Papers › WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced...

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

18 Aug 2023arXiv:2308.09583archive 2025-07-28

Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, JianGuang Lou, Chongyang Tao, Xiubo Geng, QIngwei Lin, Shifeng Chen, Yansong Tang, Dongmei Zhang

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

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: named in the paper: 16 samples from 1 repository, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nlpxucan/wizardlm mentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 10 ran (3 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
7ran
6unverified

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from nlpxucan/wizardlm. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

nlpxucan/wizardlm named in the paper 16 samples, 10 ran (3 instrument-failed) · 6 unverified
createBreadthPrompt Evol_Instruct/breadth.py ran fingerprinted no licence file found · pointer only · 410f51b076230435 · report fixture: signature instruction:str/0/str · returned str · level recorded 2026-09-24
createConcretizingPrompt Evol_Instruct/depth.py ran fingerprinted no licence file found · pointer only · d28ba5ece582e599 · report fixture: signature instruction:str/0/str · returned str · level recorded 2026-09-24
createConstraintsPrompt Evol_Instruct/depth.py ran · our draft was wrong fingerprinted no licence file found · pointer only · e549385d87bbf8ef · report fixture: signature instruction:str/0/str · returned str · level recorded 2026-09-22
createDeepenPrompt Evol_Instruct/depth.py ran fingerprinted no licence file found · pointer only · 7a497b34ae3bc6e2 · report fixture: signature instruction:str/0/str · returned str · level recorded 2026-09-24
extract_text in 13 papers WizardCoder/src/mbpp_gen.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 7a733b18081436f3 · report fixture: signature prompt:str/0/str, remove_lines:bool/0/bool · returned str · level recorded 2026-09-22
generate_prompt in 110 papers WizardLM/src/inference_wizardlm.py ran fingerprinted no licence file found · pointer only · 0bd14db8e7b2cb18 · report fixture: signature instruction:str/0/str, input:str/0/str · returned str · level recorded 2026-09-24
generate_prompt in 110 papers WizardCoder/src/humaneval_gen.py ran fingerprinted no licence file found · pointer only · e8a51ca7c61c54e2 · report fixture: signature input:str/0/str · returned str · level recorded 2026-09-24
generate_prompt in 110 papers WizardCoder/src/inference_wizardcoder.py ran fingerprinted no licence file found · pointer only · 0773321052909441 · report fixture: signature instruction:str/0/str, input:NoneType/0/? · returned str · level recorded 2026-09-24
generate_prompt in 110 papers WizardCoder/src/mbpp_gen.py ran fingerprinted no licence file found · pointer only · 13dc99a819a4f615 · report fixture: signature input:str/0/str · returned str · level recorded 2026-09-24
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
WizardLM/src/train_freeform.py ran · our draft was wrong no licence file found · pointer only · 51c01dd0d033f660 · report fixture: signature sources:list/1/str, targets:list/1/str, tokenizer:callable/0/? · returned dict · level recorded 2026-09-24
call_chatgpt in 5 papers Evol_Instruct/openai_access.py unverified no licence file found · pointer only · 55025d9bb2011c5a · report
evaluate in 514 papers WizardLM/src/inference_wizardlm.py unverified no licence file found · pointer only · 8f1e18f0c59b59be · report
evaluate in 514 papers WizardCoder/src/inference_wizardcoder.py unverified no licence file found · pointer only · e03723b85938f4f0 · report
get_model in 368 papers WizardCoder/src/humaneval_gen.py unverified no licence file found · pointer only · fcb999210417b348 · report
get_oai_completion Evol_Instruct/openai_access.py unverified no licence file found · pointer only · 9aa01a80f5634d81 · report
main in 235 papers WizardLM/src/infer_wizardlm13b.py unverified no licence file found · pointer only · e7c8e0d548af8b2f · report

Tasks

Arithmetic ReasoningGSM8KMathMath Word Problem SolvingMathematical Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Arithmetic Reasoning GSM8K WizardMath-7B-V1.1 Accuracy 83.2 #54 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K WizardMath-7B-V1.1 Parameters (Billion) 7 #54 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K WizardMath-70B-V1.0 Accuracy 81.6 #64 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K WizardMath-70B-V1.0 Parameters (Billion) 70 #64 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K WizardMath-13B-V1.0 Accuracy 63.9 #113 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K WizardMath-13B-V1.0 Parameters (Billion) 13 #113 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K WizardMath-7B-V1.0 Accuracy 54.9 #128 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K WizardMath-7B-V1.0 Parameters (Billion) 7 #128 of 164 Archive leaderboard report
Math Word Problem Solving MATH WizardMath-7B-V1.1 Accuracy 33.0 #85 of 135 Archive leaderboard report
Math Word Problem Solving MATH WizardMath-7B-V1.1 Parameters (Billions) 7 #85 of 135 Archive leaderboard report
Math Word Problem Solving MATH WizardMath-70B-V1.0 Accuracy 22.7 #99 of 135 Archive leaderboard report
Math Word Problem Solving MATH WizardMath-70B-V1.0 Parameters (Billions) 70 #99 of 135 Archive leaderboard report
Math Word Problem Solving MATH WizardMath-13B-V1.0 Accuracy 14.0 #110 of 135 Archive leaderboard report
Math Word Problem Solving MATH WizardMath-13B-V1.0 Parameters (Billions) 13 #110 of 135 Archive leaderboard report
Math Word Problem Solving MATH WizardMath-7B-V1.0 Accuracy 10.7 #115 of 135 Archive leaderboard report
Math Word Problem Solving MATH WizardMath-7B-V1.0 Parameters (Billions) 7 #115 of 135 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3GPT-4Label SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections