Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Constraint Satisfaction on Graph Coloring (test)
Loading...
88
Accuracy
HyperGuide
11.04
31.02
51
70.98
May 22, 2026
Accuracy
Updated 8d ago
Evaluation Results
Method
Method
Links
Accuracy
HyperGuide
Base model=Qwen2.5
2026.05
88
HyperGuide
Base model=GPT-OSS
2026.05
81
SoftCoT
Base model=Qwen2.5
2026.05
79
SoftCoT
Base model=GPT-OSS
2026.05
68
PT-SFT
Base model=Qwen2.5
2026.05
64
Few-shot
Base model=Qwen2.5
2026.05
63
HyperGuide
Base model=Mistral
2026.05
63
Self-Consistency
Base model=Qwen2.5
2026.05
60
OVM
Base model=Qwen2.5
2026.05
59.4
PT-SFT
Base model=GPT-OSS
2026.05
58
Self-Consistency
Base model=GPT-OSS
2026.05
57.4
SoftCoT
Base model=Mistral
2026.05
57
OVM
Base model=Mistral
2026.05
55.4
OVM
Base model=GPT-OSS
2026.05
53
PT-SFT
Base model=Mistral
2026.05
52
Few-shot
Base model=GPT-OSS
2026.05
51
Self-Consistency
Base model=Mistral
2026.05
49.6
Tree of Thoughts
Base model=GPT-OSS
2026.05
49
Few-shot
Base model=Mistral
2026.05
49
Tree of Thoughts
Base model=Qwen2.5
2026.05
34
Tree of Thoughts
Base model=Mistral
2026.05
14
Feedback
Search any
task
Search any
task