List your company

Clinical Question Answering on LiveMedBench (offline)

57.95AccuracySkeMex
29.3536.77544.251.625Jun 8, 2026

Evaluation results

MethodLinks
SkeMexBackbone=DeepSeek-V3.2, Setting=Offline2026.0657.95
MempBackbone=DeepSeek-V3.2, Setting=Offline2026.0654.79
Agent KBBackbone=DeepSeek-V3.2, Setting=Offline2026.0654.59
CFMBackbone=DeepSeek-V3.2, Setting=Offline2026.0654.29
GMBackbone=DeepSeek-V3.2, Setting=Offline2026.0654.1
SkeMexBackbone=Qwen3.6-Plus, Setting=Offline2026.0653.97
DILUBackbone=DeepSeek-V3.2, Setting=Offline2026.0653.94
DCBackbone=DeepSeek-V3.2, Setting=Offline2026.0653.76
AWMBackbone=DeepSeek-V3.2, Setting=Offline2026.0653.39
GSEMBackbone=DeepSeek-V3.2, Setting=Offline2026.0653.2
VoyagerBackbone=DeepSeek-V3.2, Setting=Offline2026.0652.74
SkillWeaverBackbone=DeepSeek-V3.2, Setting=Offline2026.0652.15
EvolverBackbone=DeepSeek-V3.2, Setting=Offline2026.0651.86
AWMBackbone=Qwen3.6-Plus, Setting=Offline2026.0650.39
SkillWeaverBackbone=Qwen3.6-Plus, Setting=Offline2026.0650.2
CFMBackbone=Qwen3.6-Plus, Setting=Offline2026.0650.07
DILUBackbone=Qwen3.6-Plus, Setting=Offline2026.0649.97
VoyagerBackbone=Qwen3.6-Plus, Setting=Offline2026.0649.17
MempBackbone=Qwen3.6-Plus, Setting=Offline2026.0649.06
Agent KBBackbone=Qwen3.6-Plus, Setting=Offline2026.0649.01
MobileEBackbone=DeepSeek-V3.2, Setting=Offline2026.0648.96
DCBackbone=Qwen3.6-Plus, Setting=Offline2026.0648.9
ReflexionBackbone=Qwen3.6-Plus, Setting=Offline2026.0648.72
GMBackbone=Qwen3.6-Plus, Setting=Offline2026.0648.69
ReActBackbone=DeepSeek-V3.2, Setting=Offline2026.0648.64
MobileEBackbone=Qwen3.6-Plus, Setting=Offline2026.0648.44
CRITICBackbone=Qwen3.6-Plus, Setting=Offline2026.0647.75
GSEMBackbone=Qwen3.6-Plus, Setting=Offline2026.0647.61
ExPeLBackbone=Qwen3.6-Plus, Setting=Offline2026.0647.42
EvolverBackbone=Qwen3.6-Plus, Setting=Offline2026.0647.26
ReActBackbone=Qwen3.6-Plus, Setting=Offline2026.0646.93
CoTBackbone=DeepSeek-V3.2, Setting=Offline2026.0644.93
CoTBackbone=MedGemma-27B, Setting=Offline2026.0640.64
CRITICBackbone=DeepSeek-V3.2, Setting=Offline2026.0639.26
ReflexionBackbone=DeepSeek-V3.2, Setting=Offline2026.0638.75
ExPeLBackbone=DeepSeek-V3.2, Setting=Offline2026.0637.72
CoTBackbone=HuluMed-32B, Setting=Offline2026.0635.58
CoTBackbone=Lingshu-32B, Setting=Offline2026.0630.45