Summarization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
85.28Win Rate
12
Feb 26, 2026
18.72ROUGE Score
12
Feb 26, 2026
23.39ROUGE
12
Feb 26, 2026
4.98Completeness
12
Feb 26, 2026
5Completeness Score
12
Feb 26, 2026
22.32ROUGE-L
12
Jun 9, 2026
83BERTScore
12
Jun 2, 2026
20.93ROUGE-L
12
Feb 26, 2026
22.46ROUGE-L
12
Feb 26, 2026
31.46ROUGE-L
12
Feb 26, 2026
6,573Edit Distance
12
Feb 26, 2026
19.23ROUGE
12
Feb 26, 2026
51Precision
12
Feb 26, 2026
42.96ROUGE-1
12
Feb 26, 2026
36.05ROUGE-1 Score
12
Feb 26, 2026
29.15BLEU-1
11
Feb 27, 2026
22.03GM
11
Feb 26, 2026
39.1ROUGE-L
11
Feb 26, 2026
56.86Win Rate (GPT-4o)
11
Feb 27, 2026
48Completeness
11
Feb 26, 2026
43Completeness
11
Feb 26, 2026
66Completeness
11
Feb 26, 2026
0.72Completeness
11
Feb 26, 2026
4.54Tau
11
Feb 26, 2026
30.16ROUGE-1 Recall
11
Feb 26, 2026