Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on MBPP (Accuracy, Delta)
Loading...
72.47
Accuracy
Qwen2.5(14B)T
40.8852
49.0851
57.285
65.4849
Jul 4, 2026
Accuracy
Delta (Accuracy Change)
Updated 18d ago
Evaluation Results
Method
Method
Links
Accuracy
Delta (Accuracy Change)
Qwen2.5(14B)T
Generation Length=8096
2026.07
72.47
-
Qwen2.5(14B)T
Generation Length=1024
2026.07
53.13
-
RG-OPD (ours)
Generation Length=8096
2026.07
50
6
RG-OPD (ours)
Generation Length=1024
2026.07
49.33
5.6
Reverse KL [1]
Generation Length=8096
2026.07
47.27
3.27
Reverse KL [1]
Generation Length=1024
2026.07
46.6
2.87
Qwen2.5(1.5B)S
Generation Length=8096
2026.07
44
0
Qwen2.5(1.5B)S
Generation Length=1024
2026.07
43.73
0
TSD-KD [10]
Generation Length=8096
2026.07
42.33
-1.67
TSD-KD [10]
Generation Length=1024
2026.07
42.2
-1.53
TSD-KD [10]*
Generation Length=1024
2026.07
42.1
-1.63
Feedback
Search any
task
Search any
task