Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on HumanEval (Acc, Step)
Loading...
59.76
Accuracy
KLASS
24.2336
33.4568
42.68
51.9032
Nov 7, 2025
Accuracy
Steps
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Steps
KLASS
Model=Dream
2025.11
59.76
73.73
Top-k Margin
Model=Dream
2025.11
58.53
256
Entropy
Model=Dream
2025.11
58.53
256
Top-k Margin
Model=Dream
2025.11
43.29
128
Entropy
Model=Dream
2025.11
43.29
128
KLASS
Model=LLaDA
2025.11
40.85
91.98
Top-k Margin
Model=LLaDA
2025.11
39.63
256
Entropy
Model=LLaDA
2025.11
35.97
256
Top-k Margin
Model=LLaDA
2025.11
30.48
128
Entropy
Model=LLaDA
2025.11
25.6
128
Feedback
Search any
task
Search any
task