--- title: "cceval vs CodeGeeX" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/amazon-science-cceval-vs-zai-org-codegeex" tools: ["amazon-science-cceval", "zai-org-codegeex"] --- # cceval vs CodeGeeX *GraphCanon updated Oct 8, 2026* ## Verdict Pick cceval if cceval is designed for assessing cross-file code completion capabilities in multilingual environments across different setups and retrieval methods; pick CodeGeeX if 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. [cceval](https://crosscodeeval.github.io/) reports 184 GitHub stars, 29 forks, and 5 open issues, last pushed Aug 15, 2025. [CodeGeeX](https://codegeex.cn) has 8.8k stars, 686 forks, and 189 open issues, last pushed Aug 13, 2024. Figures are from public GitHub metadata via [cceval's repository](https://github.com/amazon-science/cceval) and [CodeGeeX's repository](https://github.com/zai-org/CodeGeeX). | | [cceval](/tools/amazon-science-cceval.md) | [CodeGeeX](/tools/zai-org-codegeex.md) | | --- | --- | --- | | Tagline | CrossCodeEval Benchmark for Cross-File Code Completion | CodeGeeX: An Open Multilingual Code Generation Model | | Stars | 184 | 8,806 | | Forks | 29 | 686 | | Open issues | 5 | 189 | | Language | Python | Python | | Adopt for | cceval is designed for assessing cross-file code completion capabilities in multilingual environments across different setups and retrieval methods. | 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 | - | - | | Runtime | - | - | | License | Apache-2.0 | 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. | | Categories | Evaluation & Observability | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [cceval](/tools/amazon-science-cceval.md) | [CodeGeeX](/tools/zai-org-codegeex.md) | | --- | --- | --- | | Days since push | 418d | 766d | | Open issues (now) | 5 | 189 | | Stars delta | +2 (30d) | -3 (30d) | | Open issues delta | 0 (30d) | +1 (30d) | | Full report | [trust report](/tools/amazon-science-cceval/trust.md) | [trust report](/tools/zai-org-codegeex/trust.md) | ## Shared compatibility - **Python**: [cceval](/tools/amazon-science-cceval.md) - Python runtime; [CodeGeeX](/tools/zai-org-codegeex.md) - Python runtime ## Decision facts: cceval - **Adopt for:** cceval is designed for assessing cross-file code completion capabilities in multilingual environments across different setups and retrieval methods. ## Decision facts: CodeGeeX - **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. - **Adopt for:** 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. - **License detail:** 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. ## Choose when ### Choose cceval if… - Tags unique to cceval: benchmark, code-completion, cross-file, evaluation-tool. - Also covers Evaluation & Observability. - You need to evaluate the performance of cross-file code completion systems that can handle multiple programming languages simultaneously ### 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. - Also covers LLM Frameworks, Model Training. - 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 cceval - Your evaluation needs are focused solely on single-file or intralingual code completion benchmarks - You require real-time data access or live updates; cceval provides pre-packaged datasets that need to be manually obtained and uncompressed ## 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. ## Common questions ### What is the difference between cceval and CodeGeeX? cceval: CrossCodeEval Benchmark for Cross-File Code Completion. CodeGeeX: CodeGeeX: An Open Multilingual Code Generation Model. See the comparison table for live GitHub stats and shared categories. ### When should I choose cceval over CodeGeeX? Choose cceval over CodeGeeX when Tags unique to cceval: benchmark, code-completion, cross-file, evaluation-tool; Also covers Evaluation & Observability; You need to evaluate the performance of cross-file code completion systems that can handle multiple programming languages simultaneously. ### When should I choose CodeGeeX over cceval? Choose CodeGeeX over cceval 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; Also covers LLM Frameworks, Model Training; 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 cceval? Your evaluation needs are focused solely on single-file or intralingual code completion benchmarks You require real-time data access or live updates; cceval provides pre-packaged datasets that need to be manually obtained and uncompressed ### 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 cceval or CodeGeeX more popular on GitHub? CodeGeeX has more GitHub stars (8,806 vs 184). Stars measure visibility, not whether either tool fits your constraints. ### Are cceval and CodeGeeX open source? Yes - both are open-source projects on GitHub (cceval: Apache-2.0, CodeGeeX: Apache-2.0). ### Where can I find alternatives to cceval or CodeGeeX? GraphCanon lists graph-backed alternatives at [cceval alternatives](/tools/amazon-science-cceval/alternatives) and [CodeGeeX alternatives](/tools/zai-org-codegeex/alternatives) ([cceval markdown twin](/tools/amazon-science-cceval/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/amazon-science-cceval-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, cceval or CodeGeeX? cceval: 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 cceval and CodeGeeX? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [cceval trust report](/tools/amazon-science-cceval/trust); [CodeGeeX trust report](/tools/zai-org-codegeex/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=amazon-science-cceval`](/api/graphcanon/graph?tool=amazon-science-cceval) - 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/_