List your company

Graph Reasoning on OOD graph (test)

38.91GraphWiz ScoreAutoSelection
29.123631.664334.20536.7457May 13, 2026

Evaluation results

MethodLinks
AutoSelectionModel=Qwen2.5-1.5B, Group=Recipe2026.0538.9158.5448.73
RandomModel=Qwen2.5-1.5B, Group=Top-k2026.0538.7153.2245.97
MONAModel=Qwen2.5-3B, Group=Top-k2026.0538.5659.1948.88
SemDedupModel=Qwen2.5-1.5B, Group=Dedup2026.0538.4653.5446
IFDModel=Qwen2.5-1.5B, Group=Top-k2026.0537.9357.0947.51
AOModel=Qwen2.5-1.5B, Group=Top-k2026.0537.6557.7447.7
Full dataModel=Qwen2.5-3B, Group=Full2026.0537.3164.0350.67
N-gramModel=Qwen2.5-1.5B, Group=Top-k2026.0537.2852.2544.77
MONAModel=Qwen2.5-1.5B, Group=Top-k2026.0537.1856.4546.82
Full dataModel=Qwen2.5-1.5B, Group=Full2026.0536.9654.0345.5
RandomModel=Qwen2.5-1.5B, Group=Recipe2026.0536.8850.1643.52
RandomModel=Qwen2.5-3B, Group=Top-k2026.0536.7556.2946.52
AutoSelectionModel=Qwen2.5-3B, Group=Recipe2026.0536.2865.6550.97
IFDModel=Qwen2.5-3B, Group=Top-k2026.0536.2555.846.03
N-gramModel=Qwen2.5-3B, Group=Top-k2026.0536.1557.4146.78
SemDedupModel=Qwen2.5-3B, Group=Dedup2026.0535.8761.9348.9
VarentropyModel=Qwen2.5-3B, Group=Top-k2026.0535.8156.6146.21
VarentropyModel=Qwen2.5-1.5B, Group=Top-k2026.0535.7152.944.31
RandomModel=Qwen2.5-3B, Group=Recipe2026.0535.7166.2951
AOModel=Qwen2.5-3B, Group=Top-k2026.0534.6266.1250.37
Full dataModel=Llama3.2-1B, Group=Full2026.0533.6257.2545.44
AutoSelectionModel=Llama3.2-1B, Group=Recipe2026.0533.5955.4844.54
N-gramModel=Llama3.2-1B, Group=Top-k2026.0532.6550.4841.57
RandomModel=Llama3.2-1B, Group=Top-k2026.0532.4353.2242.83
VarentropyModel=Llama3.2-1B, Group=Top-k2026.0532.4348.740.57
RandomModel=Llama3.2-1B, Group=Recipe2026.0532.1653.5542.86
MONAModel=Llama3.2-1B, Group=Top-k2026.0532.0954.6743.38
AOModel=Llama3.2-1B, Group=Top-k2026.0531.215543.11
SemDedupModel=Llama3.2-1B, Group=Dedup2026.0530.5649.3539.96
IFDModel=Llama3.2-1B, Group=Top-k2026.0529.550.840.15