Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on MBPP (Accuracy Before/After Delta)
Loading...
55.2
MBPP Accuracy (Pre-Exec)
CausalFlow
50.728
51.889
53.05
54.211
May 25, 2026
MBPP Accuracy (Pre-Exec)
MBPP Accuracy (Post-Exec)
MBPP Accuracy Gain (Δ)
Updated 8d ago
Evaluation Results
Method
Method
Links
MBPP Accuracy (Pre-Exec)
MBPP Accuracy (Post-Exec)
MBPP Accuracy Gain (Δ)
CausalFlow
2026.05
55.2
76.4
21.2
Direct
2026.05
51.4
51.4
0
Self-Reflection
2026.05
51.4
78.9
27.4
Self-Refine
2026.05
50.9
90.3
39.4
Feedback
Search any
task
Search any
task