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

Medical Reasoning on MedBullets and MedXQA

84.87Accuracy (MedBullets)

LLaMA3.2-3B-Instruct (Full-shot)

Updated 1mo ago

Evaluation Results

Method	Links
LLaMA3.2-3B-Instruct (Full-shot) 2026.04		84.87	42.88	63.88
Qwen3-4B-Base (Full-shot) 2026.04		68.09	45.3	56.7
LLaMA3.2-3B-Instruct (HEAL) 2026.04		60.53	32.27	46.4
LLaMA3.2-3B-Instruct (Hybrid) 2026.04		58.55	30.15	44.35
Qwen3-4B-Base (HEAL) 2026.04		57.24	44.39	50.82
LLaMA3.2-3B-Instruct (Few-shot) 2026.04		56.91	31.36	44.14
Qwen3-4B-Base (Hybrid) 2026.04		55.92	42.73	49.33
Qwen3-4B-Base (Few-shot) 2026.04		55.26	43.18	49.22
Qwen3-4B-Base (Only-General) 2026.04		49.67	39.7	44.69
Qwen3-1.7B-Base (HEAL) 2026.04		49.34	40	44.67
Qwen3-1.7B-Base (Full-shot) 2026.04		49.01	40.45	44.73
LLaMA3.2-3B-Instruct (Only-General) 2026.04		48.68	28.48	38.58
Qwen3-1.7B-Base (Hybrid) 2026.04		45.39	38.64	42.02
Qwen3-1.7B-Base (Few-shot) 2026.04		45.07	38.33	41.7
Qwen3-4B-Base 2026.04		43.09	33.93	38.51
Qwen3-1.7B-Base (Only-General) 2026.04		42.11	32.73	37.42
Qwen3-1.7B-Base 2026.04		41.78	31.06	36.42
LLaMA3.2-3B-Instruct 2026.04		40.46	26.82	33.64