Lucie-7B — benchmark results

Provider: OpenLLM-France. Released 2024-10-10. Access: Open.

Unified ELO 1328 ± 25, rank #1476 of 1776 rated models, from 30 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Spanish NLU - Sentiment Headlines ES41.13Sentiment classification Score (%)55.6
EuroEval Italian NLU - Sentipolc1646.33Sentiment classification Score (%)43
EuroEval Portuguese NLU - MultiWikiQA PT65.42Reading comprehension Score (%)39.2
EuroEval Portuguese NLU - SST-2 PT69.84Sentiment classification Score (%)35.7
EuroEval Spanish NLU - ScaLA ES2.69Linguistic acceptability Score (%)34.1
Open LLM Leaderboard - MuSR6.81Score32.2
EuroEval Portuguese NLU40.55NLU Average Score (%)30.3
EuroEval Portuguese NLU - ScaLA PT2.61Linguistic acceptability Score (%)28
EuroEval Italian NLU - ScaLA IT4.58Linguistic acceptability Score (%)27.7
Open LLM Leaderboard - GPQA3.02Score27.6
EuroEval Portuguese27.67Average Score (%)24
EuroEval Spanish NLU29.29NLU Average Score (%)23.4

Interactive version: theaggregate.ai/model?slug=lucie-7b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.