EuroLLM-1.7B: benchmark results

Provider: EuroLLM. Released 2024-09-24. Access: Open.

Aggregate Rating 1208 ± 17, rank #9405 of 10524 rated models, from 178 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LA Leaderboard - XCOPA Basque52.2Accuracy (%)71.3
LA Leaderboard - HumorQA58.82Accuracy (%)70.6
LA Leaderboard - xStoryCloze Galician60.62Accuracy (%)70.6
LA Leaderboard - WNLI Spanish59.15Accuracy (%)69.9
LA Leaderboard - WiC Basque50Accuracy (%)64.7
Lara Mini Base Report (base-model protocol) - Global PIQA (non-parallel), All Languages (0-shot)56.5Accuracy (%) averaged over all languages/variants of the ben62
LA Leaderboard - MGSM Catalan3.2Exact Match (%)60
LA Leaderboard - MGSM Galician2.8Exact Match (%)60
LA Leaderboard - QNLI Basque51.26Accuracy (%)58.8
LA Leaderboard - caBREU Catalan11.78BLEU58.8
LA Leaderboard - XNLI Spanish48.35Accuracy (%)57.4
Lara Mini Base Report (base-model protocol) - T-HellaSwag, All Languages (0-shot)38Accuracy normalized by answer length (%) averaged over all l57.4

Interactive version: theaggregate.ai/model?slug=eurollm-1-7b · How It Works · Data refreshed daily, snapshot 2026-11-22.