EuroLLM-1.7B-Instruct: benchmark results
Provider: EuroLLM. Released 2024-08-06. Access: Open.
Unified ELO 1218 ± 14, rank #1551 of 1632 rated models, from 171 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - WNLI Catalan | 67.61 | Accuracy (%) | 93.4 |
| LA Leaderboard - caBREU Catalan | 14.13 | BLEU | 76.5 |
| LA Leaderboard - EpecKorrefBin Basque | 54 | Accuracy (%) | 75.7 |
| LA Leaderboard - xStoryCloze Galician | 60.03 | Accuracy (%) | 67.6 |
| LA Leaderboard - QNLI Basque | 52.52 | Accuracy (%) | 66.9 |
| LA Leaderboard - XCOPA Basque | 52 | Accuracy (%) | 66.2 |
| LA Leaderboard - ClinTreatES | 56.63 | Semantic Answer Similarity (x100) | 62.7 |
| LA Leaderboard - XNLI Galician | 46.02 | Accuracy (%) | 61.8 |
| LA Leaderboard - NoticIA | 10.18 | ROUGE-1 (%) | 58.5 |
| LA Leaderboard - RagQuAS | 76.85 | Semantic Answer Similarity (x100) | 55.9 |
| LA Leaderboard - CoQCat | 52.58 | F1 (%) | 55.4 |
| LA Leaderboard - Summarization Galician | 4.42 | BLEU | 53.7 |
Interactive version: theaggregate.ai/model?slug=eurollm-1-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-10-08.