Comparison
CodeGen vs CodeT5
Verdict
Pick CodeGen if codeGen is a family of open-source models for program synthesis developed by Salesforce AI Research, available in various sizes from 350M to 16B parameters. It is trained on TPU-v4 and competes with OpenAI Codex; pick CodeT5 if codeT5 is a large language model for code understanding and generation, developed by Salesforce, and is released under the BSD-3-Clause.
Markdown twin · CodeGen alternatives · CodeT5 alternatives
GraphCanon updated Sep 20, 2026
9views this month
Trust & integrity
| Signal | CodeGen | CodeT5 |
|---|---|---|
| Maintenance | Slowing (107d since push) As of Sep 18, 2026 · github_public_v1 | Archived (84d since push) As of Sep 18, 2026 · github_public_v1 |
| Provenance | Not a fork · Organization account As of Sep 18, 2026 · github_public_v1 | Not a fork · Organization account As of Sep 18, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Sep 18, 2026 · osv@v1 | No lockfile (source not queried) As of Sep 18, 2026 · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- CodeGen
- A family of open-source models for program synthesis
- CodeT5
- Open Code LLMs for Code Understanding and Generation
Stars
- CodeGen
- 5.2k
- CodeT5
- 3.1k
Forks
- CodeGen
- 420
- CodeT5
- 486
Open issues
- CodeGen
- 49
- CodeT5
- 88
Language
- CodeGen
- Python
- CodeT5
- Python
Adopt for
- CodeGen
- CodeGen is a family of open-source models for program synthesis developed by Salesforce AI Research, available in various sizes from 350M to 16B parameters. It is trained on TPU-v4 and competes with OpenAI Codex.
- CodeT5
- CodeT5 is a large language model for code understanding and generation, developed by Salesforce, and is released under the BSD-3-Clause license.
Persona
- CodeGen
- -
- CodeT5
- -
Runtime
- CodeGen
- -
- CodeT5
- -
License
- CodeGen
- Apache-2.0
- CodeT5
- CodeT5 is released under the BSD-3-Clause license, which allows for free use, modification, and distribution, provided that the original copyright notice and disclaimer are included.
Last pushed
- CodeGen
- Jun 2, 2026
- CodeT5
- Jun 25, 2026
Categories
- CodeGen
- LLM Frameworks, Model Training
- CodeT5
- LLM Frameworks, Model Training
Trust and health
Maintenance
- CodeGen
- Slowing (36%)
- CodeT5
- Archived (8%)
Days since push
- CodeGen
- 107d
- CodeT5
- 84d
Archived on GitHub
- CodeGen
- No
- CodeT5
- Yes
Open issues (now)
- CodeGen
- 49
- CodeT5
- 88
Stars delta
- CodeGen
- +1 (30d)
- CodeT5
- -5 (30d)
Open issues delta
- CodeGen
- +1 (30d)
- CodeT5
- 0 (30d)
Full report
- CodeGen
- Trust report
- CodeT5
- Trust report
Choose CodeGen if…
- License: CodeGen is Apache-2.0, CodeT5 is BSD-3-Clause.
- Tags unique to CodeGen: codex, generativemodel, languagemodel, llm.
- When you need an open-source alternative to proprietary models like OpenAI Codex for program synthesis.
When NOT to use CodeGen
- If your project strictly requires proprietary models with specific features not available in open-source alternatives.
- When the hardware requirements for TPU-v4 trained models are not met or are not preferred in your environment.
- If the latest version of CodeGen does not meet the specific performance or feature requirements of your project.
- For projects that require models with a different licensing model, as CodeGen is licensed under Apache-2.0.
Choose CodeT5 if…
- License: CodeT5 is BSD-3-Clause, CodeGen is Apache-2.0.
- Requirements: Min 8 GB RAM; The model may require significant computational resources for training and inference..
- Tags unique to CodeT5: code-generation, code-intelligence, code-understanding, language-model.
- When you need a tool specifically for code understanding and generation tasks, as CodeT5 is designed with a focus on these areas.
When NOT to use CodeT5
- If your project involves promoting or profiting from violence, hate, division, environmental destruction, abuse of human rights, or the destruction of people's physical and mental health, as these are
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (salesforce/CodeGen) · observed Sep 20, 2026
- GitHub forks (salesforce/CodeGen) · observed Sep 20, 2026
- Last push (salesforce/CodeGen) · observed Jun 2, 2026
- License file (Apache-2.0) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Sep 18, 2026
- Trust scan (lockfile / OSV) · observed Sep 18, 2026
- GitHub stars (salesforce/CodeT5) · observed Sep 20, 2026
- GitHub forks (salesforce/CodeT5) · observed Sep 20, 2026
- Last push (salesforce/CodeT5) · observed Jun 25, 2026
- License file (BSD-3-Clause) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Sep 18, 2026
- Trust scan (lockfile / OSV) · observed Sep 18, 2026
GitHub stars on cards: CodeGen 5.2k · CodeT5 3.1k (synced Sep 20, 2026).
Common questions
- What is the difference between CodeGen and CodeT5?
- CodeGen: A family of open-source models for program synthesis. 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; When you need an open-source alternative to proprietary models like OpenAI Codex for program synthesis.
- When should I choose CodeT5 over CodeGen?
- Choose CodeT5 over CodeGen when License: CodeT5 is BSD-3-Clause, CodeGen is Apache-2.0; Requirements: Min 8 GB RAM; The model may require significant computational resources for training and inference.; Tags unique to CodeT5: code-generation, code-intelligence, code-understanding, language-model; When you need a tool specifically for code understanding and generation tasks, as CodeT5 is designed with a focus on these areas.
- When should I avoid CodeGen?
- If your project strictly requires proprietary models with specific features not available in open-source alternatives. When the hardware requirements for TPU-v4 trained models are not met or are not preferred in your environment. If the latest version of CodeGen does not meet the specific performance or feature requirements of your project. For projects that require models with a different licensing model, as CodeGen is licensed under Apache-2.0.
- When should I avoid CodeT5?
- If your project involves promoting or profiting from violence, hate, division, environmental destruction, abuse of human rights, or the destruction of people's physical and mental health, as these are
- Is CodeGen or CodeT5 more popular on GitHub?
- CodeGen has more GitHub stars (5,180 vs 3,093). 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 and CodeT5 alternatives (CodeGen markdown twin, CodeT5 markdown twin), 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 mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, CodeGen or CodeT5?
- CodeGen: Slowing. 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; CodeT5 trust report.