Portuguese Educational Proficiency on PT-C
71.4AccuracyAMALIA-9B-SFT
Evaluation results
| Method | Links | |
|---|---|---|
| AMALIA-9B-SFTModel Category=Fully open models, Training=SFT, Instruction-tuned=true2026.03 | 71.4 | |
| AMALIA-9B-DPOModel Category=Fully open models, Training=DPO, Instruction-tuned=true2026.03 | 67.1 | |
| EuroLLM-9BModel Category=Fully open models, Instruction-tuned=true2026.03 | 58.6 | |
| Salamandra-7BModel Category=Fully open models, Instruction-tuned=true2026.03 | 44.3 | |
| Apertus-8BModel Category=Fully open models, Instruction-tuned=true2026.03 | 40 | |
| Qwen 2.5-7BModel Category=Open weight models, Instruction-tuned=true2026.03 | 40 | |
| Ministral-8BModel Category=Open weight models, Instruction-tuned=true2026.03 | 40 | |
| Llama 3.1-8BModel Category=Open weight models, Instruction-tuned=true2026.03 | 38.6 | |
| Gemma 2-9BModel Category=Open weight models, Instruction-tuned=true2026.03 | 34.3 | |
| Mistral-7BModel Category=Open weight models, Instruction-tuned=true2026.03 | 34.3 | |
| OLMo 2-7BModel Category=Fully open models, Instruction-tuned=true2026.03 | 32.9 | |
| Gervasio-8BModel Category=Open weight models, Instruction-tuned=true2026.03 | 30 | |
| Qwen 3-8BModel Category=Open weight models, Instruction-tuned=true2026.03 | 28.6 | |
| Gemma 3-12BModel Category=Open weight models, Instruction-tuned=true2026.03 | 21.4 |