Textual Entailment
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
90.3Accuracy
21
Feb 26, 2026
0.356AUPRC
11
Feb 26, 2026
44.3AUPRC
9
Feb 26, 2026
44.1ASR
8
Mar 12, 2026
38.2ASR
8
Mar 12, 2026
22.1ASR
8
Mar 12, 2026
0.764F1 Score
6
Mar 20, 2026
85.5Attack Success Rate
6
Feb 26, 2026
92.4F1 Score
6
Feb 26, 2026
79.9F1 Score
4
Feb 26, 2026