Text-to-Text
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
8.5A AND B
8
Apr 14, 2026
68.2Accuracy
6
Apr 7, 2026
75.2Accuracy
6
Apr 7, 2026
80.6Accuracy (ESNLI Test)
6
Apr 7, 2026
31.8Score
4
Feb 26, 2026
88Score
4
Feb 26, 2026
65.7Score
4
Feb 26, 2026
89.9Score
4
Feb 26, 2026
31.8Score
4
Feb 26, 2026
87.4Score
4
Feb 26, 2026
75.2Score
4
Feb 26, 2026
50.6Score
4
Feb 26, 2026
75.2Score
4
Feb 26, 2026