List your company

Multimodal Reasoning on MMMU-Pro offline (test)

51.79AccuracySkeMex
27.641233.910640.1846.4494Jun 8, 2026

Evaluation results

MethodLinks
SkeMexBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0651.79
SkeMexBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0648.21
CoTBackbone=Hulu-Med-32B, Evaluation Setting=Offline2026.0646.43
DILUBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0646.43
GMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0646.43
EvolverBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0646.43
MobileEBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0646.43
ReflexionBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0644.64
VoyagerBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0644.64
ExPeLBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0644.64
AWMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0644.64
Agent KBBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0644.64
DCBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0644.64
GSEMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0642.86
CRITICBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0642.86
ReActBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0641.07
MempBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0641.07
SkillWeaverBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0641.07
CFMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0641.07
CoTBackbone=MedGemma-27B, Evaluation Setting=Offline2026.0639.29
GSEMBackbone=Qwen3.6-Plus, Evaluation Setting=Offline2026.0639.29
GMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0637.5
AWMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0637.5
DCBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0637.5
CFMBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0637.5
ReActBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0635.71
CRITICBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0635.71
MempBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0635.71
EvolverBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0635.71
MobileEBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0635.71
ExPeLBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0633.93
SkillWeaverBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0633.93
CoTBackbone=Lingshu-32B, Evaluation Setting=Offline2026.0632.14
CoTBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0632.14
ReflexionBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0632.14
VoyagerBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0632.14
Agent KBBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0632.14
DILUBackbone=DeepSeek-V3.2, Evaluation Setting=Offline2026.0628.57