Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on MBPP EvalPlus
Loading...
84.9
Pass@1
Llama 3.1 Instruct
57.964
64.957
71.95
78.943
Apr 23, 2025
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
Llama 3.1 Instruct
Model Scale=70B
2025.04
84.9
Llama 3 Instruct
Model Scale=70B
2025.04
82.8
ParamΔ
Model Scale=70B
2025.04
80.7
ParamΔ
Model Scale=8B
2025.04
73.3
Llama 3 Instruct
Model Scale=8B
2025.04
70.6
Llama 3.1 Instruct
Model Scale=8B
2025.04
70.4
Llama 3.1 Base
Model Scale=70B
2025.04
70.4
Llama 3 Base
Model Scale=70B
2025.04
66.9
Llama 3.1 Base
Model Scale=8B
2025.04
59.3
Llama 3 Base
Model Scale=8B
2025.04
59
Feedback
Search any
task
Search any
task