summarization benchmark
XLSum English
Large-scale multilingual abstractive summarization dataset comprising 1 million professionally annotated article-summary pairs from BBC, covering 44 languages. XL-Sum is highly abstractive, concise, and of high quality, designed to encourage research on multilingual abstractive summarization tasks.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
XLSum English leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | NV | 31.6% | 100.0% | 1 | C |
XLSum English highlights
The top published results on this benchmark's own scale.
What is XLSum English?
Definition and scoring fields from the benchmark registry.
Large-scale multilingual abstractive summarization dataset comprising 1 million professionally annotated article-summary pairs from BBC, covering 44 languages. XL-Sum is highly abstractive, concise, and of high quality, designed to encourage research on multilingual abstractive summarization tasks.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- XLSum English
- Modality
- text
- Primary category
- summarization
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- xlsum-english|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about XLSum English.
Which model scores highest on XLSum English?
Llama 3.1 Nemotron 70B Instruct is currently ranked first with 31.6%.
What does XLSum English measure?
Large-scale multilingual abstractive summarization dataset comprising 1 million professionally annotated article-summary pairs from BBC, covering 44 languages. XL-Sum is highly abstractive, concise, and of high quality, designed to encourage research on multilingual abstractive summarization tasks.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.