List your company

Medical Question Answering on MedQA (Accuracy and Prompting Deltas)

92.8AccuracyOctoToolsbase
84.16886.40988.6590.891Feb 16, 2025

Evaluation results

MethodLinks
OctoToolsbaseBackbone=gpt-4o-2024-08-06, Modality=Text, Domain=Medical, Visual Understanding=false, Numerical Calculation=false, Knowledge Retrieval=true, Multi-step Reasoning=false2025.0292.8——
OctoToolsBackbone=gpt-4o-2024-08-06, Modality=Text, Domain=Medical, Visual Understanding=false, Numerical Calculation=false, Knowledge Retrieval=true, Multi-step Reasoning=false2025.0291.576.7
CoTBackbone=gpt-4o-2024-08-06, Modality=Text, Domain=Medical, Visual Understanding=false, Numerical Calculation=false, Knowledge Retrieval=true, Multi-step Reasoning=false2025.0284.8——
0-shotBackbone=gpt-4o-2024-08-06, Modality=Text, Domain=Medical, Visual Understanding=false, Numerical Calculation=false, Knowledge Retrieval=true, Multi-step Reasoning=false2025.0284.5——