Clinical Question Answering on LiveMedBench (offline)
57.95AccuracySkeMex
Evaluation Results
| Method | Links | |
|---|---|---|
| SkeMexBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 57.95 | |
| MempBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 54.79 | |
| Agent KBBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 54.59 | |
| CFMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 54.29 | |
| GMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 54.1 | |
| SkeMexBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 53.97 | |
| DILUBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 53.94 | |
| DCBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 53.76 | |
| AWMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 53.39 | |
| GSEMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 53.2 | |
| VoyagerBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 52.74 | |
| SkillWeaverBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 52.15 | |
| EvolverBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 51.86 | |
| AWMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 50.39 | |
| SkillWeaverBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 50.2 | |
| CFMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 50.07 | |
| DILUBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 49.97 | |
| VoyagerBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 49.17 | |
| MempBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 49.06 | |
| Agent KBBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 49.01 | |
| MobileEBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 48.96 | |
| DCBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 48.9 | |
| ReflexionBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 48.72 | |
| GMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 48.69 | |
| ReActBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 48.64 | |
| MobileEBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 48.44 | |
| CRITICBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 47.75 | |
| GSEMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 47.61 | |
| ExPeLBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 47.42 | |
| EvolverBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 47.26 | |
| ReActBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 46.93 | |
| CoTBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 44.93 | |
| CoTBackbone=MedGemma-27B, Setting=Offline2026.06 | 40.64 | |
| CRITICBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 39.26 | |
| ReflexionBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 38.75 | |
| ExPeLBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 37.72 | |
| CoTBackbone=HuluMed-32B, Setting=Offline2026.06 | 35.58 | |
| CoTBackbone=Lingshu-32B, Setting=Offline2026.06 | 30.45 |