Summarization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
20.7ROUGE-2
38
Feb 26, 2026
36.88ROUGE-L
38
Feb 27, 2026
0.372Pearson Correlation
36
Feb 26, 2026
10.64M Score
35
Feb 26, 2026
30.91ROUGE-L Score
33
May 22, 2026
48ROUGE-L
33
Mar 12, 2026
3.58Speedup
32
May 4, 2026
37.82ROUGE 2
31
Apr 7, 2026
43.57ROUGE-L
30
May 22, 2026
27.2ROUGE Score
30
May 15, 2026
6.51MAT Score
30
May 20, 2026
46ROUGE Score
30
May 11, 2026
37F1 Score
30
Feb 26, 2026
91.3BERTScore F1
30
Feb 26, 2026
2.062Mean Auto-Rating (r)
29
Feb 26, 2026
4.325Mean Auto-Rating (r)
29
Feb 26, 2026
4.47Mean Auto-Rating (r)
29
Feb 26, 2026
3.52Mean Auto-Rating (r)
29
Feb 26, 2026
-0.276Hamming Score
28
Feb 26, 2026
69.6Accuracy
28
Feb 26, 2026
34.79F1 Score
28
Feb 26, 2026
51.6ROUGE-L
27
Mar 4, 2026
3.382Speedup Ratio
26
Apr 8, 2026
0.44Overall Score
26
Feb 26, 2026
4.97Comprehensiveness
24
Feb 26, 2026