List your company

Multi-choice Medical Question Answering on Medical QA Multi-choice

70.7MMLU-Med AccuracyMedLA + LLaMA3.1(8B)
18.38831.96945.5559.131Sep 28, 2025

Evaluation results

MethodLinks
MedLA + LLaMA3.1(8B)Method Category=Logic Based, Backbone=LLaMA3.1(8B)2025.0970.762.676.569.9
LLaMA3.1Method Category=General & Medical LLMs with COT, Chain of Thought (CoT)=true, Model Size=8B2025.0968.154.970.664.5
LLaMA3.1 [baseline]Method Category=General & Medical LLMs, Model Size=8B2025.0967.756.368.764.2
LLaMA3Method Category=General & Medical LLMs with COT, Chain of Thought (CoT)=true, Model Size=8B2025.0965.155.264.261.5
MDAgentsMethod Category=Multi Agents2025.096553.46460.8
MedAgentsMethod Category=Multi Agents2025.0964.353.264.160.5
MistralMethod Category=General & Medical LLMs, Model Size=7B2025.0963.447.764.458.5
LLaMA3Method Category=General & Medical LLMs, Model Size=8B2025.0963.456.665.461.8
MistralMethod Category=General & Medical LLMs with COT, Chain of Thought (CoT)=true, Model Size=7B2025.0963.447.465.158.6
DyLANMethod Category=Multi Agents2025.0962.551.663.859.3
MedAlpacaMethod Category=General & Medical LLMs with COT, Chain of Thought (CoT)=true, Model Size=7B2025.0960.339.948.549.6
MV-LLaMA3.1Method Category=Multi Agents, Model Size=8B2025.0960.246.865.257.4
MedAlpacaMethod Category=General & Medical LLMs, Model Size=7B2025.096040.149.349.8
MedRAGMethod Category=RAG Based, Model Size=70B2025.0957.948.771.959.5
Self-RAGMethod Category=RAG Based, Model Size=13B2025.0950.240.864.651.9
KG-RankMethod Category=RAG Based, Model Size=13B2025.0945.236.250.343.9
Self-RAGMethod Category=RAG Based, Model Size=7B2025.0932.23859.443.2
DragonMethod Category=Graph Based2025.0931.947.570.650
QAGNNMethod Category=Graph Based2025.0931.74770.749.8
JointLKMethod Category=Graph Based2025.0928.842.570.647.3
PMC-LLaMAMethod Category=General & Medical LLMs, Model Size=7B2025.0920.724.734.626.7
PMC-LLaMAMethod Category=General & Medical LLMs with COT, Chain of Thought (CoT)=true, Model Size=7B2025.0920.420.820.820.7