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.

Llama 3.1 Nemotron 70B Instruct from NVIDIA currently leads the XLSum English leaderboard with a score of 0.316 across 1 evaluated AI models.

Paper

Progress Over Time

Interactive timeline showing model performance evolution on XLSum English

State-of-the-art frontier
Open
Proprietary

XLSum English Leaderboard

1 models
ContextCostLicense
170B
Notice missing or incorrect data?

FAQ

Common questions about XLSum English.

What is the XLSum English benchmark?

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.

What is the XLSum English leaderboard?

The XLSum English leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Llama 3.1 Nemotron 70B Instruct by NVIDIA leads with a score of 0.316. The average score across all models is 0.316.

What is the highest XLSum English score?

The highest XLSum English score is 0.316, achieved by Llama 3.1 Nemotron 70B Instruct from NVIDIA.

How many models are evaluated on XLSum English?

1 models have been evaluated on the XLSum English benchmark, with 0 verified results and 1 self-reported results.

Where can I find the XLSum English paper?

The XLSum English paper is available at https://arxiv.org/abs/2106.13822. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does XLSum English cover?

XLSum English is categorized under language and summarization. The benchmark evaluates text models with multilingual support.

More evaluations to explore

Related benchmarks in the same category

View all language
MMLU-Pro

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.

language
119 models
MMLU

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

language
99 models
MMLU-Redux

An improved version of the MMLU benchmark featuring manually re-annotated questions to identify and correct errors in the original dataset. Provides more reliable evaluation metrics for language models by addressing dataset quality issues found in the original MMLU.

language
45 models
MMMLU

Multilingual Massive Multitask Language Understanding dataset released by OpenAI, featuring professionally translated MMLU test questions across 14 languages including Arabic, Bengali, German, Spanish, French, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese, Swahili, Yoruba, and Chinese. Contains approximately 15,908 multiple-choice questions per language covering 57 subjects.

language
45 models
MMLU-ProX

Extended version of MMLU-Pro providing additional challenging multiple-choice questions for evaluating language models across diverse academic and professional domains. Built on the foundation of the Massive Multitask Language Understanding benchmark framework.

language
29 models
BIG-Bench Hard

BIG-Bench Hard (BBH) is a subset of 23 challenging BIG-Bench tasks selected because prior language model evaluations did not outperform average human-rater performance. The benchmark contains 6,511 evaluation examples testing various forms of multi-step reasoning including arithmetic, logical reasoning (Boolean expressions, logical deduction), geometric reasoning, temporal reasoning, and language understanding. Tasks require capabilities such as causal judgment, object counting, navigation, pattern recognition, and complex problem solving.

language
21 models