BLEU score for English-to-Spanish translation on the FLORES-200 devtest set, as reported in this repository's model cards.
unassessed
| Category | translation |
|---|---|
| Subcategory | en-es |
| Page status | active |
| Metric | BLEU |
| Direction | higher_is_better |
| Unit | % |
| Dataset size | 1012 |
| Dataset licence | CC BY-SA 4.0 |
| Publisher | Meta AI (FAIR), NLLB Team; now maintained by the Open Language Data Initiative (OLDI) |
flores_en_es scores how well a model translates the FLORES-200 devtest sentences from English into Spanish, one of the highest-resource pairs in the benchmark and one of the most heavily represented languages in web training data.
Translate the 1012 FLORES-200 devtest sentences from English into Spanish; score against the human Spanish reference.
| Model | Provider | Score | Card as of |
|---|---|---|---|
| GPT-4 | OpenAI | 71.2 | 2026-04 |
| GPT-4 Turbo | OpenAI | 71.2 | 2026-04 |
| GPT-4o | OpenAI | 71.2 | 2026-04 |
| GPT-4o (2024-05-13) | OpenAI | 71.2 | 2026-04 |
| GPT-4o (2024-08-06) | OpenAI | 71.2 | 2026-04 |
| GPT-4o (2024-11-20) | OpenAI | 71.2 | 2026-04 |
| GPT-4o mini | OpenAI | 71.2 | 2026-04 |
| Claude Sonnet 3.5 | Anthropic | 70.8 | 2026-04 |
| Claude Sonnet 3.5 v2 | Anthropic | 70.8 | 2026-04 |
| Gemini 1.5 Flash | Google DeepMind | 68.1 | 2026-04 |
| Gemini 1.5 Flash-8B | Google DeepMind | 68.1 | 2026-04 |
| Gemini 1.5 Pro | Google DeepMind | 68.1 | 2026-04 |
| Gemini 2.0 Flash | Google DeepMind | 68.1 | 2026-04 |
| Gemini 2.5 Flash | Google DeepMind | 68.1 | 2026-04 |
| Gemini 2.5 Pro | Google DeepMind | 68.1 | 2026-04 |