{"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/wizardcoder-empowering-code-large-language","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","arxiv_id":"2306.08568","date":"2023-06-14","proceeding":null,"authors":["Ziyang Luo","Can Xu","Pu Zhao","Qingfeng Sun","Xiubo Geng","Wenxiang Hu","Chongyang Tao","Jing Ma","QIngwei Lin","Daxin Jiang"],"abstract":"Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In this paper, we introduce WizardCoder, which empowers Code LLMs with complex instruction fine-tuning, by adapting the Evol-Instruct method to the domain of code. Through comprehensive experiments on four prominent code generation benchmarks, namely HumanEval, HumanEval+, MBPP, and DS-1000, we unveil the exceptional capabilities of our model. It surpasses all other open-source Code LLMs by a substantial margin. Moreover, our model even outperforms the largest closed LLMs, Anthropic's Claude and Google's Bard, on HumanEval and HumanEval+. Our code, model weights, and data are public at https://github.com/nlpxucan/WizardLM","url_abs":"https://arxiv.org/abs/2306.08568v1","url_pdf":"https://arxiv.org/pdf/2306.08568v1.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":"wizardcoder-empowering-code-large-language","repo_url":"https://github.com/nlpxucan/wizardlm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wizardcoder-empowering-code-large-language","repo_url":"https://github.com/kyle-lyu/codeact","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wizardcoder-empowering-code-large-language","repo_url":"https://github.com/kyle-lyu/data-efficient-finetuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"wizardcoder-empowering-code-large-language","repo_url":"https://github.com/nickrosh/evol-teacher","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"humaneval","task_name":"HumanEval"},{"task_slug":null,"task_name":"mbpp"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-codecontests","task":"Code Generation","dataset":"CodeContests","model":"WizardCoder-15B","rank_in_archive_order":8,"of":8,"metrics":{"Test Set pass@1":"1.11","Test Set pass@5":"3.18","Val Set pass@1":"1.98","Val Set pass@5":"3.27"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"WizardCoder 15B","rank_in_archive_order":58,"of":99,"metrics":{"Accuracy":"51.8"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.08568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08568"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/nlpxucan/wizardlm","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kyle-lyu/codeact","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kyle-lyu/data-efficient-finetuning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nickrosh/evol-teacher","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":1,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"ran":3,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"fb57aad9f9c18c48","entry":"construct_prompt","repo":"kyle-lyu/data-efficient-finetuning","repo_kind":"listed","path":"utils/dataset.py","file_url":"https://github.com/kyle-lyu/data-efficient-finetuning/blob/HEAD/utils/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb57aad9f9c18c48"}},{"code_sha256_prefix":"7a733b18081436f3","entry":"extract_text","repo":"nickrosh/evol-teacher","repo_kind":"listed","path":"humaneval_gen.py","file_url":"https://github.com/nickrosh/evol-teacher/blob/HEAD/humaneval_gen.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a733b18081436f3"}},{"code_sha256_prefix":"13dc99a819a4f615","entry":"generate_prompt","repo":"nickrosh/evol-teacher","repo_kind":"listed","path":"humaneval_gen.py","file_url":"https://github.com/nickrosh/evol-teacher/blob/HEAD/humaneval_gen.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"13dc99a819a4f615"}},{"code_sha256_prefix":"55673ce583151195","entry":"check_instruction","repo":"nickrosh/evol-teacher","repo_kind":"listed","path":"generate_evol.py","file_url":"https://github.com/nickrosh/evol-teacher/blob/HEAD/generate_evol.py","link_basis":"harvester_set","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":"55673ce583151195"}},{"code_sha256_prefix":"bb994e5a934af0d1","entry":"convert_alpaca_to_evol","repo":"nickrosh/evol-teacher","repo_kind":"listed","path":"generate_evol.py","file_url":"https://github.com/nickrosh/evol-teacher/blob/HEAD/generate_evol.py","link_basis":"harvester_set","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":"bb994e5a934af0d1"}},{"code_sha256_prefix":"c7517f1da7dd5864","entry":"get_model","repo":"nickrosh/evol-teacher","repo_kind":"listed","path":"humaneval_gen.py","file_url":"https://github.com/nickrosh/evol-teacher/blob/HEAD/humaneval_gen.py","link_basis":"harvester_set","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":"c7517f1da7dd5864"}},{"code_sha256_prefix":"c618c35455396999","entry":"load_instructions","repo":"nickrosh/evol-teacher","repo_kind":"listed","path":"generate_evol.py","file_url":"https://github.com/nickrosh/evol-teacher/blob/HEAD/generate_evol.py","link_basis":"harvester_set","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":"c618c35455396999"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}