Clinical Question Answering on MedXpertQA Text modality (offline)
46.49AccuracySkeMex
Evaluation Results
| Method | Links | |
|---|---|---|
| SkeMexBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 46.49 | |
| CRITICBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 44.32 | |
| ExPeLBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 44.32 | |
| AWMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 44.32 | |
| EvolverBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 44.32 | |
| GSEMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 44.32 | |
| MempBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 43.78 | |
| CFMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 43.78 | |
| SkillWeaverBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 43.24 | |
| MobileEBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 43.24 | |
| Agent KBBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 42.7 | |
| ReflexionBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 42.16 | |
| GMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 42.16 | |
| DCBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 42.16 | |
| VoyagerBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 41.08 | |
| DILUBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 40.54 | |
| SkeMexBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 35.68 | |
| ReActBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 35.14 | |
| GSEMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 34.59 | |
| ReActBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 33.51 | |
| ExPeLBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 33.51 | |
| AWMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 33.51 | |
| Agent KBBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 33.51 | |
| MobileEBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 33.51 | |
| CFMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 33.51 | |
| CoTBackbone=HuluMed-32B, Setting=Offline2026.06 | 32.97 | |
| CoTBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 32.43 | |
| DILUBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 32.43 | |
| SkillWeaverBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 32.43 | |
| EvolverBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 32.43 | |
| DCBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 32.43 | |
| CRITICBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 31.89 | |
| MempBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 31.89 | |
| GMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 30.27 | |
| CoTBackbone=MedGemma-27B, Setting=Offline2026.06 | 29.73 | |
| VoyagerBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 29.73 | |
| ReflexionBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 28.11 | |
| CoTBackbone=Lingshu-32B, Setting=Offline2026.06 | 23.78 |