Multitask Language Understanding on MMLU Professional Medicine FR (test)
84.19AccuracyQwen3-32B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-32BType=Instruct2026.04 | 84.19 | |
| Qwen3-14BType=Instruct2026.04 | 78.68 | |
| MedGemma-27B-itType=BioMed2026.04 | 78.68 | |
| Qwen3-8B-BaseType=Base2026.04 | 76.47 | |
| Qwen3-8BType=Instruct2026.04 | 72.79 | |
| Qwen3-4B-BaseType=Base2026.04 | 69.49 | |
| Qwen3-4BType=Instruct2026.04 | 68.38 | |
| Llama3.1-8B-InstructType=Instruct2026.04 | 61.4 | |
| Apertus-8B-InstructType=Instruct2026.04 | 60.66 | |
| Apollo-7BType=BioMed2026.04 | 59.93 | |
| Apertus-8BType=Base2026.04 | 59.56 | |
| Qwen3-1.7B-BaseType=Base2026.04 | 56.25 | |
| EuroLLM-9B-InstructType=Instruct2026.04 | 56.25 | |
| EuroLLM-9BType=Base2026.04 | 55.88 | |
| Llama3.2-1BType=Base2026.04 | 55.51 | |
| Llama3.1-8BType=Base2026.04 | 55.51 | |
| Mistral-7B-v0.3Type=Base2026.04 | 54.41 | |
| Mistral-7B-Instruct-v0.3Type=Instruct2026.04 | 52.94 | |
| GPT-OSS-20BType=Instruct2026.04 | 52.94 | |
| MedGemma-4B-itType=BioMed2026.04 | 51.47 | |
| SmolLM-3BType=Instruct2026.04 | 49.26 | |
| Olmo3-7BType=Base2026.04 | 48.9 | |
| Qwen3-1.7BType=Instruct2026.04 | 48.16 | |
| BioMistral-7BType=BioMed2026.04 | 46.32 | |
| Gaperon-8BType=Base2026.04 | 42.28 | |
| Qwen3-0.6B-BaseType=Base2026.04 | 37.13 | |
| MedGemma-4B-ptType=BioMed2026.04 | 35.29 | |
| Qwen3-0.6BType=Instruct2026.04 | 33.46 | |
| Gaperon-1BType=Base2026.04 | 30.88 | |
| Llama3.2-1B-InstructType=Instruct2026.04 | 26.47 | |
| Gemma3-1B-ptType=Base2026.04 | 24.63 | |
| Gemma3-270m-ptType=Base2026.04 | 23.16 | |
| BaguettotronType=Base2026.04 | 20.96 | |
| Gemma3-1B-itType=Instruct2026.04 | 20.96 | |
| Gemma3-270m-itType=Instruct2026.04 | 18.75 |