Skip to main content
PaperLLMsv1.0

Code Llama: Open Foundation Models for Code

by Meta AI · open-source · Last verified 2026-03-17

Introduced Code Llama, a family of large language models for code built on Llama 2 through code-specific pretraining and fine-tuning. Code Llama achieves state-of-the-art performance among open models on HumanEval and MBPP, with variants for Python, instruction following, and long context (100K tokens).

https://arxiv.org/abs/2308.12950
B+
B+Good
Adoption: A+Quality: AFreshness: ACitations: AEngagement: F

Specifications

License
Llama 2 Community License
Pricing
open-source
Capabilities
code-generation, code-completion, fill-in-the-middle, long-context-code, instruction-following
Integrations
huggingface, ollama, llama-cpp
Use Cases
code-generation, code-completion, automated-programming, code-explanation
API Available
No
Tags
code-llama, meta, code-generation, open-source, llama-2
Added
2026-03-17
Completeness
100%

Index Score

74.3
Adoption
90
Quality
89
Freshness
83
Citations
82
Engagement
0

Put AI to work for your business

Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service