Cross-task generalization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62.2Weighted Avg Rouge-L
27
Feb 26, 2026
0.65Similarity Score
4
Apr 14, 2026
0.689Similarity
4
Apr 14, 2026
39.59ROUGE-L
4
Feb 26, 2026
53.6Test Final Score
3
Jun 4, 2026
70.3Test Final Score
3
Jun 4, 2026
48.5Test Fin Score
3
Jun 4, 2026
0.806Test Final Score
3
Jun 4, 2026
3.076Answerability Classification
3
Feb 26, 2026