Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Reasoning on MBPP (Execution Efficiency)
Loading...
1
Average Code Length
Target Model
0.7536
2.4168
4.08
5.7432
Mar 13, 2026
Average Code Length
Execution Speedup
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Code Length
Execution Speedup
Accuracy
Target Model
Target Model=Qwen / Qw...
2026.03
1
1
53.56
Draft Model
Draft Model=Qwen / Qwe...
2026.03
1
3.56
14.15
OSD-LR
Target Model=Qwen / Qw...
2026.03
5.66
1.09
50.54
LR
Target Model=Qwen / Qw...
2026.03
5.76
1.09
50.65
Online-LR
Target Model=Qwen / Qw...
2026.03
7.16
1.14
51.19
Feedback
Search any
task
Search any
task