Constraint Satisfaction on Graph Coloring (test)
88AccuracyHyperGuide
Evaluation Results
| Method | Links | |
|---|---|---|
| HyperGuideBase model=Qwen2.52026.05 | 88 | |
| HyperGuideBase model=GPT-OSS2026.05 | 81 | |
| SoftCoTBase model=Qwen2.52026.05 | 79 | |
| SoftCoTBase model=GPT-OSS2026.05 | 68 | |
| PT-SFTBase model=Qwen2.52026.05 | 64 | |
| Few-shotBase model=Qwen2.52026.05 | 63 | |
| HyperGuideBase model=Mistral2026.05 | 63 | |
| Self-ConsistencyBase model=Qwen2.52026.05 | 60 | |
| OVMBase model=Qwen2.52026.05 | 59.4 | |
| PT-SFTBase model=GPT-OSS2026.05 | 58 | |
| Self-ConsistencyBase model=GPT-OSS2026.05 | 57.4 | |
| SoftCoTBase model=Mistral2026.05 | 57 | |
| OVMBase model=Mistral2026.05 | 55.4 | |
| OVMBase model=GPT-OSS2026.05 | 53 | |
| PT-SFTBase model=Mistral2026.05 | 52 | |
| Few-shotBase model=GPT-OSS2026.05 | 51 | |
| Self-ConsistencyBase model=Mistral2026.05 | 49.6 | |
| Tree of ThoughtsBase model=GPT-OSS2026.05 | 49 | |
| Few-shotBase model=Mistral2026.05 | 49 | |
| Tree of ThoughtsBase model=Qwen2.52026.05 | 34 | |
| Tree of ThoughtsBase model=Mistral2026.05 | 14 |