EuroLLM-9B: benchmark results
Provider: EuroLLM. Released 2025-02-01. Access: Open.
Unified ELO 1394 ± 15, rank #1224 of 1632 rated models, from 413 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - CatalanQA | 84.2 | F1 (%) | 100 |
| LA Leaderboard - caBREU Catalan | 19.55 | BLEU | 100 |
| EuroEval Finnish NLU - Tydiqa FI | 77.33 | Reading comprehension Score (%) | 99.2 |
| LA Leaderboard - OpenBookQA Galician | 33.4 | Accuracy (%) | 98.5 |
| LA Leaderboard - xStoryCloze Galician | 70.75 | Accuracy (%) | 97.1 |
| LA Leaderboard - XL-Sum Spanish | 3.77 | BLEU | 97 |
| LA Leaderboard - CoQCat | 76.1 | F1 (%) | 96.9 |
| LA Leaderboard - XQuAD Catalan | 75.09 | F1 (%) | 96.9 |
| EuroEval Dutch Simplification - Duidelijke Taal | 56.49 | Score (%) | 96.6 |
| LA Leaderboard - OpenBookQA Spanish | 37.8 | Accuracy (%) | 95.6 |
| LA Leaderboard - TE-ca | 52.24 | Accuracy (%) | 95.6 |
| EuroEval Czech NLU - CSFD Sentiment | 64.86 | Sentiment classification Score (%) | 94.3 |
Interactive version: theaggregate.ai/model?slug=eurollm-9b · How It Works · Data refreshed daily, snapshot 2026-10-08.