Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on MBPP (Response Accuracy)
Loading...
65.7
Response Accuracy
SuCo
1.532
18.191
34.85
51.509
Jun 16, 2026
Response Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Response Accuracy
SuCo
Model Scale=7B
2026.06
65.7
LHRMs
Model Scale=7B
2026.06
62.4
S-GRPO
Model Scale=7B
2026.06
62.3
AdaptThink
Model Scale=7B
2026.06
62
AdaCoT
Model Scale=7B
2026.06
61.7
DeepSeek-R1-Distill
Model Scale=7B
2026.06
57.6
SuCo
Model Scale=1.5B
2026.06
48.5
AdaCoT
Model Scale=1.5B
2026.06
44.3
LHRMs
Model Scale=1.5B
2026.06
43.1
S-GRPO
Model Scale=1.5B
2026.06
42.9
AdaptThink
Model Scale=1.5B
2026.06
42.1
DeepSeek-R1-Distill
Model Scale=1.5B
2026.06
41
Math-Instruct
Model Scale=7B
2026.06
26.4
Math-Base
Model Scale=7B
2026.06
13.1
Math-Instruct
Model Scale=1.5B
2026.06
6.1
Math-Base
Model Scale=1.5B
2026.06
4
Feedback
Search any
task
Search any
task