Summarization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
24Informational Content Score
4
Feb 26, 2026
45.12ROUGE-1 Score
4
Feb 26, 2026
28Info Score
4
Feb 26, 2026
30.31ROUGE-1
4
Feb 26, 2026
41.9QA Score
4
Feb 26, 2026
159Non-Redundancy
4
Feb 26, 2026
13.9R Score
3
Jun 8, 2026
51.8R Score
3
Jun 8, 2026
65Best Score
3
Jun 5, 2026
6.45BERTScore F1
3
Jun 2, 2026
14.33BERTScore F1
3
Jun 2, 2026
34.08BERTScore F1
3
Jun 2, 2026
38ROUGE-1 F1
3
Jun 2, 2026
48.18ROUGE-1
3
May 22, 2026
5.13Average Acceptance Length (τ)
3
May 15, 2026
45.9METEOR
3
Apr 24, 2026
30.79ROUGE-L
3
Apr 24, 2026
0.408BLEURT Score
3
Apr 24, 2026
36ROUGE-1
3
Apr 21, 2026
90.5Win Rate
3
Apr 14, 2026
0.643Win Rate
3
Feb 26, 2026
46ROUGE-L
3
Feb 26, 2026
30.91ROUGE-1 Score
3
Feb 26, 2026
182.7Throughput (tokens/s)
3
Feb 26, 2026
0.63Human Rating
3
Feb 26, 2026