FLORES-200
A multilingual machine translation evaluation benchmark released by Meta, covering 200 languages. It provides standardized evaluation datasets to support machine translation research for low-resource languages.
Timeline (last 90 days)
FLORES devtest is the development test set in the FLORES-200 dataset released by Meta AI, with about 1,012 sentences per language, drawn from public texts such as Wikipedia and manually proofread.
Existing evaluation benchmarks such as XNLI and FLORES-200 mostly operate at the granularity of language codes and do not distinguish regional variants within the same language code.
All Facts (2)
FLORES devtest is the development test set in the FLORES-200 dataset released by Meta AI, with about 1,012 sentences per language, drawn from public texts such as Wikipedia and manually proofread.
50%UnverifiedExisting evaluation benchmarks such as XNLI and FLORES-200 mostly operate at the granularity of language codes and do not distinguish regional variants within the same language code.
50%