Out-of-Domain Generalization on Out-of-Domain Generalization Suite Aggregate
78.18Average AccuracySkeMex
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SkeMexBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 78.18 | 13.91 | |
| SkeMexBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 75.79 | 13.78 | |
| EvolverBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 75.21 | 10.94 | |
| MobileEBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.97 | 10.7 | |
| Agent KBBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.84 | 10.57 | |
| VoyagerBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.77 | 10.5 | |
| AWMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.75 | 10.48 | |
| DILUBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.74 | 10.47 | |
| ExPeLBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.55 | 10.28 | |
| ReflexionBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.4 | 10.13 | |
| GMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.23 | 9.96 | |
| MempBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 74.05 | 9.78 | |
| SkillWeaverBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 73.85 | 9.58 | |
| CFMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 73.72 | 9.45 | |
| CRITICBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 73.35 | 9.08 | |
| DCBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 73.09 | 8.82 | |
| EvolverBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 70.35 | 8.34 | |
| GMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 70.25 | 8.24 | |
| DCBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 69.63 | 7.62 | |
| CFMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 69.62 | 7.61 | |
| MobileEBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 69.38 | 7.37 | |
| AWMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 69.08 | 7.07 | |
| Agent KBBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 69.07 | 7.06 | |
| MempBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 69.05 | 7.04 | |
| SkillWeaverBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 69.05 | 7.04 | |
| CRITICBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 67.98 | 5.97 | |
| DILUBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 67.42 | 5.41 | |
| ReflexionBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 67.22 | 5.21 | |
| GSEMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 67.1 | 2.83 | |
| VoyagerBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 66.96 | 4.95 | |
| ExPeLBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 66.63 | 4.62 | |
| ReActBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 64.27 | — | |
| GSEMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 63.88 | 1.87 | |
| CoTBackbone=Hulu-Med-32B, Evaluation Setting=Offline2026.06 | 62.67 | — | |
| ReActBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 62.01 | — | |
| CoTBackbone=MedGemma-27B, Evaluation Setting=Offline2026.06 | 61.05 | — | |
| CoTBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 59.06 | — | |
| CoTBackbone=Lingshu-32B, Evaluation Setting=Offline2026.06 | 52.88 | — |