Multitask Language Understanding on MMLU Professional Medicine (test)
85.29AccuracyQwen3-32B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-32BType=Instruct2026.04 | 85.29 | |
| Qwen3-8B-BaseType=Base2026.04 | 83.46 | |
| Qwen3-14BType=Instruct2026.04 | 83.46 | |
| MedGemma-27B-itType=BioMed2026.04 | 83.09 | |
| Qwen3-8BType=Instruct2026.04 | 82.35 | |
| Qwen3-4B-BaseType=Base2026.04 | 78.31 | |
| Llama3.1-8B-InstructType=Instruct2026.04 | 76.47 | |
| Qwen3-4BType=Instruct2026.04 | 76.1 | |
| Llama3.2-1BType=Base2026.04 | 69.85 | |
| Llama3.1-8BType=Base2026.04 | 69.85 | |
| Apollo-7BType=BioMed2026.04 | 68.01 | |
| Mistral-7B-v0.3Type=Base2026.04 | 65.07 | |
| Qwen3-1.7B-BaseType=Base2026.04 | 64.71 | |
| Olmo3-7BType=Base2026.04 | 63.6 | |
| Apertus-8B-InstructType=Instruct2026.04 | 62.87 | |
| Mistral-7B-Instruct-v0.3Type=Instruct2026.04 | 62.5 | |
| MedGemma-4B-itType=BioMed2026.04 | 62.13 | |
| Apertus-8BType=Base2026.04 | 60.29 | |
| EuroLLM-9B-InstructType=Instruct2026.04 | 59.56 | |
| GPT-OSS-20BType=Instruct2026.04 | 59.19 | |
| Qwen3-1.7BType=Instruct2026.04 | 58.09 | |
| SmolLM-3BType=Instruct2026.04 | 55.88 | |
| Qwen3-0.6B-BaseType=Base2026.04 | 55.51 | |
| EuroLLM-9BType=Base2026.04 | 55.51 | |
| BioMistral-7BType=BioMed2026.04 | 55.15 | |
| Llama3.2-1B-InstructType=Instruct2026.04 | 51.84 | |
| Gaperon-8BType=Base2026.04 | 48.53 | |
| BaguettotronType=Base2026.04 | 44.85 | |
| Gaperon-1BType=Base2026.04 | 44.85 | |
| Gemma3-270m-ptType=Base2026.04 | 43.38 | |
| Qwen3-0.6BType=Instruct2026.04 | 41.18 | |
| MedGemma-4B-ptType=BioMed2026.04 | 38.24 | |
| Gemma3-270m-itType=Instruct2026.04 | 36.76 | |
| Gemma3-1B-ptType=Base2026.04 | 30.51 | |
| Gemma3-1B-itType=Instruct2026.04 | 27.21 |