Multiple-choice Question Answering on MMLU Medical subjects (EN/FR Subject Accuracy) benchmark leaderboard · SOTA2 Research

Multiple-choice Question Answering on MMLU Medical subjects (EN/FR Subject Accuracy)

80Anatomy (EN) AccuracyQwen3-32B

Evaluation Results

Method	Links
Qwen3-32B2026.04		80	67.41	86.42	80.38
Qwen3-14B2026.04		79.26	67.41	81.51	78.49
MedGemma-27B-it2026.04		79.26	68.89	81.89	76.98
Qwen3-8B-Base2026.04		74.07	62.22	80	74.72
Qwen3-8B2026.04		73.33	62.96	77.36	74.72
Qwen3-4B-Base2026.04		68.15	54.81	80.38	70.94
Mistral-7B-Instruct-v0.32026.04		64.44	44.44	68.3	60.38
Qwen3-4B2026.04		63.7	57.78	76.23	68.3
Mistral-7B-v0.32026.04		61.48	55.56	65.66	59.25
Llama3.1-8B2026.04		60.74	57.78	72.08	62.26
Apertus-8B2026.04		60	54.81	73.21	66.42
Qwen3-1.7B-Base2026.04		59.26	48.15	67.92	59.25
Apertus-8B-Instruct2026.04		59.26	60.74	70.94	61.89
EuroLLM-9B-Instruct2026.04		59.26	57.04	60.38	59.62
Apollo-7B2026.04		59.26	47.41	69.43	61.51
Olmo3-7B2026.04		57.78	44.44	69.43	55.85
EuroLLM-9B2026.04		57.04	56.3	61.51	59.25
Qwen3-1.7B2026.04		57.04	40.74	63.02	55.09
Gaperon-8B2026.04		54.81	40	55.47	54.72
SmolLM-3B2026.04		54.81	45.93	67.55	60.75
MedGemma-4B-it2026.04		54.81	52.59	61.51	63.02
Llama3.2-1B-Instruct2026.04		51.85	44.44	47.17	38.87
Llama3.1-8B-Instruct2026.04		51.85	44.44	47.17	38.87
GPT-OSS-20B2026.04		48.89	60	66.42	62.26
MedGemma-4B-pt2026.04		48.89	42.96	52.83	48.68
Qwen3-0.6B2026.04		48.15	45.19	50.19	44.53
Qwen3-0.6B-Base2026.04		47.41	29.63	56.98	49.81
BioMistral-7B2026.04		46.67	42.96	63.77	55.47
Gemma3-1B-it2026.04		41.48	34.07	43.77	43.77
Llama3.2-1B2026.04		40.74	26.67	30.57	27.55
Gemma3-1B-pt2026.04		32.59	28.89	21.89	23.77
Gemma3-270m-it2026.04		26.67	22.96	25.28	28.3
Baguettotron2026.04		20	26.67	24.53	24.53
Gaperon-1B2026.04		17.04	19.26	26.79	32.08
Gemma3-270m-pt2026.04		16.3	16.3	28.68	23.77