{"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/wizardmath-empowering-mathematical-reasoning","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","arxiv_id":"2308.09583","date":"2023-08-18","proceeding":null,"authors":["Haipeng Luo","Qingfeng Sun","Can Xu","Pu Zhao","JianGuang Lou","Chongyang Tao","Xiubo Geng","QIngwei Lin","Shifeng Chen","Yansong Tang","Dongmei Zhang"],"abstract":"Large language models (LLMs), such as GPT-4, have shown remarkable performance in natural language processing (NLP) tasks, including challenging mathematical reasoning. However, most existing open-source models are only pre-trained on large-scale internet data and without math-related optimization. In this paper, we present WizardMath, which enhances the mathematical CoT reasoning abilities of LLMs without using external python tools, by applying our proposed Reinforcement Learning from Evol-Instruct Feedback (RLEIF) method to the domain of math. Through extensive experiments on two mathematical reasoning benchmarks, namely GSM8k and MATH, we reveal the extraordinary capabilities of our model. Remarkably, WizardMath-Mistral 7B surpasses top-tier open-source LLMs by a substantial margin with higher data efficiency. Furthermore, WizardMath 70B even outperforms GPT-3.5-Turbo, Claude 2, Gemini Pro and GPT-4-early-version. Additionally, our preliminary exploration highlights the pivotal role of instruction evolution and process supervision in achieving exceptional math performance. For more details refer to https://github.com/nlpxucan/WizardLM","url_abs":"https://arxiv.org/abs/2308.09583v2","url_pdf":"https://arxiv.org/pdf/2308.09583v2.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":"wizardmath-empowering-mathematical-reasoning","repo_url":"https://github.com/nlpxucan/wizardlm","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"WizardMath-7B-V1.1","rank_in_archive_order":54,"of":164,"metrics":{"Accuracy":"83.2","Parameters (Billion)":"7"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"WizardMath-70B-V1.0","rank_in_archive_order":64,"of":164,"metrics":{"Accuracy":"81.6","Parameters (Billion)":"70"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"WizardMath-13B-V1.0","rank_in_archive_order":113,"of":164,"metrics":{"Accuracy":"63.9","Parameters (Billion)":"13"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"WizardMath-7B-V1.0","rank_in_archive_order":128,"of":164,"metrics":{"Accuracy":"54.9","Parameters (Billion)":"7"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"WizardMath-7B-V1.1","rank_in_archive_order":85,"of":135,"metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"WizardMath-70B-V1.0","rank_in_archive_order":99,"of":135,"metrics":{"Accuracy":"22.7","Parameters (Billions)":"70"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"WizardMath-13B-V1.0","rank_in_archive_order":110,"of":135,"metrics":{"Accuracy":"14.0","Parameters (Billions)":"13"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"WizardMath-7B-V1.0","rank_in_archive_order":115,"of":135,"metrics":{"Accuracy":"10.7","Parameters (Billions)":"7"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.09583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09583"}},"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":"deterministic:regex_extraction","url":"https://github.com/nlpxucan/WizardLM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nlpxucan/wizardlm","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"named_in_paper":{"samples":16,"ran":10,"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":16,"samples":[{"code_sha256_prefix":"410f51b076230435","entry":"createBreadthPrompt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"Evol_Instruct/breadth.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/Evol_Instruct/breadth.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"410f51b076230435"}},{"code_sha256_prefix":"d28ba5ece582e599","entry":"createConcretizingPrompt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"Evol_Instruct/depth.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/Evol_Instruct/depth.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d28ba5ece582e599"}},{"code_sha256_prefix":"e549385d87bbf8ef","entry":"createConstraintsPrompt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"Evol_Instruct/depth.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/Evol_Instruct/depth.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e549385d87bbf8ef"}},{"code_sha256_prefix":"7a497b34ae3bc6e2","entry":"createDeepenPrompt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"Evol_Instruct/depth.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/Evol_Instruct/depth.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a497b34ae3bc6e2"}},{"code_sha256_prefix":"7a733b18081436f3","entry":"extract_text","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardCoder/src/mbpp_gen.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardCoder/src/mbpp_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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a733b18081436f3"}},{"code_sha256_prefix":"0bd14db8e7b2cb18","entry":"generate_prompt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardLM/src/inference_wizardlm.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardLM/src/inference_wizardlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0bd14db8e7b2cb18"}},{"code_sha256_prefix":"e8a51ca7c61c54e2","entry":"generate_prompt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardCoder/src/humaneval_gen.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardCoder/src/humaneval_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8a51ca7c61c54e2"}},{"code_sha256_prefix":"0773321052909441","entry":"generate_prompt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardCoder/src/inference_wizardcoder.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardCoder/src/inference_wizardcoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0773321052909441"}},{"code_sha256_prefix":"13dc99a819a4f615","entry":"generate_prompt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardCoder/src/mbpp_gen.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardCoder/src/mbpp_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"13dc99a819a4f615"}},{"code_sha256_prefix":"51c01dd0d033f660","entry":"preprocess","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardLM/src/train_freeform.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardLM/src/train_freeform.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"51c01dd0d033f660"}},{"code_sha256_prefix":"55025d9bb2011c5a","entry":"call_chatgpt","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"Evol_Instruct/openai_access.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/Evol_Instruct/openai_access.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55025d9bb2011c5a"}},{"code_sha256_prefix":"8f1e18f0c59b59be","entry":"evaluate","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardLM/src/inference_wizardlm.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardLM/src/inference_wizardlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f1e18f0c59b59be"}},{"code_sha256_prefix":"e03723b85938f4f0","entry":"evaluate","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardCoder/src/inference_wizardcoder.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardCoder/src/inference_wizardcoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e03723b85938f4f0"}},{"code_sha256_prefix":"fcb999210417b348","entry":"get_model","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardCoder/src/humaneval_gen.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardCoder/src/humaneval_gen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fcb999210417b348"}},{"code_sha256_prefix":"9aa01a80f5634d81","entry":"get_oai_completion","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"Evol_Instruct/openai_access.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/Evol_Instruct/openai_access.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9aa01a80f5634d81"}},{"code_sha256_prefix":"e7c8e0d548af8b2f","entry":"main","repo":"nlpxucan/WizardLM","repo_kind":"named_in_paper","path":"WizardLM/src/infer_wizardlm13b.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardLM/src/infer_wizardlm13b.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7c8e0d548af8b2f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}