Summarization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
23.1ROUGE-2
9
Feb 27, 2026
13.8ROUGE-2
9
Feb 27, 2026
60.22ROUGE-1
9
Feb 26, 2026
36.15R-1
9
Feb 26, 2026
40.9RL Score
9
Feb 26, 2026
40.3ROUGE-1
9
Feb 26, 2026
22.9ROUGE
9
Feb 26, 2026
27.6ROUGE
9
Feb 26, 2026
13.05ROUGE-2
8
Jun 11, 2026
18.99ROUGE-2
8
Jun 11, 2026
54.27ROUGE-1
8
Jun 5, 2026
48.54ROUGE-1
8
Jun 5, 2026
72.2Pairwise Preference Rate
8
Jun 2, 2026
84.1Pairwise Preference Rate
8
Jun 2, 2026
90.5Pairwise Preference Rate
8
Jun 2, 2026
87.5Pairwise Preference Rate
8
Jun 2, 2026
80Win Rate
8
May 27, 2026
24.86R-LCS
8
May 19, 2026
25.16R-LCS
8
May 19, 2026
26.68R-LCS
8
May 19, 2026
285mTokens
8
Mar 20, 2026
24.5Best Accuracy
8
Mar 4, 2026
25.3Best Accuracy
8
Mar 4, 2026
15.6ROUGE-L
8
Feb 26, 2026
80.37Win Rate
8
Feb 26, 2026