Natural Language Understanding on EuroEval French
52.2EuroEval ScoreEuroLLM-9B (Base)
Evaluation results
| Method | Links | |
|---|---|---|
| EuroLLM-9B (Base)Language model=EuroLLM-9B2026.05 | 52.2 | |
| aya-3B (Base)Language model=aya-3B2026.05 | 45.9 | |
| ICR (8B)Parameters=8B, Comparison=EuroLLM-9B2026.05 | 9.9 | |
| MAPO (13B)Parameters=13B, Comparison=EuroLLM-9B2026.05 | 7.4 | |
| aya-3B (Multilingual All Lang SFT)Regime=Multilingual, Post-training=SFT, Data=All Lang2026.05 | 7.2 | |
| aya-3B (Multilingual Max-R SFT)Regime=Multilingual, Post-training=SFT, Data=Max-R2026.05 | 7.2 | |
| aya-3B (Monolingual Max-R SFT)Regime=Monolingual, Post-training=SFT, Data=Max-R2026.05 | 6.8 | |
| EuroLLM-9B (Multilingual All Lang SFT)Regime=Multilingual, Post-training=SFT, Data=All Lang2026.05 | 6.6 | |
| aya-3B (Monolingual In-lang SFT)Regime=Monolingual, Post-training=SFT, Data=In-lang2026.05 | 5.2 | |
| ICR (8B)Parameters=8B, Comparison=aya-3B2026.05 | 3.6 | |
| EuroLLM-9B (Multilingual Max-R SFT)Regime=Multilingual, Post-training=SFT, Data=Max-R2026.05 | 2.7 | |
| EuroLLM-9B (Monolingual In-lang SFT)Regime=Monolingual, Post-training=SFT, Data=In-lang2026.05 | 2 | |
| EuroLLM-9B (Monolingual Max-R SFT)Regime=Monolingual, Post-training=SFT, Data=Max-R2026.05 | 1.3 | |
| MAPO (13B)Parameters=13B, Comparison=aya-3B2026.05 | 1.1 | |
| EuroLLM-9B (Multilingual Paired DPO)Regime=Multilingual, Post-training=DPO, Data=Paired2026.05 | 0.8 | |
| EuroLLM-9B (Monolingual Paired DPO)Regime=Monolingual, Post-training=DPO, Data=Paired2026.05 | 0.6 | |
| aya-3B (Multilingual Paired DPO)Regime=Multilingual, Post-training=DPO, Data=Paired2026.05 | 0.3 | |
| aya-3B (Monolingual Paired DPO)Regime=Monolingual, Post-training=DPO, Data=Paired2026.05 | 0.1 |