{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/taco-topics-in-algorithmic-code-generation","title":"TACO: Topics in Algorithmic COde generation dataset","arxiv_id":"2312.14852","date":"2023-12-22","proceeding":null,"authors":["Rongao Li","Jie Fu","Bo-Wen Zhang","Tao Huang","Zhihong Sun","Chen Lyu","Guang Liu","Zhi Jin","Ge Li"],"abstract":"We introduce TACO, an open-source, large-scale code generation dataset, with a focus on the optics of algorithms, designed to provide a more challenging training dataset and evaluation benchmark in the field of code generation models. TACO includes competition-level programming questions that are more challenging, to enhance or evaluate problem understanding and reasoning abilities in real-world programming scenarios. There are 25433 and 1000 coding problems in training and test set, as well as up to 1.55 million diverse solution answers. Moreover, each TACO problem includes several fine-grained labels such as task topics, algorithms, programming skills, and difficulty levels, providing a more precise reference for the training and evaluation of code generation models. The dataset and evaluation scripts are available on Hugging Face Hub (https://huggingface.co/datasets/BAAI/TACO) and Github (https://github.com/FlagOpen/TACO).","url_abs":"https://arxiv.org/abs/2312.14852v3","url_pdf":"https://arxiv.org/pdf/2312.14852v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"taco-topics-in-algorithmic-code-generation","repo_url":"https://github.com/flagopen/taco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[{"slug":"taco-topics-in-algorithmic-code-generation","name":"TACO-BAAI","full_name":"Topics in Algorithmic Code generation dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-taco-code","task":"Code Generation","dataset":"TACO-BAAI","model":"GPT-4","rank_in_archive_order":1,"of":3,"metrics":{"easy pass@1":"31.50%"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-taco-code","task":"Code Generation","dataset":"TACO-BAAI","model":"Starcoder-15.5B","rank_in_archive_order":2,"of":3,"metrics":{"easy pass@1":"11.6%"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-taco-code","task":"Code Generation","dataset":"TACO-BAAI","model":"CodeLlama-7B-Python","rank_in_archive_order":3,"of":3,"metrics":{"easy pass@1":"9.32%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.14852","atlas_url":"https://app.syntology.ai/?focus=2312.14852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14852"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flagopen/taco","reach":null}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"22edb7e072a27088","entry":"preprocess_scores","repo":"flagopen/taco","repo_kind":"official","path":"datamodule/taco_dataset.py","file_url":"https://github.com/flagopen/taco/blob/HEAD/datamodule/taco_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"22edb7e072a27088"}},{"code_sha256_prefix":"cd0076785940b1fe","entry":"preprocess","repo":"flagopen/taco","repo_kind":"official","path":"datamodule/taco_dataset.py","file_url":"https://github.com/flagopen/taco/blob/HEAD/datamodule/taco_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd0076785940b1fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}