Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code on HumanEval
Loading...
1
True WS Score
PromptCOS
-0.04
0.23
0.5
0.77
Sep 3, 2025
True WS Score
False WS Score
Min WS Distance
Updated 8d ago
Evaluation Results
Method
Method
Links
True WS Score
False WS Score
Min WS Distance
PromptCOS
Model=CodeGemma-2b
2025.09
1
0.04
0.94
PromptCOS
Model=CodeGemma-7b
2025.09
1
0.14
0.84
PR
Model=CodeGemma-7b
2025.09
0.99
0.85
0
PR
Model=CodeGemma-2b
2025.09
0.91
0.91
-0.03
PC*
Model=CodeGemma-7b
2025.09
0.37
0.02
0.34
PC*
Model=CodeGemma-2b
2025.09
0.36
0.04
0.3
PCG
Model=CodeGemma-7b
2025.09
0.31
0.14
0.13
PCG
Model=CodeGemma-2b
2025.09
0
0
0
Feedback
Search any
task
Search any
task
