Summarization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
14.83ROUGE-1
8
Feb 26, 2026
2.3Speedup
8
Feb 26, 2026
0.89BERTScore
8
May 8, 2026
75.61Preference vs SFT (%)
8
Feb 26, 2026
0.3Std Dev ROUGE-1
8
Feb 26, 2026
0.83Std Dev ROUGE-1
8
Feb 26, 2026
0.52Std Dev ROUGE-1
8
Feb 26, 2026
0.21ROUGE-1 Std Dev
8
Feb 26, 2026
0.11ROUGE-1 Std Dev
8
Feb 26, 2026
11.4NOUN
8
Feb 26, 2026
23.8ROUGE-2 Score
8
Feb 27, 2026
35.8ROUGE-1
8
Feb 26, 2026
46.66ROUGE-1
8
Feb 26, 2026
66Relevance
8
Feb 26, 2026
40.34ROUGE-1
8
Feb 26, 2026
65.73BERTScore F1
8
Feb 26, 2026
19.07Total Score
7
Jun 9, 2026
91.9Structural Score
7
May 15, 2026
48.7ROUGE-L
7
Apr 28, 2026
58.14ROUGE-1
7
Apr 20, 2026
60.11ROUGE-1
7
Apr 20, 2026
64.2ROUGE-1
7
Apr 20, 2026
59.324ROUGE-1 Score
7
Apr 20, 2026
59.68R1 Score
7
Apr 20, 2026
57.401R1
7
Apr 20, 2026