Alternatives hub · graph-backed
CodeGeeX alternatives
In short
Top alternatives to CodeGeeX are CodeGen and CodeT5, ranked by typed graph edges - model-training.
Not a popularity vote. Each alternative is a typed graph neighbor of CodeGeeX in LLM Frameworks, Model Training - ranked by edge type and constraint overlap, with live GitHub stats shown for context.
CodeGeeX trust report - maintenance, provenance, and scan signals for CodeGeeX.
GraphCanon updated Sep 20, 2026 · GitHub pushed Aug 13, 2024
33views this month
CodeGeeX alternatives (markdown)
Comparison table
Top graph-backed alternatives with live GitHub stars. Use the compare link for a full head-to-head.
| Alternative | Stars | Language | Relation | Why | Compare |
|---|---|---|---|---|---|
| CodeGen | 5.2k | Python | same category | A family of open-source models for program synthesis | Compare |
| CodeT5 | 3.1k | Python | same category | Open Code LLMs for Code Understanding and Generation | Compare |
| OpenCoder-llm | 2.1k | Python | same category | The Open Cookbook for Top-Tier Code Large Language Models | Compare |
| Awesome-Code-LLM | 1.3k | - | same category | 👨💻 An awesome and curated list of best code-LLM for research | Compare |
| CodeBERT | 2.8k | Python | same category | CodeBERT series models for code pretraining in Python and programming languages | Compare |
| Hands-On-Large-Language-Models | 29k | Jupyter Notebook | same category | Code for the book 'Hands-On Large Language Models' | Compare |
| bigcode-evaluation-harness | 1.1k | Python | same category | A framework for evaluating autoregressive code generation language models | Compare |
| cceval | 184 | Python | same category | CrossCodeEval Benchmark for Cross-File Code Completion | Compare |
A family of open-source models for program synthesis
Open Code LLMs for Code Understanding and Generation
The Open Cookbook for Top-Tier Code Large Language Models
👨💻 An awesome and curated list of best code-LLM for research.
CodeBERT series models for code pretraining in Python and programming languages
Code for the book 'Hands-On Large Language Models'
A framework for evaluating autoregressive code generation language models.
CrossCodeEval Benchmark for Cross-File Code Completion
Breaking the Barrier of Closed-Source Models in Code Intelligence
Holistic and contamination-free evaluation of large language models for code
When NOT to use CodeGeeX
Constraint-first guidance from category fit and live maintenance signals - not marketing copy.
- 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.
Related alternatives hubs
High-intent OSS-vs-OSS alternatives pages elsewhere in the graph (including vector-DB picks for Pinecone-style queries).
Head-to-head comparisons
Common questions
- What are the best alternatives to CodeGeeX?
- Graph-backed alternatives to CodeGeeX (8.8k GitHub stars) include CodeGen (5.2k stars, same category); CodeT5 (3.1k stars, same category); OpenCoder-llm (2.1k stars, same category); Awesome-Code-LLM (1.3k stars, same category); CodeBERT (2.8k stars, same category). GraphCanon ranks them by typed relationship edges and constraint overlap, not marketing votes or raw star sort.
- How does GraphCanon rank CodeGeeX alternatives?
- Direct alternative and successor edges from the knowledge graph come first, ordered by edge type and shared constraint facets (persona, runtime, hosting). Category neighbours fill the list only after curated edges. Stars are shown for context, not as the primary sort.
- 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 CodeGeeX open source?
- Yes. CodeGeeX is an open-source project on GitHub under the Apache-2.0 license, with 8,806 stars.
- What is CodeGeeX used for?
- CodeGeeX is an open-source multilingual code generation model initially implemented in Mindspore and trained on Ascend 910 AI Processors. It offers a torch-compatible version for GPU platforms.
- What category is CodeGeeX in?
- CodeGeeX is categorized under LLM Frameworks, Model Training in the GraphCanon knowledge graph.
- How do CodeGeeX alternatives compare head-to-head?
- Each alternative has a neutral compare page against CodeGeeX, for example CodeGen vs CodeGeeX, CodeT5 vs CodeGeeX, OpenCoder-llm vs CodeGeeX. Stats come from live GitHub metadata.
- Is there a machine-readable alternatives list?
- Yes. The markdown twin at CodeGeeX alternatives lists direct alternatives and same-category tools with internal links to each tool markdown page.
- Where are other high-intent alternatives hubs?
- Related P0 OSS-vs-OSS hubs: LangChain alternatives, LlamaIndex alternatives, Qdrant alternatives, FinRobot alternatives, free-llm-api-resources alternatives, caveman alternatives, rtk alternatives, unsloth alternatives, ollama alternatives. Vector-database intent (including Pinecone-style queries) is covered at Qdrant alternatives.
- Where can I see maintenance and security signals for CodeGeeX?
- GraphCanon publishes a sourced trust report for CodeGeeX at CodeGeeX trust report - maintenance posture, fork provenance, and dependency/MCP scan status with methodology tags. Not a safety grade.