List your company

Medical Question Answering on MedAgentsBench

59.55MedBullets ScoreGSEM
38.510843.972949.43554.8971Mar 23, 2026

Evaluation results

MethodLinks
GSEMBackbone=Qwen3.5-35B2026.0359.5577.0241294169.24
Mem0gBackbone=Qwen3.5-35B2026.0358.4376.836214164.25
VanillaBackbone=Qwen3.5-35B2026.0355.0674.6241274066.74
Mem0Backbone=Qwen3.5-35B2026.0353.9376.836213059.94
GraphRAGBackbone=Qwen3.5-35B2026.0352.817243213061
A-MemBackbone=Qwen3.5-35B2026.0352.8171.9938233665.46
ReMeBackbone=Qwen3.5-35B2026.0351.6976.3835263667.2
Mem0gBackbone=DeepSeek-V3.22026.0350.5674.6237292763.19
Naïve RAGBackbone=Qwen3.5-35B2026.0350.5676.3743243565.38
GSEMBackbone=DeepSeek-V3.22026.0349.4374.8441342770.9
VanillaBackbone=DeepSeek-V3.22026.0348.3174.6240283164.78
A-MemBackbone=DeepSeek-V3.22026.0348.3172.4336263269.01
Naïve RAGBackbone=DeepSeek-V3.22026.0347.1974.8438292768.56
ReMeBackbone=DeepSeek-V3.22026.0347.1974.1837272768.03
FLEXBackbone=DeepSeek-V3.22026.0343.8270.7230241966.06
GraphRAGBackbone=DeepSeek-V3.22026.0342.768.9338272465.61
FLEXBackbone=Qwen3.5-35B2026.0340.4560.6124132256.01
Mem0Backbone=DeepSeek-V3.22026.0339.3273.7436262962.96