--- title: "CodeGen vs CodeGeeX" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/salesforce-codegen-vs-zai-org-codegeex" tools: ["salesforce-codegen", "zai-org-codegeex"] --- # CodeGen vs CodeGeeX *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 CodeGeeX if codeGeeX is an open-source multilingual code generation model, originally developed with MindSpore and compatible with PyTorch through DeepSpeed integration. [CodeGen](https://github.com/salesforce/CodeGen) reports 5.2k GitHub stars, 421 forks, and 48 open issues, last pushed Jun 2, 2026. [CodeGeeX](https://codegeex.cn) has 8.8k stars, 688 forks, and 188 open issues, last pushed Aug 13, 2024. Figures are from public GitHub metadata via [CodeGen's repository](https://github.com/salesforce/CodeGen) and [CodeGeeX's repository](https://github.com/zai-org/CodeGeeX). | | [CodeGen](/tools/salesforce-codegen.md) | [CodeGeeX](/tools/zai-org-codegeex.md) | | --- | --- | --- | | Tagline | Family of open-source models for program synthesis. | CodeGeeX is an open multilingual code generation model implemented in Mindspore and available via PyTorch. | | Stars | 5,179 | 8,809 | | Forks | 421 | 688 | | Open issues | 48 | 188 | | 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. | CodeGeeX is an open-source multilingual code generation model, originally developed with MindSpore and compatible with PyTorch through DeepSpeed integration. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | Categories | LLM Frameworks, Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [CodeGen](/tools/salesforce-codegen.md) | [CodeGeeX](/tools/zai-org-codegeex.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Dormant (18%) | | Days since push | 60d | 719d | | Open issues (now) | 48 | 188 | | Full report | [trust report](/tools/salesforce-codegen/trust.md) | [trust report](/tools/zai-org-codegeex/trust.md) | ## Shared compatibility - **Python**: [CodeGen](/tools/salesforce-codegen.md) - Python runtime; [CodeGeeX](/tools/zai-org-codegeex.md) - Python runtime ## 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: CodeGeeX - **Adopt for:** CodeGeeX is an open-source multilingual code generation model, originally developed with MindSpore and compatible with PyTorch through DeepSpeed integration. ## Choose when ### Choose CodeGen if… - Tags unique to CodeGen: codex, generativemodel, languagemodel, llm. - When you require high-performance model training and code generation that matches or exceeds the performance of OpenAI Codex on specific tasks - More recently updated (last pushed Jun 2, 2026). ### Choose CodeGeeX if… - Tags unique to CodeGeeX: ai programming tools, code generation, pretrained-models. - When you require support for multilingual code generation and your project has a Python-based infrastructure with CUDA GPU availability. - More GitHub stars (8.8k vs 5.2k) - visibility, not fit. ## 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 CodeGeeX - If your development environment lacks the necessary dependencies like Python 3.7+, CUDA 11+, PyTorch 1.10+, and DeepSpeed 0.6+. - In scenarios where an open-source solution is not preferable or when support for exclusively one language's syntax is sufficient. ## Common questions ### What is the difference between CodeGen and CodeGeeX? CodeGen: Family of open-source models for program synthesis.. CodeGeeX: CodeGeeX is an open multilingual code generation model implemented in Mindspore and available via PyTorch.. 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 require high-performance model training and code generation that matches or exceeds the performance of OpenAI Codex on specific tasks; More recently updated (last pushed Jun 2, 2026). ### When should I choose CodeGeeX over CodeGen? Choose CodeGeeX over CodeGen when Tags unique to CodeGeeX: ai programming tools, code generation, pretrained-models; When you require support for multilingual code generation and your project has a Python-based infrastructure with CUDA GPU availability; More GitHub stars (8.8k vs 5.2k) - visibility, not fit. ### 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 CodeGeeX? If your development environment lacks the necessary dependencies like Python 3.7+, CUDA 11+, PyTorch 1.10+, and DeepSpeed 0.6+. In scenarios where an open-source solution is not preferable or when support for exclusively one language's syntax is sufficient. ### Is CodeGen or CodeGeeX more popular on GitHub? CodeGeeX has more GitHub stars (8,809 vs 5,179). 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](/tools/salesforce-codegen/alternatives) and [CodeGeeX alternatives](/tools/zai-org-codegeex/alternatives) ([CodeGen markdown twin](/tools/salesforce-codegen/alternatives.md), [CodeGeeX markdown twin](/tools/zai-org-codegeex/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-zai-org-codegeex.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, CodeGen or CodeGeeX? CodeGen: Steady. 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](/tools/salesforce-codegen/trust); [CodeGeeX trust report](/tools/zai-org-codegeex/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/_