--- title: "CodeBERT vs CodeGeeX" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-codebert-vs-zai-org-codegeex" tools: ["microsoft-codebert", "zai-org-codegeex"] --- # CodeBERT vs CodeGeeX *GraphCanon updated Aug 5, 2026* ## Verdict Pick CodeBERT if codeBERT is an advanced pre-trained model for programming and natural language tasks in multiple languages like Python and Java; pick CodeGeeX if codeGeeX is an open-source multilingual code generation model, originally developed with MindSpore and compatible with PyTorch through DeepSpeed integration. [CodeBERT](https://github.com/microsoft/CodeBERT) reports 2.8k GitHub stars, 497 forks, and 86 open issues, last pushed Jul 9, 2023. [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 [CodeBERT's repository](https://github.com/microsoft/CodeBERT) and [CodeGeeX's repository](https://github.com/zai-org/CodeGeeX). | | [CodeBERT](/tools/microsoft-codebert.md) | [CodeGeeX](/tools/zai-org-codegeex.md) | | --- | --- | --- | | Tagline | CodeBERT series models for code pretraining in Python and programming languages | CodeGeeX is an open multilingual code generation model implemented in Mindspore and available via PyTorch. | | Stars | 2,787 | 8,809 | | Forks | 497 | 688 | | Open issues | 86 | 188 | | Language | Python | Python | | Adopt for | CodeBERT is an advanced pre-trained model for programming and natural language tasks in multiple languages like Python and Java. | CodeGeeX is an open-source multilingual code generation model, originally developed with MindSpore and compatible with PyTorch through DeepSpeed integration. | | Persona | - | - | | Runtime | - | - | | License | MIT | Apache-2.0 | | Categories | Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [CodeBERT](/tools/microsoft-codebert.md) | [CodeGeeX](/tools/zai-org-codegeex.md) | | --- | --- | --- | | Days since push | 1123d | 719d | | Open issues (now) | 86 | 188 | | Full report | [trust report](/tools/microsoft-codebert/trust.md) | [trust report](/tools/zai-org-codegeex/trust.md) | ## Shared compatibility - **Python**: [CodeBERT](/tools/microsoft-codebert.md) - Python runtime; [CodeGeeX](/tools/zai-org-codegeex.md) - Python runtime ## Decision facts: CodeBERT - **Requirements:** Install torch and transformers via pip before using CodeBERT for embedding generation or other tasks; Ensure Python and Hugging Face's transformers framework are available, as they form the core execution environment for utilizing this model - **Adopt for:** CodeBERT is an advanced pre-trained model for programming and natural language tasks in multiple languages like Python and Java. ## 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 CodeBERT if… - License: CodeBERT is MIT, CodeGeeX is Apache-2.0. - Requirements: Install torch and transformers via pip before using CodeBERT for embedding generation or other tasks; Ensure Python and Hugging Face's transformers framework are available, as they form the core execution environment for utilizing this model. - Tags unique to CodeBERT: code pretraining, transformers framework. - When you need to work on tasks involving both programming and natural language processing across six different programming languages: Python, Java, JavaScript, PHP, Ruby, Go ### Choose CodeGeeX if… - License: CodeGeeX is Apache-2.0, CodeBERT is MIT. - Tags unique to CodeGeeX: ai programming tools, code generation, pretrained-models. - Also covers LLM Frameworks. - When you require support for multilingual code generation and your project has a Python-based infrastructure with CUDA GPU availability. ## When NOT to use CodeBERT - Avoid for direct mask prediction tasks without MLM (Masked Language Model) fine-tuning as CodeBERT is not natively equipped for such tasks unlike its variant designed with MLM capabilities - Do not consider it if your project requires pre-training models on a wider variety of programming languages beyond the six supported by this model ## 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 CodeBERT and CodeGeeX? CodeBERT: CodeBERT series models for code pretraining in Python and programming languages. 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 CodeBERT over CodeGeeX? Choose CodeBERT over CodeGeeX when License: CodeBERT is MIT, CodeGeeX is Apache-2.0; Requirements: Install torch and transformers via pip before using CodeBERT for embedding generation or other tasks; Ensure Python and Hugging Face's transformers framework are available, as they form the core execution environment for utilizing this model; Tags unique to CodeBERT: code pretraining, transformers framework; When you need to work on tasks involving both programming and natural language processing across six different programming languages: Python, Java, JavaScript, PHP, Ruby, Go. ### When should I choose CodeGeeX over CodeBERT? Choose CodeGeeX over CodeBERT when License: CodeGeeX is Apache-2.0, CodeBERT is MIT; Tags unique to CodeGeeX: ai programming tools, code generation, pretrained-models; Also covers LLM Frameworks; When you require support for multilingual code generation and your project has a Python-based infrastructure with CUDA GPU availability. ### When should I avoid CodeBERT? Avoid for direct mask prediction tasks without MLM (Masked Language Model) fine-tuning as CodeBERT is not natively equipped for such tasks unlike its variant designed with MLM capabilities Do not consider it if your project requires pre-training models on a wider variety of programming languages beyond the six supported by this model ### 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 CodeBERT or CodeGeeX more popular on GitHub? CodeGeeX has more GitHub stars (8,809 vs 2,787). Stars measure visibility, not whether either tool fits your constraints. ### Are CodeBERT and CodeGeeX open source? Yes - both are open-source projects on GitHub (CodeBERT: MIT, CodeGeeX: Apache-2.0). ### Where can I find alternatives to CodeBERT or CodeGeeX? GraphCanon lists graph-backed alternatives at [CodeBERT alternatives](/tools/microsoft-codebert/alternatives) and [CodeGeeX alternatives](/tools/zai-org-codegeex/alternatives) ([CodeBERT markdown twin](/tools/microsoft-codebert/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/microsoft-codebert-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, CodeBERT or CodeGeeX? CodeBERT: Dormant. 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 CodeBERT and CodeGeeX? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [CodeBERT trust report](/tools/microsoft-codebert/trust); [CodeGeeX trust report](/tools/zai-org-codegeex/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=microsoft-codebert`](/api/graphcanon/graph?tool=microsoft-codebert) - 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/_