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

Clinical Case Diagnosis on MedCaseReasoning official (test)

0.9246Accuracy

SEA (Qwen-8b)

Updated 9d ago

Evaluation Results

Method	Links
SEA (Qwen-8b) 2026.04		0.9246	0.8681	0.012
SEA (Qwen-4b) 2026.04		0.8453	0.8176	0.015
Qwen3-8b (RL-DiagnosticRewardOnly) 2026.04		0.7732	0.7231	0.023
Qwen3-4b (RL-DiagnosticRewardOnly) 2026.04		0.7411	0.6954	0.025
Qwen3-4b (SFT) 2026.04		0.7225	0.7012	0.02
Qwen3-8b (SFT) 2026.04		0.721	0.6895	0.02
Qwen3-8b (SFT+ShortTerm-Memory) 2026.04		0.5633	0.5087	0.023
MedGemma-27B 2026.04		0.547	0.5113	0.023
Qwen3-14B 2026.04		0.5035	0.4289	0.024
OLMo3-7B 2026.04		0.4712	0.4385	0.025
Qwen3-8b 2026.04		0.4511	0.4187	0.025
Qwen3-4b 2026.04		0.432	0.4002	0.025
Qwen3-8b (ReAct+ShortTerm-Memory) 2026.04		0.4251	0.383	0.025
LLaMa-3.1-8B 2026.04		0.421	0.3978	0.025