Clinical Question Answering on LiveClin Text modality (offline)
92.08AccuracyEvolver
Evaluation Results
| Method | Links | |
|---|---|---|
| EvolverBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 92.08 | |
| SkeMexBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 92.08 | |
| SkillWeaverBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 91.09 | |
| CFMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 91.09 | |
| SkeMexBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 91.09 | |
| Agent KBBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 86.14 | |
| CRITICBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 86.14 | |
| DILUBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 86.14 | |
| GMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 86.14 | |
| SkillWeaverBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 86.14 | |
| ReActBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 85.15 | |
| CRITICBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 85.15 | |
| ReflexionBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 85.15 | |
| DCBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 85.15 | |
| MobileEBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 85.15 | |
| CoTBackbone=MedGemma-27B, Setting=Offline2026.06 | 84.16 | |
| ExPeLBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 84.16 | |
| AWMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 84.16 | |
| EvolverBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 84.16 | |
| CoTBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 83.17 | |
| VoyagerBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 83.17 | |
| Agent KBBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 83.17 | |
| GSEMBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 83.17 | |
| DILUBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 82.18 | |
| ExPeLBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 82.18 | |
| DCBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 82.18 | |
| MobileEBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 82.18 | |
| VoyagerBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 82.18 | |
| MempBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 82.18 | |
| ReflexionBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 81.19 | |
| CFMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 81.19 | |
| GSEMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 81.19 | |
| ReActBackbone=Qwen3.6-Plus, Setting=Offline2026.06 | 81.19 | |
| GMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 80.2 | |
| AWMBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 79.21 | |
| CoTBackbone=HuluMed-32B, Setting=Offline2026.06 | 76.24 | |
| MempBackbone=DeepSeek-V3.2, Setting=Offline2026.06 | 75.25 | |
| CoTBackbone=Lingshu-32B, Setting=Offline2026.06 | 72.28 |