Share your thoughts, 1 month free Claude Pro on usSee more

Multitask Language Understanding on MMLU Medical Genetics (test)

94Accuracy (MMLU Medical Genetics)

Qwen3-32B

Updated 9d ago

Evaluation Results

Method	Links
Qwen3-32B 2026.04		94
Qwen3-14B 2026.04		89
MedGemma-27B-it 2026.04		87
Qwen3-8B-Base 2026.04		86
Qwen3-8B 2026.04		86
Llama3.1-8B-Instruct 2026.04		84
Qwen3-4B-Base 2026.04		81
Llama3.2-1B 2026.04		80
Llama3.1-8B 2026.04		80
Qwen3-4B 2026.04		80
Apollo-7B 2026.04		77
Olmo3-7B 2026.04		76
Qwen3-1.7B 2026.04		75
Qwen3-1.7B-Base 2026.04		73
Mistral-7B-v0.3 2026.04		73
Mistral-7B-Instruct-v0.3 2026.04		72.22
EuroLLM-9B 2026.04		69
Apertus-8B 2026.04		67
SmolLM-3B 2026.04		67
MedGemma-4B-it 2026.04		67
Apertus-8B-Instruct 2026.04		65
BioMistral-7B 2026.04		65
GPT-OSS-20B 2026.04		64
EuroLLM-9B-Instruct 2026.04		63
Gaperon-8B 2026.04		62.5
Qwen3-0.6B-Base 2026.04		62
Llama3.2-1B-Instruct 2026.04		57
MedGemma-4B-pt 2026.04		55
Qwen3-0.6B 2026.04		54
Gemma3-1B-it 2026.04		41
Baguettotron 2026.04		30
Gaperon-1B 2026.04		30
Gemma3-1B-pt 2026.04		27
Gemma3-270m-it 2026.04		27
Gemma3-270m-pt 2026.04		25