List your company

Medical Question Answering on MedQA (Decision-Useful Rate)

89.8Decision-Useful RateHCQR
21.05638.90356.7574.597Mar 19, 2026

Evaluation results

MethodLinks
HCQRBackbone=Qwen3 30B2026.0389.8
HCQRBackbone=Qwen3 4B2026.0383.2
HCQRBackbone=Average2026.0382.1
HCQRBackbone=Llama3.1 8B2026.0381.8
HCQRBackbone=Llama3.2 3B2026.0373.4
RewritingBackbone=Qwen3 30B2026.0365.6
RewritingBackbone=Qwen3 4B2026.0362.2
RewritingBackbone=Average2026.0356.1
HyDEBackbone=Qwen3 30B2026.0354.6
HyDEBackbone=Llama3.1 8B2026.0354.5
HyDEBackbone=Average2026.0353.4
HyDEBackbone=Qwen3 4B2026.0352.8
HyDEBackbone=Llama3.2 3B2026.0351.6
RewritingBackbone=Llama3.1 8B2026.0351.2
RewritingBackbone=Llama3.2 3B2026.0345.2
Rerank-RAGBackbone=Llama3.2 3B2026.0344.1
Rerank-RAGBackbone=Llama3.1 8B2026.0344.1
Rerank-RAGBackbone=Qwen3 4B2026.0344.1
Rerank-RAGBackbone=Qwen3 30B2026.0344.1
Rerank-RAGBackbone=Average2026.0344.1
Simple RAGBackbone=Llama3.2 3B2026.0330
Simple RAGBackbone=Llama3.1 8B2026.0330
Simple RAGBackbone=Qwen3 4B2026.0330
Simple RAGBackbone=Qwen3 30B2026.0330
Simple RAGBackbone=Average2026.0330
MAIN-RAGBackbone=Qwen3 30B2026.0326.7
MAIN-RAGBackbone=Llama3.1 8B2026.0326.4
MAIN-RAGBackbone=Average2026.0325.4
MAIN-RAGBackbone=Qwen3 4B2026.0324.7
MAIN-RAGBackbone=Llama3.2 3B2026.0323.7