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

Mallin laatu k%C3%A4%C3%A4nnetyiss%C3%A4 eurooppalaisten kielten vertailuarvoissa. EU21-rivit ovat per%C3%A4isin OpenGPT-X-arvioinnista, joka julkaistiin Teuken 7B Instruct v0.6:n kanssa, joka k%C3%A4%C3%A4nt%C3%A4%C3%A4 ARC:n, HellaSwagin, TruthfulQA:n ja MMLU:n 21 kattamalleen EU-kielelle ja raportoi yhden keskiarvon mallia kohti. MMMLU-rivi on Googlen oma monikielinen MMLU-luku Gemma 4:lle.

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.