List your company

Clinical Question Answering on MedXpertQA Multimodal modality (offline)

54.73AccuracyGM
31.53837.55943.5849.601Jun 8, 2026

Evaluation results

MethodLinks
GMBackbone=Qwen3.6-Plus, Setting=Offline2026.0654.73
SkeMexBackbone=Qwen3.6-Plus, Setting=Offline2026.0654.73
AWMBackbone=Qwen3.6-Plus, Setting=Offline2026.0652.7
MempBackbone=Qwen3.6-Plus, Setting=Offline2026.0652.03
Agent KBBackbone=Qwen3.6-Plus, Setting=Offline2026.0652.03
EvolverBackbone=Qwen3.6-Plus, Setting=Offline2026.0652.03
GSEMBackbone=Qwen3.6-Plus, Setting=Offline2026.0652.03
SkillWeaverBackbone=Qwen3.6-Plus, Setting=Offline2026.0651.35
CFMBackbone=Qwen3.6-Plus, Setting=Offline2026.0651.35
SkeMexBackbone=DeepSeek-V3.2, Setting=Offline2026.0650.68
DILUBackbone=Qwen3.6-Plus, Setting=Offline2026.0650.68
ExPeLBackbone=Qwen3.6-Plus, Setting=Offline2026.0650.68
DCBackbone=Qwen3.6-Plus, Setting=Offline2026.0650
VoyagerBackbone=Qwen3.6-Plus, Setting=Offline2026.0649.32
MobileEBackbone=Qwen3.6-Plus, Setting=Offline2026.0649.32
GSEMBackbone=DeepSeek-V3.2, Setting=Offline2026.0648.65
ReflexionBackbone=Qwen3.6-Plus, Setting=Offline2026.0648.65
CRITICBackbone=Qwen3.6-Plus, Setting=Offline2026.0648.65
ReActBackbone=Qwen3.6-Plus, Setting=Offline2026.0647.3
ReActBackbone=DeepSeek-V3.2, Setting=Offline2026.0646.62
DILUBackbone=DeepSeek-V3.2, Setting=Offline2026.0646.62
GMBackbone=DeepSeek-V3.2, Setting=Offline2026.0646.62
Agent KBBackbone=DeepSeek-V3.2, Setting=Offline2026.0646.62
EvolverBackbone=DeepSeek-V3.2, Setting=Offline2026.0646.62
DCBackbone=DeepSeek-V3.2, Setting=Offline2026.0646.62
ReflexionBackbone=DeepSeek-V3.2, Setting=Offline2026.0645.95
VoyagerBackbone=DeepSeek-V3.2, Setting=Offline2026.0645.95
ExPeLBackbone=DeepSeek-V3.2, Setting=Offline2026.0645.95
AWMBackbone=DeepSeek-V3.2, Setting=Offline2026.0645.95
MempBackbone=DeepSeek-V3.2, Setting=Offline2026.0644.59
SkillWeaverBackbone=DeepSeek-V3.2, Setting=Offline2026.0644.59
CFMBackbone=DeepSeek-V3.2, Setting=Offline2026.0644.59
CoTBackbone=DeepSeek-V3.2, Setting=Offline2026.0642.57
MobileEBackbone=DeepSeek-V3.2, Setting=Offline2026.0642.57
CoTBackbone=MedGemma-27B, Setting=Offline2026.0641.89
CRITICBackbone=DeepSeek-V3.2, Setting=Offline2026.0641.22
CoTBackbone=HuluMed-32B, Setting=Offline2026.0638.51
CoTBackbone=Lingshu-32B, Setting=Offline2026.0632.43