Comparison
CodeGen vs CodeGeeX
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 CodeGeeX if codeGeeX is an open-source multilingual code generation model that supports both Mindspore and PyTorch frameworks, making it suitable for developers.
Markdown twin · CodeGen alternatives · CodeGeeX alternatives
GraphCanon updated Sep 20, 2026
13views this month
vs
Trust & integrity
| Signal | CodeGen | CodeGeeX |
|---|---|---|
| Maintenance | Slowing (107d since push) As of Sep 18, 2026 · github_public_v1 | Dormant (766d 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 | Published findings 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
- CodeGeeX
- CodeGeeX: An Open Multilingual Code Generation Model
Stars
- CodeGen
- 5.2k
- CodeGeeX
- 8.8k
Forks
- CodeGen
- 420
- CodeGeeX
- 686
Open issues
- CodeGen
- 49
- CodeGeeX
- 189
Language
- CodeGen
- Python
- CodeGeeX
- 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.
- CodeGeeX
- CodeGeeX is an open-source multilingual code generation model that supports both Mindspore and PyTorch frameworks, making it suitable for developers working with Ascend 910 AI Processors or GPU platforms.
Persona
- CodeGen
- -
- CodeGeeX
- -
Runtime
- CodeGen
- -
- CodeGeeX
- -
License
- CodeGen
- Apache-2.0
- CodeGeeX
- CodeGeeX is licensed under the Apache-2.0 license, allowing for broad use, modification, and distribution of the code, while the model itself is under a separate license.
Last pushed
- CodeGen
- Jun 2, 2026
- CodeGeeX
- Aug 13, 2024
Categories
- CodeGen
- LLM Frameworks, Model Training
- CodeGeeX
- LLM Frameworks, Model Training
Trust and health
Maintenance
- CodeGen
- Slowing (36%)
- CodeGeeX
- Dormant (18%)
Days since push
- CodeGen
- 107d
- CodeGeeX
- 766d
Open issues (now)
- CodeGen
- 49
- CodeGeeX
- 189
Stars delta
- CodeGen
- +1 (30d)
- CodeGeeX
- -3 (30d)
OSV dependency advisories
- CodeGen
- No lockfile (source not queried)
- CodeGeeX
- Published findings
Full report
- CodeGen
- Trust report
- CodeGeeX
- Trust report
Shared compatibility
- Python · CodeGen: Python runtime · CodeGeeX: Python runtime
Choose CodeGen if…
- Tags unique to CodeGen: codex, generativemodel, languagemodel, llm.
- When you need an open-source alternative to proprietary models like OpenAI Codex for program synthesis.
- More recently updated (last pushed Jun 2, 2026).
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 CodeGeeX if…
- Requirements: Requires Docker; Requires Python 3.7+, CUDA 11+, PyTorch 1.10+, and DeepSpeed 0.6+.; Supports installation via pip or through a Docker container for quick setup..
- Tags unique to CodeGeeX: code-generation, code-generation-model, gpu-support, mindspore.
- When you need a multilingual code generation model that supports both Mindspore and PyTorch frameworks, allowing flexibility between Ascend 910 AI Processors and GPU platforms.
When NOT to use CodeGeeX
- If your project is strictly limited to TensorFlow or other frameworks not supported by CodeGeeX, as it primarily supports Mindspore and PyTorch.
- When your development environment does not support Python 3.7+, CUDA 11+, PyTorch 1.10+, or DeepSpeed 0.6+, as these are the minimum requirements for running CodeGeeX.
- If you are looking for a model that does not require specific hardware like Ascend 910 AI Processors or GPUs, as CodeGeeX is optimized for these platforms.
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 (zai-org/CodeGeeX) · observed Sep 20, 2026
- GitHub forks (zai-org/CodeGeeX) · observed Sep 20, 2026
- Last push (zai-org/CodeGeeX) · observed Aug 13, 2024
- 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 on cards: CodeGen 5.2k · CodeGeeX 8.8k (synced Sep 20, 2026).
Common questions
- What is the difference between CodeGen and CodeGeeX?
- CodeGen: A family of open-source models for program synthesis. CodeGeeX: CodeGeeX: An Open Multilingual Code Generation Model. See the comparison table for live GitHub stats and shared categories.
- When should I choose CodeGen over CodeGeeX?
- Choose CodeGen over CodeGeeX when Tags unique to CodeGen: codex, generativemodel, languagemodel, llm; When you need an open-source alternative to proprietary models like OpenAI Codex for program synthesis; More recently updated (last pushed Jun 2, 2026).
- When should I choose CodeGeeX over CodeGen?
- Choose CodeGeeX over CodeGen when Requirements: Requires Docker; Requires Python 3.7+, CUDA 11+, PyTorch 1.10+, and DeepSpeed 0.6+.; Supports installation via pip or through a Docker container for quick setup.; Tags unique to CodeGeeX: code-generation, code-generation-model, gpu-support, mindspore; When you need a multilingual code generation model that supports both Mindspore and PyTorch frameworks, allowing flexibility between Ascend 910 AI Processors and GPU platforms.
- 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 CodeGeeX?
- If your project is strictly limited to TensorFlow or other frameworks not supported by CodeGeeX, as it primarily supports Mindspore and PyTorch. When your development environment does not support Python 3.7+, CUDA 11+, PyTorch 1.10+, or DeepSpeed 0.6+, as these are the minimum requirements for running CodeGeeX. If you are looking for a model that does not require specific hardware like Ascend 910 AI Processors or GPUs, as CodeGeeX is optimized for these platforms.
- Is CodeGen or CodeGeeX more popular on GitHub?
- CodeGeeX has more GitHub stars (8,806 vs 5,180). Stars measure visibility, not whether either tool fits your constraints.
- Are CodeGen and CodeGeeX open source?
- Yes - both are open-source projects on GitHub (CodeGen: Apache-2.0, CodeGeeX: Apache-2.0).
- Where can I find alternatives to CodeGen or CodeGeeX?
- GraphCanon lists graph-backed alternatives at CodeGen alternatives and CodeGeeX alternatives (CodeGen markdown twin, CodeGeeX 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 CodeGeeX?
- CodeGen: Slowing. CodeGeeX: Dormant. 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 CodeGeeX?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: CodeGen trust report; CodeGeeX trust report.