Multilingual Summarization
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
34ROUGE-L
8
Feb 26, 2026
0.37Token-level Language Confusion (%)
5
Jun 9, 2026
0.23Token-level Language Confusion
5
Jun 9, 2026
0.38Token-level Language Confusion
5
Jun 9, 2026
3.45Token-level Language Confusion
5
Jun 9, 2026
11Token-level Language Confusion (%)
5
Jun 9, 2026
3.51Token-level Language Confusion
5
Jun 9, 2026
4.78Token-level Language Confusion (%)
5
Jun 9, 2026
0.28Token-level Language Confusion
5
Jun 9, 2026
20.5Training Time (h)
2
Feb 26, 2026
22.5Training Time (h)
2
Feb 26, 2026