List your company

Medical Question Answering on VitalBench Tier B (670) (test)

65.2Overall AccuracyLifeAgent*
12.78426.3924053.608May 28, 2026

Evaluation results

MethodLinks
LifeAgent*Setting=Oracle2026.0565.28041.868.8
Health-LLMSetting=Oracle, Prompting Strategy=zero-shot2026.0558.877.323.268.8
Health-LLMSetting=Oracle, Prompting Strategy=few-shot2026.0555.872.940.249.8
VitalAgentSetting=Leakage-free2026.0555.774.144.344.3
Health-LLMSetting=Oracle, Prompting Strategy=few-shot CoT2026.0549.662.741.841.2
Health-LLMSetting=Leakage-free, Prompting Strategy=few-shot2026.053056.119.19.5
Health-LLMSetting=Leakage-free, Prompting Strategy=few-shot CoT2026.0529.654.120.19.5
LifeAgent*Setting=Leakage-free2026.0528.754.516.59.5
Health-LLMSetting=Leakage-free, Prompting Strategy=zero-shot2026.0528.255.313.99.5
PHIASetting=Oracle2026.0522.73127.88.6
PHIASetting=Leakage-free2026.0514.824.319.10