--- title: "CodeBERT vs CodeT" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-codebert-vs-microsoft-codet" tools: ["microsoft-codebert", "microsoft-codet"] --- # CodeBERT vs CodeT *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 CodeT if projects from Microsoft to upgrade large-scale pretrained language models for programming and reasoning tasks. [CodeBERT](https://github.com/microsoft/CodeBERT) reports 2.8k GitHub stars, 497 forks, and 86 open issues, last pushed Jul 9, 2023. [CodeT](https://github.com/microsoft/CodeT) has 678 stars, 86 forks, and 10 open issues, last pushed Nov 1, 2024. Figures are from public GitHub metadata via [CodeBERT's repository](https://github.com/microsoft/CodeBERT) and [CodeT's repository](https://github.com/microsoft/CodeT). | | [CodeBERT](/tools/microsoft-codebert.md) | [CodeT](/tools/microsoft-codet.md) | | --- | --- | --- | | Tagline | CodeBERT series models for code pretraining in Python and programming languages | CodeT | | Stars | 2,787 | 678 | | Forks | 497 | 86 | | Open issues | 86 | 10 | | 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. | Projects from Microsoft to upgrade large-scale pretrained language models for programming and reasoning tasks. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | Model Training | Developer Tools, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [CodeBERT](/tools/microsoft-codebert.md) | [CodeT](/tools/microsoft-codet.md) | | --- | --- | --- | | Days since push | 1123d | 642d | | Open issues (now) | 86 | 10 | | Full report | [trust report](/tools/microsoft-codebert/trust.md) | [trust report](/tools/microsoft-codet/trust.md) | ## 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: CodeT - **Adopt for:** Projects from Microsoft to upgrade large-scale pretrained language models for programming and reasoning tasks. ## Choose when ### Choose CodeBERT if… - 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 CodeT if… - Tags unique to CodeT: language-models, programming, reasoning. - Also covers Developer Tools. - When you need advanced code generation with test generation features. ## 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 CodeT - Avoid if your project strictly needs a different programming task than those provided by CodeT projects. - Skip if your workflow does not support or benefit from an enhanced reasoning capability in models. ## Common questions ### What is the difference between CodeBERT and CodeT? CodeBERT: CodeBERT series models for code pretraining in Python and programming languages. CodeT: CodeT. See the comparison table for live GitHub stats and shared categories. ### When should I choose CodeBERT over CodeT? Choose CodeBERT over CodeT when 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 CodeT over CodeBERT? Choose CodeT over CodeBERT when Tags unique to CodeT: language-models, programming, reasoning; Also covers Developer Tools; When you need advanced code generation with test generation features. ### 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 CodeT? Avoid if your project strictly needs a different programming task than those provided by CodeT projects. Skip if your workflow does not support or benefit from an enhanced reasoning capability in models. ### Is CodeBERT or CodeT more popular on GitHub? CodeBERT has more GitHub stars (2,787 vs 678). Stars measure visibility, not whether either tool fits your constraints. ### Are CodeBERT and CodeT open source? Yes - both are open-source projects on GitHub (CodeBERT: MIT, CodeT: MIT). ### Where can I find alternatives to CodeBERT or CodeT? GraphCanon lists graph-backed alternatives at [CodeBERT alternatives](/tools/microsoft-codebert/alternatives) and [CodeT alternatives](/tools/microsoft-codet/alternatives) ([CodeBERT markdown twin](/tools/microsoft-codebert/alternatives.md), [CodeT markdown twin](/tools/microsoft-codet/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-microsoft-codet.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, CodeBERT or CodeT? CodeBERT: Dormant. CodeT: 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 CodeT? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [CodeBERT trust report](/tools/microsoft-codebert/trust); [CodeT trust report](/tools/microsoft-codet/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/_