Title: European languages %E2%80%94 Benchmarks | LLM EU
Canonical: https://llmeu.com/nl/benchmarks/eu-languages/
Markdown mirror: https://llmeu.com/nl/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

Modelkwaliteit op vertaalde Europese-taalbenchmarks. De EU21-rijen komen van de OpenGPT-X-evaluatie gepubliceerd met Teuken 7B Instruct v0.6, die ARC, HellaSwag, TruthfulQA en MMLU vertaalt naar de 21 EU-talen die het bestrijkt en %C3%A9%C3%A9n gemiddelde per model rapporteert. De MMMLU-rij is Google's eigen meertalige MMLU-cijfer voor Gemma 4.

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.