Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Codebase generation on Recipe App
Loading...
82
Feature Completion
Code-L2MAC
16.48
33.49
50.5
67.51
Oct 2, 2023
Feature Completion
Error Rate
LOC
Test Success Rate
Code Coverage
Updated 1mo ago
Evaluation Results
Method
Method
Links
Feature Completion
Error Rate
LOC
Test Success Rate
Code Coverage
Code-L2MAC
2023.10
82
0
497
24.6
94.2
AutoGPT
2023.10
39.2
1.85
106
1.3
9.8
Self-Refine
2023.10
26
0.1
149
2
76.2
GPT4
2023.10
21.6
3.15
97.5
9.2
10.7
CodeT
2023.10
20.5
0
96.5
3.05
97.8
Reflexion
2023.10
19
0.25
95.9
2.95
89.9
Feedback
Search any
task
Search any
task