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

Medical Diagnosis on AgentClinic OOD original (test)

0.684Similarity (Sim)

Aloe-Beta-70B

Updated 23d ago

Evaluation Results

Method	Links
Aloe-Beta-70B 2026.05		0.684	39.5	39.5
Aloe-Beta-70B 2026.05		0.684	39.5	39.5
MedExAgent-8B 2026.05		0.672	37.8	37.8
MedExAgent-8B 2026.05		0.672	37.8	37.8
MedExAgent-8B 2026.05		0.669	31.8	31.8
MedExAgent-8B 2026.05		0.653	26.6	26.9
Qwen3-32B 2026.05		0.637	31	36.8
Qwen2-32B 2026.05		0.637	31	36.8
HuatuoGPT-o1-70B 2026.05		0.625	23.8	24.9
HuatuoGPT-o1-70B 2026.05		0.625	23.8	24.9
Qwen3-14B 2026.05		0.614	22.6	28.4
Qwen2-14B 2026.05		0.614	22.6	28.4
MedExAgent-8B 2026.05		0.589	28.6	28.9
Llama-3.1-8B-Instruct 2026.05		0.575	22.5	29.8
Llama-3.1-8B-Instruct 2026.05		0.575	22.5	29.8
Qwen3-8B 2026.05		0.565	15.3	21.9
Qwen2-8B 2026.05		0.565	15.3	21.9
MedGemma-27B-text-it 2026.05		0.544	21.4	24.9
MedGemma-27B-text-it 2026.05		0.544	21.4	24.9
MedExAgent-8B 2026.05		0.383	26.1	26.4