List your company

Medical Evidence Auditing on DrugAudit (test)

0.632EILlama ScoreDrugClaw
0.3460.420250.49450.56875May 31, 2026

Evaluation results

MethodLinks
DrugClawMode=graph2026.050.6320.6230.6850.9180.852
DrugClawMode=linear2026.050.6260.5910.6560.9160.887
DrugClawMode=graph, web-search fallback=disabled2026.050.6220.6280.6630.9310.876
Direct LLMModel=GPT-52026.050.5130.4940.4010.7140.825
Biomni2026.050.4890.470.3560.7930.787
DeepEvidence2026.050.4770.4570.4610.6030.732
Direct LLMModel=GPT-5-mini2026.050.430.4030.2680.8170.815
ToolUniverse2026.050.3570.340.1460.7960.828