--- title: "CodeGen vs CodeT5" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/salesforce-codegen-vs-salesforce-codet5" tools: ["salesforce-codegen", "salesforce-codet5"] --- # CodeGen vs CodeT5 *GraphCanon updated Aug 2, 2026* ## Verdict Pick CodeGen if codeGen is a series of open-source large language models designed for program synthesis. Trained on TPUs, CodeGen offers several versions with varying capabilities from basic code generation to advanced infill sampling; pick CodeT5 if codeT5, an open-source LLM for code understanding and generation under BSD-3-Clause license. [CodeGen](https://github.com/salesforce/CodeGen) reports 5.2k GitHub stars, 421 forks, and 48 open issues, last pushed Jun 2, 2026. [CodeT5](https://arxiv.org/abs/2305.07922) has 3.1k stars, 487 forks, and 88 open issues, last pushed Jun 25, 2026. Figures are from public GitHub metadata via [CodeGen's repository](https://github.com/salesforce/CodeGen) and [CodeT5's repository](https://github.com/salesforce/CodeT5). | | [CodeGen](/tools/salesforce-codegen.md) | [CodeT5](/tools/salesforce-codet5.md) | | --- | --- | --- | | Tagline | Family of open-source models for program synthesis. | Home of CodeT5: Open Code LLMs for Code Understanding and Generation | | Stars | 5,179 | 3,098 | | Forks | 421 | 487 | | Open issues | 48 | 88 | | Language | Python | Python | | Adopt for | CodeGen is a series of open-source large language models designed for program synthesis. Trained on TPUs, CodeGen offers several versions with varying capabilities from basic code generation to advanced infill sampling. | CodeT5, an open-source LLM for code understanding and generation under BSD-3-Clause license. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | BSD-3-Clause | | Categories | LLM Frameworks, Model Training | Developer Tools, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [CodeGen](/tools/salesforce-codegen.md) | [CodeT5](/tools/salesforce-codet5.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Archived (8%) | | Days since push | 60d | 38d | | Archived on GitHub | No | Yes | | Open issues (now) | 48 | 88 | | Full report | [trust report](/tools/salesforce-codegen/trust.md) | [trust report](/tools/salesforce-codet5/trust.md) | ## Decision facts: CodeGen - **Adopt for:** CodeGen is a series of open-source large language models designed for program synthesis. Trained on TPUs, CodeGen offers several versions with varying capabilities from basic code generation to advanced infill sampling. ## Decision facts: CodeT5 - **Adopt for:** CodeT5, an open-source LLM for code understanding and generation under BSD-3-Clause license. ## Choose when ### Choose CodeGen if… - License: CodeGen is Apache-2.0, CodeT5 is BSD-3-Clause. - Tags unique to CodeGen: codex, generativemodel, languagemodel, llm. - Also covers Model Training. - When you require high-performance model training and code generation that matches or exceeds the performance of OpenAI Codex on specific tasks ### Choose CodeT5 if… - License: CodeT5 is BSD-3-Clause, CodeGen is Apache-2.0. - Tags unique to CodeT5: code generation, code-intelligence, code-understanding, language-model. - Also covers Developer Tools. - When focusing on Python projects needing advanced code understanding or generation. ## When NOT to use CodeGen - In scenarios where the model's primary use is not centered around code generation or program synthesis, as its specialized training may limit its effectiveness for other types of generative tasks - If your project strictly requires a smaller memory footprint or simpler deployment because advanced models like CodeGen2.5 require significant computational resources and setup ## When NOT to use CodeT5 - If the project requires proprietary licensing protection, given its open-source nature under BSD-3-Clause. - Avoid if real-time performance is a crucial requirement since LLMs typically lag in speed. ## Common questions ### What is the difference between CodeGen and CodeT5? CodeGen: Family of open-source models for program synthesis.. CodeT5: Home of CodeT5: Open Code LLMs for Code Understanding and Generation. See the comparison table for live GitHub stats and shared categories. ### When should I choose CodeGen over CodeT5? Choose CodeGen over CodeT5 when License: CodeGen is Apache-2.0, CodeT5 is BSD-3-Clause; Tags unique to CodeGen: codex, generativemodel, languagemodel, llm; Also covers Model Training; When you require high-performance model training and code generation that matches or exceeds the performance of OpenAI Codex on specific tasks. ### When should I choose CodeT5 over CodeGen? Choose CodeT5 over CodeGen when License: CodeT5 is BSD-3-Clause, CodeGen is Apache-2.0; Tags unique to CodeT5: code generation, code-intelligence, code-understanding, language-model; Also covers Developer Tools; When focusing on Python projects needing advanced code understanding or generation. ### When should I avoid CodeGen? In scenarios where the model's primary use is not centered around code generation or program synthesis, as its specialized training may limit its effectiveness for other types of generative tasks If your project strictly requires a smaller memory footprint or simpler deployment because advanced models like CodeGen2.5 require significant computational resources and setup ### When should I avoid CodeT5? If the project requires proprietary licensing protection, given its open-source nature under BSD-3-Clause. Avoid if real-time performance is a crucial requirement since LLMs typically lag in speed. ### Is CodeGen or CodeT5 more popular on GitHub? CodeGen has more GitHub stars (5,179 vs 3,098). Stars measure visibility, not whether either tool fits your constraints. ### Are CodeGen and CodeT5 open source? Yes - both are open-source projects on GitHub (CodeGen: Apache-2.0, CodeT5: BSD-3-Clause). ### Where can I find alternatives to CodeGen or CodeT5? GraphCanon lists graph-backed alternatives at [CodeGen alternatives](/tools/salesforce-codegen/alternatives) and [CodeT5 alternatives](/tools/salesforce-codet5/alternatives) ([CodeGen markdown twin](/tools/salesforce-codegen/alternatives.md), [CodeT5 markdown twin](/tools/salesforce-codet5/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/salesforce-codegen-vs-salesforce-codet5.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, CodeGen or CodeT5? CodeGen: Steady. CodeT5: Archived. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for CodeGen and CodeT5? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [CodeGen trust report](/tools/salesforce-codegen/trust); [CodeT5 trust report](/tools/salesforce-codet5/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=salesforce-codegen`](/api/graphcanon/graph?tool=salesforce-codegen) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_