Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Completion on BigCodeBench Hard
Loading...
16.2
Pass@1
NonDPFT
5.384
8.192
11
13.808
Dec 5, 2025
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
NonDPFT
Backbone=Qwen2.5-Coder...
2025.12
16.2
NonDPFT
Backbone=CodeQwen1.5-7...
2025.12
12.1
PrivCode
Backbone=DS-Coder-6.7B...
2025.12
9.4
JFT
Backbone=DS-Coder-6.7B...
2025.12
8.8
PrivCode
Backbone=Qwen2.5-Coder...
2025.12
8.8
PrivCode
Backbone=CodeQwen1.5-7...
2025.12
8.8
PrivCode
Backbone=CodeGemma-7B,...
2025.12
8.7
DP-Adapter
Backbone=DS-Coder-6.7B...
2025.12
8.4
NonDPFT
Backbone=DS-Coder-6.7B...
2025.12
8.1
DPFT
Backbone=DS-Coder-6.7B...
2025.12
8.1
NonDPFT
Backbone=CodeGemma-7B,...
2025.12
8.1
JFT
Backbone=Qwen2.5-Coder...
2025.12
8
JFT
Backbone=CodeQwen1.5-7...
2025.12
7.9
DP-Adapter
Backbone=CodeGemma-7B,...
2025.12
7.7
DPFT
Backbone=CodeGemma-7B,...
2025.12
7.4
DPFT
Backbone=CodeQwen1.5-7...
2025.12
7.4
JFT
Backbone=CodeGemma-7B,...
2025.12
7.2
DP-Adapter
Backbone=CodeQwen1.5-7...
2025.12
6.7
DPFT
Backbone=Qwen2.5-Coder...
2025.12
6.1
DP-Adapter
Backbone=Qwen2.5-Coder...
2025.12
5.8
Feedback
Search any
task
Search any
task
