Benchmark
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)
Oct 11
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.
Unverified50%