List your company

Combinatorial Reasoning on Graph Coloring

100AccuracyBoN
-4235077Mar 3, 2025May 16, 2025Jul 29, 2025Oct 11, 2025Dec 24, 2025Mar 8, 2026May 22, 2026

Evaluation results

MethodLinks
BoNAlgorithm=BoN, Model=Llama 70B2025.03100
SEM-CTRLAlgorithm=SEM-CTRL, Model=Llama 1B2025.03100
SEM-CTRLAlgorithm=SEM-CTRL, Model=Llama 70B2025.03100
SoftCoTBase model=Qwen2.5, Transfer cost=full retrain2026.0579
o1-previewAlgorithm=API, Model=o1-preview2025.0375
DeepSeek-R1Algorithm=API, Model=DeepSeek-R12025.0375
o4-miniAlgorithm=API, Model=o4-mini2025.0375
SoftCoTBase model=GPT-OSS, Transfer cost=full retrain2026.0568
PT-SFTBase model=Qwen2.5, Transfer cost=full retrain2026.0564
HyperGuideBase model=Qwen2.5, Transfer cost=small MLP2026.0564
Few-shotBase model=Qwen2.5, Transfer cost=N/A2026.0563
HyperGuideBase model=GPT-OSS, Transfer cost=small MLP2026.0563
Self-ConsistencyBase model=Qwen2.5, Transfer cost=N/A2026.0560
OVMBase model=Qwen2.5, Transfer cost=full retrain2026.0559.4
PT-SFTBase model=GPT-OSS, Transfer cost=full retrain2026.0558
Self-ConsistencyBase model=GPT-OSS, Transfer cost=N/A2026.0557.4
SoftCoTBase model=Mistral, Transfer cost=full retrain2026.0557
HyperGuideBase model=Mistral, Transfer cost=small MLP2026.0557
OVMBase model=Mistral, Transfer cost=full retrain2026.0555.4
OVMBase model=GPT-OSS, Transfer cost=full retrain2026.0553
PT-SFTBase model=Mistral, Transfer cost=full retrain2026.0552
Few-shotBase model=GPT-OSS, Transfer cost=N/A2026.0551
Self-ConsistencyBase model=Mistral, Transfer cost=N/A2026.0549.6
Tree of ThoughtsBase model=GPT-OSS, Transfer cost=N/A2026.0549
Few-shotBase model=Mistral, Transfer cost=N/A2026.0549
BaseAlgorithm=Base, Model=Llama 70B2025.0337.5
Tree of ThoughtsBase model=Qwen2.5, Transfer cost=N/A2026.0534
Tree of ThoughtsBase model=Mistral, Transfer cost=N/A2026.0514
BaseAlgorithm=Base, Model=Llama 1B2025.030
BoNAlgorithm=BoN, Model=Llama 1B2025.030