List your company

Clinical Question Answering on HealthBench (offline)

31.79AccuracySkeMex
7.963614.149320.33526.5207Jun 8, 2026

Evaluation results

MethodLinks
SkeMexBackbone=Qwen3.6-Plus, Setting=Offline2026.0631.79
GMBackbone=Qwen3.6-Plus, Setting=Offline2026.0628.66
CFMBackbone=Qwen3.6-Plus, Setting=Offline2026.0628.28
SkeMexBackbone=DeepSeek-V3.2, Setting=Offline2026.0627.65
GSEMBackbone=Qwen3.6-Plus, Setting=Offline2026.0627.57
ExPeLBackbone=Qwen3.6-Plus, Setting=Offline2026.0627.56
MobileEBackbone=Qwen3.6-Plus, Setting=Offline2026.0627.5
SkillWeaverBackbone=Qwen3.6-Plus, Setting=Offline2026.0627.36
Agent KBBackbone=Qwen3.6-Plus, Setting=Offline2026.0627.23
ReflexionBackbone=Qwen3.6-Plus, Setting=Offline2026.0626.89
DILUBackbone=Qwen3.6-Plus, Setting=Offline2026.0626.89
MempBackbone=Qwen3.6-Plus, Setting=Offline2026.0626.74
AWMBackbone=Qwen3.6-Plus, Setting=Offline2026.0626.6
CRITICBackbone=Qwen3.6-Plus, Setting=Offline2026.0626.29
GSEMBackbone=DeepSeek-V3.2, Setting=Offline2026.0626
EvolverBackbone=Qwen3.6-Plus, Setting=Offline2026.0625.85
VoyagerBackbone=Qwen3.6-Plus, Setting=Offline2026.0625.44
DCBackbone=Qwen3.6-Plus, Setting=Offline2026.0625.06
ReflexionBackbone=DeepSeek-V3.2, Setting=Offline2026.0624.54
ReActBackbone=Qwen3.6-Plus, Setting=Offline2026.0623.98
DCBackbone=DeepSeek-V3.2, Setting=Offline2026.0623.76
VoyagerBackbone=DeepSeek-V3.2, Setting=Offline2026.0623.74
ExPeLBackbone=DeepSeek-V3.2, Setting=Offline2026.0623.63
GMBackbone=DeepSeek-V3.2, Setting=Offline2026.0623.49
SkillWeaverBackbone=DeepSeek-V3.2, Setting=Offline2026.0623.42
DILUBackbone=DeepSeek-V3.2, Setting=Offline2026.0623.37
CFMBackbone=DeepSeek-V3.2, Setting=Offline2026.0623.26
Agent KBBackbone=DeepSeek-V3.2, Setting=Offline2026.0623.08
AWMBackbone=DeepSeek-V3.2, Setting=Offline2026.0622.84
CoTBackbone=DeepSeek-V3.2, Setting=Offline2026.0622.42
MobileEBackbone=DeepSeek-V3.2, Setting=Offline2026.0621.97
EvolverBackbone=DeepSeek-V3.2, Setting=Offline2026.0621.59
CRITICBackbone=DeepSeek-V3.2, Setting=Offline2026.0621.53
MempBackbone=DeepSeek-V3.2, Setting=Offline2026.0621.44
ReActBackbone=DeepSeek-V3.2, Setting=Offline2026.0619.06
CoTBackbone=MedGemma-27B, Setting=Offline2026.0614.83
CoTBackbone=HuluMed-32B, Setting=Offline2026.069.11
CoTBackbone=Lingshu-32B, Setting=Offline2026.068.88