
7
Feb 26, 2026
65.7Accuracy
7
Feb 26, 2026
54.2Accuracy
7
Feb 26, 2026
53.2Accuracy
7
Feb 26, 2026
42.4Accuracy
7
Feb 26, 2026
67.1Accuracy
7
Feb 27, 2026
78.5Accuracy
7
Feb 27, 2026
34.77F1 Score
7
Feb 26, 2026
32.62F1 Score
7
Feb 26, 2026
34.93ANLI R1 F1
7
Feb 26, 2026
61.51F1
7
Feb 26, 2026
80.91F1 Score
7
Feb 26, 2026
0.702Micro-F1
7
Feb 26, 2026
57Overall Score
7
Feb 26, 2026
0.738R1 Score
7
Feb 26, 2026
73.51Accuracy (en)
6
May 14, 2026
0.974Raw $
ho$
6
Apr 21, 2026
74.2Accuracy
6
Apr 3, 2026
9.9Delta Accuracy
6
Feb 26, 2026
11.7ΔAcc
6
Feb 26, 2026
82.1IID Accuracy
6
Feb 26, 2026
84.1Accuracy
6
Feb 26, 2026