Title: European languages %E2%80%94 Benchmarkid | LLM EU
Canonical: https://llmeu.com/et/benchmarks/eu-languages/
Markdown mirror: https://llmeu.com/et/benchmarks/eu-languages.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

# European languages

Mudeli kvaliteet t%C3%B5lgitud Euroopa keelte v%C3%B5rdlusalustel. EU21 read p%C3%A4rinevad OpenGPT-X hindamisest, mis avaldati koos Teuken 7B Instruct v0.6-ga, mis t%C3%B5lgib ARC, HellaSwag, TruthfulQA ja MMLU 21-sse kaetud EL-i keelde ja annab iga mudeli kohta %C3%BChe keskmise. MMMLU rida on Google'i enda mitmekeelne MMLU n%C3%A4itaja Gemma 4 jaoks.

The EU21 numbers are OpenGPT-X%E2%80%99s, taken from the Teuken 7B Instruct v0.6 model card and the accompanying evaluation preprint; they are machine-translated benchmarks, not native-language test sets. The MMMLU number is Google%E2%80%99s own. LLM EU has run no evaluation and has not verified either harness.