{"data":{"slug":"amazon-science-cceval","name":"cceval","tagline":"CrossCodeEval Benchmark for Cross-File Code Completion","github_url":"https://github.com/amazon-science/cceval","owner":"amazon-science","repo":"cceval","owner_avatar_url":"https://avatars.githubusercontent.com/u/70298811?v=4","primary_language":"Python","stars":184,"forks":29,"topics":[],"archived":false,"github_pushed_at":"2025-08-15T21:11:15+00:00","maintenance_label":"Dormant","stars_delta_30d":2,"url":"https://www.graphcanon.com/tools/amazon-science-cceval","markdown_url":"https://www.graphcanon.com/tools/amazon-science-cceval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/amazon-science-cceval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=amazon-science-cceval","description":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)","homepage_url":"https://crosscodeeval.github.io/","license":"Apache-2.0","open_issues":5,"watchers":5,"ai_summary":"A diverse and multilingual benchmark aimed at evaluating cross-file code completion across various settings and retrievers.","readme_excerpt":"## Requirements\n\n- Uncompress the CrossCodeEval data via `tar -xvJf data/crosscodeeval_data.tar.xz -C data/`\n    - The data contains {baseline, retrieval, retrieval w/ ref.} setting x {bm25, UniXCoder, OpenAI Ada} retriever.\n    - **Please [email us](mailto:y.robin.ding@gmail.com) if you need the raw data.**\n- Install dependencies via `pip install -r requirements.txt`\n- Build tree sitter via `bash scripts/build_treesitter.sh`\n\n---\n\n## License\n\nThis project is licensed under the Apache-2.0 License.","github_created_at":"2023-10-16T04:23:03+00:00","created_at":"2026-07-11T23:46:05.036182+00:00","updated_at":"2026-10-08T06:00:21.970539+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"benchmark","name":"benchmark"},{"slug":"code-completion","name":"code-completion"},{"slug":"cross-file","name":"cross-file"},{"slug":"evaluation-tool","name":"evaluation-tool"},{"slug":"multilingual","name":"multilingual"},{"slug":"neurips-2023","name":"neurips-2023"}],"trust":{"provenance":{"is_fork":false,"github_id":705470018,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-10-08T06:00:20.961Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":418,"last_release_at":null,"stars_delta_30d":2,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":21,"high_count":7,"last_scan_at":"2026-07-11T23:46:07.567Z","medium_count":8,"scan_profile":"deps","critical_count":5}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-10-08T06:00:21.634Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-10-08T06:00:21.634Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-10-08T06:00:21.634Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need to evaluate the performance of cross-file code completion systems that can handle multiple programming languages simultaneously","Your project requires a benchmark with various settings including baseline, retrieval with references, and pure retrieval approaches"],"when_not_to_use":["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"],"source":"enrich:decision_facts","observed_at":"2026-07-17T11:55:01.772Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"cceval is designed for assessing cross-file code completion capabilities in multilingual environments across different setups and retrieval methods."}]}}