Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on BigCode
Loading...
46.8
Accuracy
MCNIG
22.36
28.705
35.05
41.395
Mar 18, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
MCNIG
Model Size=8B
2026.03
46.8
ORM
Model Size=8B
2026.03
44.1
IG
Model Size=8B
2026.03
43
OVM
2026.03
34.9
QwenPRM
Model Size=7B
2026.03
31.5
Granite PRM v2
2026.03
31.4
MathShepherd
2026.03
29.5
ImplicitPRM
2026.03
29.3
Majority voting
2026.03
27.6
Single sampling
2026.03
23.3
Feedback
Search any
task
Search any
task