Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Accuracy & Step)
Loading...
80.44
Accuracy
KLASS
71.132
73.5485
75.965
78.3815
Nov 7, 2025
Accuracy
Reasoning Steps
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Reasoning Steps
KLASS
Model=Dream
2025.11
80.44
156.24
Top-k Margin
Model=Dream
2025.11
79.45
256
Entropy
Model=Dream
2025.11
79.45
256
KLASS
Model=LLaDA
2025.11
76.5
98.57
Entropy
Model=LLaDA
2025.11
75.43
256
Top-k Margin
Model=LLaDA
2025.11
74.45
128
Top-k Margin
Model=LLaDA
2025.11
74.14
256
Entropy
Model=LLaDA
2025.11
73.01
128
Top-k Margin
Model=Dream
2025.11
71.49
128
Entropy
Model=Dream
2025.11
71.49
128
Feedback
Search any
task
Search any
task