List your company

ResearchFormerly WizWand

Multiple-choice Question Answering on MMLU Medical Subjects (test)

92.36Accuracy (College Biology, EN)Qwen3-14B

Evaluation results

Method	Links
Qwen3-14B2026.04		92.36	89.58	80.92	78.03
Qwen3-32B2026.04		90.28	90.97	82.08	77.46
Qwen3-8B-Base2026.04		88.89	87.5	78.03	75.72
Qwen3-8B2026.04		88.19	85.42	79.19	73.41
MedGemma-27B-it2026.04		85.42	86.81	72.83	73.99
Qwen3-4B-Base2026.04		84.72	75	73.99	68.21
Qwen3-4B2026.04		84.72	73.61	70.52	73.99
Llama3.1-8B-Instruct2026.04		81.94	67.36	65.32	63.01
Apollo-7B2026.04		77.78	62.5	59.54	58.38
Llama3.2-1B2026.04		77.08	62.5	64.74	59.54
Llama3.1-8B2026.04		77.08	62.5	64.74	59.54
Olmo3-7B2026.04		76.39	53.47	70.52	50.87
Apertus-8B-Instruct2026.04		75	67.36	61.27	59.54
Qwen3-1.7B-Base2026.04		72.92	54.17	68.21	59.54
Apertus-8B2026.04		72.92	68.75	61.85	57.8
SmolLM-3B2026.04		72.92	59.72	64.16	55.49
Mistral-7B-Instruct-v0.32026.04		72.22	59.03	60.12	54.34
EuroLLM-9B-Instruct2026.04		71.53	71.53	53.76	54.34
GPT-OSS-20B2026.04		70.83	69.44	54.34	56.07
Mistral-7B-v0.32026.04		70.14	54.86	63.01	53.18
MedGemma-4B-it2026.04		68.75	54.86	55.49	56.65
Qwen3-1.7B2026.04		67.36	49.31	61.85	56.07
EuroLLM-9B2026.04		66.67	66.67	54.34	52.02
Gaperon-8B2026.04		62.5	52.78	47.4	45.09
Qwen3-0.6B-Base2026.04		59.72	39.58	52.6	40.46
MedGemma-4B-pt2026.04		59.03	48.61	49.71	42.77
BioMistral-7B2026.04		59.03	47.22	53.76	50.29
Qwen3-0.6B2026.04		56.25	34.03	47.4	38.15
Llama3.2-1B-Instruct2026.04		46.53	34.03	36.99	28.32
Gemma3-270m-it2026.04		34.72	22.92	21.39	21.39
Gemma3-1B-it2026.04		34.72	36.11	39.31	38.73
Baguettotron2026.04		26.39	18.06	27.17	23.12
Gemma3-1B-pt2026.04		25.69	27.08	21.39	21.97
Gaperon-1B2026.04		22.92	20.14	20.81	21.39
Gemma3-270m-pt2026.04		20.83	21.53	23.7	19.65