Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
OpenAPI completion on OpenAPI completion benchmark
Loading...
45
Correctness (Max)
Code Llama 7B
28.36
32.68
37
41.32
May 24, 2024
Correctness (Max)
Validity (Max)
Correctness (Avg)
Validity (Avg)
Updated 5mo ago
Evaluation Results
Method
Method
Links
Correctness (Max)
Validity (Max)
Correctness (Avg)
Validity (Avg)
Code Llama 7B
Fine-tuning context si...
2024.05
45
84
32
63.1
Code Llama 7B
Fine-tuning context si...
2024.05
42
79
26.8
57.1
Code Llama 7B
Document splitting=true
2024.05
42
76
34
69.1
Code Llama
Model size=7B
2024.05
36
64
31.1
60.7
Code Llama
Model size=13B, Evalua...
2024.05
34
68
30.2
64
GitHub Copilot
2024.05
29
68
29
68
Feedback
Search any
task
Search any
task