language benchmark
Translation en→Set1 spBleu
Translation evaluation using spBLEU (SentencePiece BLEU), a BLEU metric computed over text tokenized with a language-agnostic SentencePiece subword model. Introduced in the FLORES-101 evaluation benchmark for low-resource and multilingual machine translation.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
Translation en→Set1 spBleu Ranking
Higher score ranks better on this benchmark.
| 01 | AM Nova ProAmazon | 43.4% | 100.0% | 3 | C | |
| 02 | AMNova LiteAmazon | 41.5% | 50.0% | 3 | C | |
| 03 | AMNova MicroAmazon | 40.2% | 0.0% | 3 | C |
Translation en→Set1 spBleu Score Distribution
A closer view of the leading scores on this benchmark.
Translation en→Set1 spBleu Highlights
The leading models and scores on this benchmark.
What is Translation en→Set1 spBleu?
What Translation en→Set1 spBleu measures and how its scores work.
Translation evaluation using spBLEU (SentencePiece BLEU), a BLEU metric computed over text tokenized with a language-agnostic SentencePiece subword model. Introduced in the FLORES-101 evaluation benchmark for low-resource and multilingual machine translation.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Translation en→Set1 spBleu
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- translation-en→set1-spbleu|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Translation en→Set1 spBleu.
Which model scores highest on Translation en→Set1 spBleu?
Nova Pro is currently ranked first with 43.4%.
What does Translation en→Set1 spBleu measure?
Translation evaluation using spBLEU (SentencePiece BLEU), a BLEU metric computed over text tokenized with a language-agnostic SentencePiece subword model. Introduced in the FLORES-101 evaluation benchmark for low-resource and multilingual machine translation.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.