NLP

Measured on OPUS, spaCy, Stanza, Tatoeba, NLLB-200, FLORES-200, Belebele.

Observatories

7 observatories measure NLP.

78 languages

85 language directories; presence of tokenizer_exceptions and a lemmatizer distinguishes a real pipeline from a stub.

88 languages

Per-language pipeline resource listing (tokenize/mwt/pos/lemma/depparse/ner/sentiment/constituency/coref) -- the cleanest pipeline-capability source.

423 languages

Crowdsourced sentence and translation database; counts here are sentence, translation-link, and audio-recording totals per language, from Tatoeba's own exports.

196 languages

Meta's No Language Left Behind translation models covering ~200 languages (FLORES-aligned).

FLORES-200

Open index →

194 languages

Evaluation benchmark for ~200 languages — the de facto baseline for whether a language is evaluable at all.

96 languages

Reading comprehension across 100+ language variants. Presence means evaluable, not merely trainable.

NLP — IDLI