--- title: "cceval vs lever" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/amazon-science-cceval-vs-niansong1996-lever" tools: ["amazon-science-cceval", "niansong1996-lever"] --- # cceval vs lever *GraphCanon updated Aug 5, 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 lever if lever offers support for verifying language-to-code generation through actual code execution. [cceval](https://crosscodeeval.github.io/) reports 182 GitHub stars, 28 forks, and 5 open issues, last pushed Aug 15, 2025. [lever](https://arxiv.org/abs/2302.08468) has 90 stars, 8 forks, and 2 open issues, last pushed Jul 5, 2023. Figures are from public GitHub metadata via [cceval's repository](https://github.com/amazon-science/cceval) and [lever's repository](https://github.com/niansong1996/lever). | | [cceval](/tools/amazon-science-cceval.md) | [lever](/tools/niansong1996-lever.md) | | --- | --- | --- | | Tagline | CrossCodeEval Benchmark for Cross-File Code Completion | Supports learning to verify language-to-code generation with execution | | Stars | 182 | 90 | | Forks | 28 | 8 | | Open issues | 5 | 2 | | Language | Python | Python | | Adopt for | cceval is designed for assessing cross-file code completion capabilities in multilingual environments across different setups and retrieval methods. | Lever offers support for verifying language-to-code generation through actual code execution. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Lever's source code is freely available under an MIT License for modification and distribution in both personal and commercial projects. | | Categories | Evaluation & Observability | Evaluation & Observability, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [cceval](/tools/amazon-science-cceval.md) | [lever](/tools/niansong1996-lever.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Dormant (18%) | | Days since push | 354d | 1127d | | Open issues (now) | 5 | 2 | | Owner type | Organization | User | | Full report | [trust report](/tools/amazon-science-cceval/trust.md) | [trust report](/tools/niansong1996-lever/trust.md) | ## Shared compatibility - **Python**: [cceval](/tools/amazon-science-cceval.md) - Python runtime; [lever](/tools/niansong1996-lever.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: lever - **Requirements:** All of the pipelines have been tested on Linux machines only, requiring possibly custom `tree-sitter` parsers for other platforms. - **Adopt for:** Lever offers support for verifying language-to-code generation through actual code execution. - **License detail:** Lever's source code is freely available under an MIT License for modification and distribution in both personal and commercial projects. ## Choose when ### Choose cceval if… - License: cceval is Apache-2.0, lever is MIT. - Tags unique to cceval: benchmark, code-completion, cross-file, evaluation-tool. - You need to evaluate the performance of cross-file code completion systems that can handle multiple programming languages simultaneously ### Choose lever if… - License: lever is MIT, cceval is Apache-2.0. - Requirements: All of the pipelines have been tested on Linux machines only, requiring possibly custom `tree-sitter` parsers for other platforms.. - Tags unique to lever: code verification, execution based verification, language-to-code. - Also covers Model Training. - When the development team needs to verify accuracy of generated code from language inputs based on execution, and has access to Linux machines to ensure seamless functionality. ## 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 lever - Avoid Lever if developing in an environment other than Linux as it requires the use of tree-sitter parsers, which may not be compatible with your system. - Do not choose Lever if you seek a tool that does not require setting up a conda environment and installing specific dependencies to operate. ## Common questions ### What is the difference between cceval and lever? cceval: CrossCodeEval Benchmark for Cross-File Code Completion. lever: Supports learning to verify language-to-code generation with execution. See the comparison table for live GitHub stats and shared categories. ### When should I choose cceval over lever? Choose cceval over lever when License: cceval is Apache-2.0, lever is MIT; Tags unique to cceval: benchmark, code-completion, cross-file, evaluation-tool; You need to evaluate the performance of cross-file code completion systems that can handle multiple programming languages simultaneously. ### When should I choose lever over cceval? Choose lever over cceval when License: lever is MIT, cceval is Apache-2.0; Requirements: All of the pipelines have been tested on Linux machines only, requiring possibly custom `tree-sitter` parsers for other platforms.; Tags unique to lever: code verification, execution based verification, language-to-code; Also covers Model Training; When the development team needs to verify accuracy of generated code from language inputs based on execution, and has access to Linux machines to ensure seamless functionality. ### 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 lever? Avoid Lever if developing in an environment other than Linux as it requires the use of tree-sitter parsers, which may not be compatible with your system. Do not choose Lever if you seek a tool that does not require setting up a conda environment and installing specific dependencies to operate. ### Is cceval or lever more popular on GitHub? cceval has more GitHub stars (182 vs 90). Stars measure visibility, not whether either tool fits your constraints. ### Are cceval and lever open source? Yes - both are open-source projects on GitHub (cceval: Apache-2.0, lever: MIT). ### Where can I find alternatives to cceval or lever? GraphCanon lists graph-backed alternatives at [cceval alternatives](/tools/amazon-science-cceval/alternatives) and [lever alternatives](/tools/niansong1996-lever/alternatives) ([cceval markdown twin](/tools/amazon-science-cceval/alternatives.md), [lever markdown twin](/tools/niansong1996-lever/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-niansong1996-lever.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, cceval or lever? cceval: Slowing. lever: 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 lever? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [cceval trust report](/tools/amazon-science-cceval/trust); [lever trust report](/tools/niansong1996-lever/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/_