EuroLLM-22B-Instruct-2512: benchmark results
The EU-funded EuroLLM project's 22B instruct model covering the 24 official EU languages plus 11 others, trained on EuroHPC compute (December 2025). Provider: EuroLLM. Released 2025-12-01. Access: Open.
Unified ELO 1458 ± 1, rank #1884 of 3078 rated models, from 328 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - PolEmo2-OUT (multiple choice, 5-shot) | 81.98 | Accuracy (%) | 98.4 |
| EuroEval Croatian NLU - MMS HR | 46.07 | Sentiment classification Score (%) | 96.7 |
| EuroEval German NLU - ScaLA DE | 65.65 | Linguistic acceptability Score (%) | 96.6 |
| EuroEval Greek NLU - ScaLA EL | 57.12 | Linguistic acceptability Score (%) | 96.1 |
| EuroEval Italian NLU - ScaLA IT | 59.27 | Linguistic acceptability Score (%) | 96.1 |
| EuroEval Estonian NLU - Grammar ET | 51.64 | Linguistic acceptability Score (%) | 96 |
| EuroEval Portuguese NLU - ScaLA PT | 55.09 | Linguistic acceptability Score (%) | 95 |
| Open PL LLM - PPC (multiple choice, 5-shot) | 80.3 | Accuracy (%) | 93.3 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 50.66 | Sentiment classification Score (%) | 92.7 |
| EuroEval Danish Summarization - Nordjylland News | 37.44 | Score (%) | 92.4 |
| EuroEval Estonian NLU - Estonian Valence | 62.13 | Sentiment classification Score (%) | 92 |
| EuroEval Polish NLU - ScaLA PL | 55.16 | Linguistic acceptability Score (%) | 91.4 |
Interactive version: theaggregate.ai/model?slug=eurollm-22b-instruct-2512 · How It Works · Data refreshed daily, snapshot 2026-09-19.