List your company

Medical Question Answering on VitalBench Tier A (635) (test)

86Overall AccuracyVitalAgent
17.56835.33453.170.866May 28, 2026

Evaluation results

MethodLinks
VitalAgentSetting=Leakage-free2026.058687.772.999.2
Health-LLMSetting=Oracle, Prompting Strategy=few-shot2026.058272.887.6100
LifeAgent*Setting=Oracle2026.0581.972.587.6100
Health-LLMSetting=Oracle, Prompting Strategy=zero-shot2026.0578.467.884.1100
Health-LLMSetting=Oracle, Prompting Strategy=few-shot CoT2026.0577.664.388.2100
LifeAgent*Setting=Leakage-free2026.0554.547.461.265
Health-LLMSetting=Leakage-free, Prompting Strategy=zero-shot2026.0549.938.961.265
Health-LLMSetting=Leakage-free, Prompting Strategy=few-shot2026.0548.836.562.464.2
Health-LLMSetting=Leakage-free, Prompting Strategy=few-shot CoT2026.0548.334.863.565
PHIASetting=Oracle2026.0539.524.661.251.2
PHIASetting=Leakage-free2026.0520.28.246.517.1