English
9/10/es-8/fr-8/de-8/zh-7
English (ISO 639-3 eng). In words: billions of fluent speakers; tens of billions of monolingual sentences; hundreds of millions of sentences parallel with Spanish, hundreds of millions of sentences parallel with French, hundreds of millions of sentences parallel with German, tens of millions of sentences parallel with Chinese.
Score breakdown
| Component | Digit | Raw count | Reads as | Top corpus |
|---|---|---|---|---|
| Speakers (S) | 9 | 1,132,366,680 | billions | — |
| Monolingual (M) | 10 | 34,924,619,246 | tens of billions | — |
Bilingual · Spanish (es) | 8 | 409,061,333 | hundreds of millions | CCMatrix |
Bilingual · French (fr) | 8 | 328,595,738 | hundreds of millions | CCMatrix |
Bilingual · German (de) | 8 | 278,316,474 | hundreds of millions | ParaCrawl |
Bilingual · Chinese (zh) | 7 | 71,383,325 | tens of millions | CCMatrix |
Benchmark performance
Published zero-shot results used to validate the notation (see the RAN Paper).
| Task | Benchmark | Metric | Score |
|---|---|---|---|
| NER | XTREME WikiANN XLM-R Large | F1 | 84.7 |
| POS | XTREME UD XLM-R Large | Accuracy | 96.1 |
Sources
- Wikidata: Q1860
- Counts use the sources this site applies consistently (see the overview) — Ethnologue (speakers), OSCAR 23.01 (monolingual), OPUS (bilingual) — except where this page's notes record a different source. The top corpus for each bilingual partner is shown in the breakdown above.
See the RAN overview for how scores are computed and what they mean.