Natural Language Understanding on EuroEval Italian
54.3EuroEval ScoreEuroLLM-9B (Base)
Evaluation Results
| Method | Links | |
|---|---|---|
| EuroLLM-9B (Base)Language model=EuroLLM-9B2026.05 | 54.3 | |
| aya-3B (Base)Language model=aya-3B2026.05 | 51.6 | |
| aya-3B (Multilingual All Lang SFT)Regime=Multilingual, Post-training=SFT, Data=All Lang2026.05 | 11.3 | |
| aya-3B (Monolingual In-lang SFT)Regime=Monolingual, Post-training=SFT, Data=In-lang2026.05 | 10.7 | |
| aya-3B (Monolingual Max-R SFT)Regime=Monolingual, Post-training=SFT, Data=Max-R2026.05 | 10.6 | |
| aya-3B (Multilingual Max-R SFT)Regime=Multilingual, Post-training=SFT, Data=Max-R2026.05 | 10.5 | |
| EuroLLM-9B (Multilingual All Lang SFT)Regime=Multilingual, Post-training=SFT, Data=All Lang2026.05 | 9.9 | |
| EuroLLM-9B (Monolingual In-lang SFT)Regime=Monolingual, Post-training=SFT, Data=In-lang2026.05 | 7.6 | |
| EuroLLM-9B (Multilingual Max-R SFT)Regime=Multilingual, Post-training=SFT, Data=Max-R2026.05 | 5 | |
| EuroLLM-9B (Monolingual Paired DPO)Regime=Monolingual, Post-training=DPO, Data=Paired2026.05 | 3.6 | |
| EuroLLM-9B (Multilingual Paired DPO)Regime=Multilingual, Post-training=DPO, Data=Paired2026.05 | 1.3 | |
| EuroLLM-9B (Monolingual Max-R SFT)Regime=Monolingual, Post-training=SFT, Data=Max-R2026.05 | 1.2 | |
| aya-3B (Multilingual Paired DPO)Regime=Multilingual, Post-training=DPO, Data=Paired2026.05 | 0.6 | |
| aya-3B (Monolingual Paired DPO)Regime=Monolingual, Post-training=DPO, Data=Paired2026.05 | 0.4 |