Health Evaluation on MMLU-Pro Health (FR) X (test)
66.08AccuracyQwen3-32B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-32BType=Instruct2026.04 | 66.08 | |
| MedGemma-27B-itType=BioMed2026.04 | 61.86 | |
| Qwen3-14BType=Instruct2026.04 | 56.48 | |
| Qwen3-8B-BaseType=Base2026.04 | 50.22 | |
| Qwen3-8BType=Instruct2026.04 | 48.18 | |
| Apertus-8B-InstructType=Instruct2026.04 | 41.92 | |
| Qwen3-4BType=Instruct2026.04 | 41.63 | |
| Qwen3-4B-BaseType=Base2026.04 | 39.3 | |
| Llama3.1-8B-InstructType=Instruct2026.04 | 36.39 | |
| Apertus-8BType=Base2026.04 | 36.1 | |
| GPT-OSS-20BType=Instruct2026.04 | 35.81 | |
| Mistral-7B-Instruct-v0.3Type=Instruct2026.04 | 34.21 | |
| MedGemma-4B-itType=BioMed2026.04 | 31.3 | |
| EuroLLM-9B-InstructType=Instruct2026.04 | 30.86 | |
| Apollo-7BType=BioMed2026.04 | 30.71 | |
| SmolLM-3BType=Instruct2026.04 | 29.4 | |
| EuroLLM-9BType=Base2026.04 | 29.11 | |
| Llama3.1-8BType=Base2026.04 | 28.53 | |
| Mistral-7B-v0.3Type=Base2026.04 | 27.22 | |
| Qwen3-1.7B-BaseType=Base2026.04 | 25.91 | |
| Qwen3-1.7BType=Instruct2026.04 | 25.91 | |
| Gaperon-8BType=Base2026.04 | 20.52 | |
| BioMistral-7BType=BioMed2026.04 | 20.23 | |
| MedGemma-4B-ptType=BioMed2026.04 | 18.49 | |
| Olmo3-7BType=Base2026.04 | 18.2 | |
| Llama3.2-1B-InstructType=Instruct2026.04 | 16.45 | |
| Qwen3-0.6B-BaseType=Base2026.04 | 15.87 | |
| Qwen3-0.6BType=Instruct2026.04 | 14.41 | |
| Gemma3-1B-itType=Instruct2026.04 | 13.68 | |
| Llama3.2-1BType=Base2026.04 | 10.77 | |
| Gemma3-270m-itType=Instruct2026.04 | 10.63 | |
| Gemma3-1B-ptType=Base2026.04 | 9.75 | |
| Gemma3-270m-ptType=Base2026.04 | 9.46 | |
| Gaperon-1BType=Base2026.04 | 7.57 | |
| BaguettotronType=Base2026.04 | 6.26 |