Multimodal Reasoning on MMMU-Pro offline (test)
51.79AccuracySkeMex
Evaluation Results
| Method | Links | |
|---|---|---|
| SkeMexBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 51.79 | |
| SkeMexBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 48.21 | |
| CoTBackbone=Hulu-Med-32B, Evaluation Setting=Offline2026.06 | 46.43 | |
| DILUBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 46.43 | |
| GMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 46.43 | |
| EvolverBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 46.43 | |
| MobileEBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 46.43 | |
| ReflexionBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 44.64 | |
| VoyagerBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 44.64 | |
| ExPeLBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 44.64 | |
| AWMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 44.64 | |
| Agent KBBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 44.64 | |
| DCBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 44.64 | |
| GSEMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 42.86 | |
| CRITICBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 42.86 | |
| ReActBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 41.07 | |
| MempBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 41.07 | |
| SkillWeaverBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 41.07 | |
| CFMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 41.07 | |
| CoTBackbone=MedGemma-27B, Evaluation Setting=Offline2026.06 | 39.29 | |
| GSEMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.06 | 39.29 | |
| GMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 37.5 | |
| AWMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 37.5 | |
| DCBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 37.5 | |
| CFMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 37.5 | |
| ReActBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 35.71 | |
| CRITICBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 35.71 | |
| MempBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 35.71 | |
| EvolverBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 35.71 | |
| MobileEBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 35.71 | |
| ExPeLBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 33.93 | |
| SkillWeaverBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 33.93 | |
| CoTBackbone=Lingshu-32B, Evaluation Setting=Offline2026.06 | 32.14 | |
| CoTBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 32.14 | |
| ReflexionBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 32.14 | |
| VoyagerBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 32.14 | |
| Agent KBBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 32.14 | |
| DILUBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.06 | 28.57 |