language benchmark
Translation Set1→en spBleu
spBLEU (SentencePiece BLEU) evaluation metric for machine translation quality assessment, using language-agnostic SentencePiece tokenization with BLEU scoring. Part of the FLORES-101 evaluation benchmark for low-resource and multilingual machine translation.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
Translation Set1→en spBleu Ranking
Higher score ranks better on this benchmark.
| 1 | AM Nova ProAmazon | 44.4% | 100.0% | 3 | C | |
| 2 | AMNova LiteAmazon | 43.1% | 50.0% | 3 | C | |
| 3 | AMNova MicroAmazon | 42.6% | 0.0% | 3 | C |
Translation Set1→en spBleu Score Distribution
A closer view of the leading scores on this benchmark.
Translation Set1→en spBleu Highlights
The leading models and scores on this benchmark.
What is Translation Set1→en spBleu?
What Translation Set1→en spBleu measures and how its scores work.
spBLEU (SentencePiece BLEU) evaluation metric for machine translation quality assessment, using language-agnostic SentencePiece tokenization with BLEU scoring. Part of 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 Set1→en spBleu
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- translation-set1→en-spbleu|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Translation Set1→en spBleu.
Which model scores highest on Translation Set1→en spBleu?
Nova Pro is currently ranked first with 44.4%.
What does Translation Set1→en spBleu measure?
spBLEU (SentencePiece BLEU) evaluation metric for machine translation quality assessment, using language-agnostic SentencePiece tokenization with BLEU scoring. Part of 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.