EuroLLM-22B: benchmark results
Provider: EuroLLM.
Aggregate Rating 1536 ± 40, rank #1886 of 10916 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Greek MMLU - Humanities | 75.35 | Accuracy (%) | 87.7 |
| Greek MMLU - Other | 68.44 | Accuracy (%) | 80.2 |
| Greek MMLU - Greek-Specific | 77.46 | Accuracy (%) | 77.8 |
| Greek MMLU | 70.43 | Accuracy (%) | 75.3 |
| Greek MMLU - Social Sciences | 73.49 | Accuracy (%) | 75.3 |
| Greek MMLU - STEM | 66.94 | Accuracy (%) | 74.1 |
| P3B3 | 88.5 | LLM pt-PT (↑) (self-reported) | 63.2 |
| WMT25 English-Maasai chrF++ | 20.3 | chrF++ | 48.1 |
| CommunityFact | 59.23 | Overall (self-reported) | 37.5 |
| WMT25 English-Bhojpuri chrF++ | 26.4 | chrF++ | 23.5 |
| WMT25 English-Maasai ESA | 0.5 | ESA Human Score | 0 |
Interactive version: theaggregate.ai/model?slug=eurollm-22b · How It Works · Data refreshed daily, snapshot 2026-11-08.