List your company

Combinatorial Search on N-Queens N=8

22.2AccuracySoftCoT
2.967.95512.9517.945May 22, 2026

Evaluation results

MethodLinks
SoftCoTBase model=Qwen2.5, Transfer cost=full retrain2026.0522.2
HyperGuideBase model=Qwen2.5, Transfer cost=small MLP2026.0522.2
HyperGuideBase model=GPT-OSS, Transfer cost=small MLP2026.0519.8
SoftCoTBase model=GPT-OSS, Transfer cost=full retrain2026.0518.5
PT-SFTBase model=Mistral, Transfer cost=full retrain2026.0516.1
HyperGuideBase model=Mistral, Transfer cost=small MLP2026.0516.1
Tree of ThoughtsBase model=GPT-OSS, Transfer cost=N/A2026.0513.6
Tree of ThoughtsBase model=Mistral, Transfer cost=N/A2026.0513.6
Self-ConsistencyBase model=Qwen2.5, Transfer cost=N/A2026.0511.1
Few-shotBase model=Mistral, Transfer cost=N/A2026.0511.1
Self-ConsistencyBase model=Mistral, Transfer cost=N/A2026.0511.1
Few-shotBase model=Qwen2.5, Transfer cost=N/A2026.059.9
PT-SFTBase model=Qwen2.5, Transfer cost=full retrain2026.059.9
PT-SFTBase model=GPT-OSS, Transfer cost=full retrain2026.059.9
SoftCoTBase model=Mistral, Transfer cost=full retrain2026.059.9
Few-shotBase model=GPT-OSS, Transfer cost=N/A2026.056.1
OVMBase model=Qwen2.5, Transfer cost=full retrain2026.054.9
Self-ConsistencyBase model=GPT-OSS, Transfer cost=N/A2026.054.9
OVMBase model=GPT-OSS, Transfer cost=full retrain2026.054.9
Tree of ThoughtsBase model=Qwen2.5, Transfer cost=N/A2026.053.7
OVMBase model=Mistral, Transfer cost=full retrain2026.053.7