Clinical Question Answering on MedXpertQA Multimodal modality (offline)
54.73AccuracyGM
Evaluation Results
| Method | Links | |
|---|---|---|
| GMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 54.73 | |
| SkeMexBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 54.73 | |
| AWMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 52.7 | |
| MempBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 52.03 | |
| Agent KBBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 52.03 | |
| EvolverBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 52.03 | |
| GSEMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 52.03 | |
| SkillWeaverBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 51.35 | |
| CFMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 51.35 | |
| SkeMexBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 50.68 | |
| DILUBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 50.68 | |
| ExPeLBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 50.68 | |
| DCBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 50 | |
| VoyagerBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 49.32 | |
| MobileEBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 49.32 | |
| GSEMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 48.65 | |
| ReflexionBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 48.65 | |
| CRITICBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 48.65 | |
| ReActBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 47.3 | |
| ReActBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 46.62 | |
| DILUBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 46.62 | |
| GMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 46.62 | |
| Agent KBBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 46.62 | |
| EvolverBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 46.62 | |
| DCBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 46.62 | |
| ReflexionBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 45.95 | |
| VoyagerBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 45.95 | |
| ExPeLBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 45.95 | |
| AWMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 45.95 | |
| MempBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 44.59 | |
| SkillWeaverBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 44.59 | |
| CFMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 44.59 | |
| CoTBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 42.57 | |
| MobileEBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 42.57 | |
| CoTBackbone=MedGemma-27B, Setting=Offline2026.06 | 41.89 | |
| CRITICBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 41.22 | |
| CoTBackbone=HuluMed-32B, Setting=Offline2026.06 | 38.51 | |
| CoTBackbone=Lingshu-32B, Setting=Offline2026.06 | 32.43 |