Medical LLM Evaluation on LLMEval Med

73.5Reasoning Score

Gemini-2.5-Pro

Updated 26d ago

Evaluation Results

Method
Gemini-2.5-Pro 2026.02	73.5	72.5	60.1	-
Qwen3-235B-Instruct 2026.02	65.7	76.2	61.5	-
Baichuan-M2-32B 2026.02	64.2	63.8	64.2	-
o3 2026.02	63.8	66.9	65.8	-
Deepseek-R1 2026.02	63.4	69.6	69.6	-
GPT-4.1 2026.02	60.4	57.3	58.8	-
Qwen3-30B-A3B-Instruct + More Query Rubrics 2026.02	59.8	79.8	57.8	-
Qwen3-32B 2026.02	59.1	62.3	59.3	-
Claude-3.7-Sonnet 2026.02	57.8	75.2	54	-
HuatuoGPT-o1-72B 2026.02	56.9	56.3	49.5	-
Qwen3-30B-A3B-Instruct 2026.02	54.9	67	52.1	-
Qwen3-4B-Instruct + Doctor Rubrics 2026.02	46.1	81.7	55.9	-
Qwen3-4B-Instruct + More Query Rubrics 2026.02	44.7	87.2	55.4	-
Qwen3-4B-Instruct + Principle Rubrics 2026.02	42.2	80.7	52.6	-
Qwen3-4B-Instruct 2026.02	39.2	66.1	49.8	-
Qwen3-4B-Instruct + Draft Rubrics 2026.02	39.2	85.3	52.6	-
Qwen2.5-7B-Instruct 2026.03	-	-	-	56
SFT 2026.03	-	-	-	34.8
DPO 2026.03	-	-	-	35.8
RLVR 2026.03	-	-	-	60.5
HeRL 2026.03	-	-	-	65
Llama-3.2-3B-Instruct 2026.03	-	-	-	16.1
SFT 2026.03	-	-	-	15.1
DPO 2026.03	-	-	-	11.5
RLVR 2026.03	-	-	-	18.5
HeRL 2026.03	-	-	-	18.7
Qwen3-4B-Instruct-2507 2026.03	-	-	-	74.5
SFT 2026.03	-	-	-	73.3
DPO 2026.03	-	-	-	74.9
RLVR 2026.03	-	-	-	78.1
HeRL 2026.03	-	-	-	79.3