Papers › MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

5 Oct 2023arXiv:2310.03731archive 2025-07-28

Ke Wang, Houxing Ren, Aojun Zhou, Zimu Lu, Sichun Luo, Weikang Shi, Renrui Zhang, Linqi Song, Mingjie Zhan, Hongsheng Li

The recently released GPT-4 Code Interpreter has demonstrated remarkable proficiency in solving challenging math problems, primarily attributed to its ability to seamlessly reason with natural language, generate code, execute code, and continue reasoning based on the execution output. In this paper, we present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations and, consequently, enhancing their mathematical reasoning abilities. We propose a method of generating novel and high-quality datasets with math problems and their code-based solutions, referred to as MathCodeInstruct. Each solution interleaves natural language, code, and execution results. We also introduce a customized supervised fine-tuning and inference approach. This approach yields the MathCoder models, a family of models capable of generating code-based solutions for solving challenging math problems. Impressively, the MathCoder models achieve state-of-the-art scores among open-source LLMs on the MATH (45.2%) and GSM8K (83.9%) datasets, substantially outperforming other open-source alternatives. Notably, the MathCoder model not only surpasses ChatGPT-3.5 and PaLM-2 on GSM8K and MATH but also outperforms GPT-4 on the competition-level MATH dataset. The dataset and models will be released at https://github.com/mathllm/MathCoder.

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 2 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mathllm/mathcoder officialmentioned in papermentioned on GitHubSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 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

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong

Licence: 0 of the 2 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 mathllm/mathcoder. “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.

mathllm/mathcoder official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
load_jsonl in 179 papers src/inference.py ran · our draft was wrong Apache-2.0 (permissive) · 17081a7b73a41850 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-22
truncate_decimals src/inference.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 36efc3181b04788b · report fixture: signature s:str/0/str, decimal_places:int/0/int, role:str/0/str · returned str · level recorded 2026-09-22

Tasks

Arithmetic ReasoningGSM8KMathMath Word Problem SolvingMathematical Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Arithmetic Reasoning GSM8K MathCoder-L-70B Accuracy 83.9 #53 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-L-70B Parameters (Billion) 70 #53 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-CL-34B Accuracy 81.7 #63 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-CL-34B Parameters (Billion) 34 #63 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-CL-13B Accuracy 74.1 #90 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-CL-13B Parameters (Billion) 7 #90 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-L-13B Accuracy 72.6 #99 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-L-13B Parameters (Billion) 13 #99 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-CL-7B Accuracy 67.8 #107 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-CL-7B Parameters (Billion) 7 #107 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-L-7B Accuracy 64.2 #112 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K MathCoder-L-7B Parameters (Billion) 7 #112 of 164 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-CL-34B Accuracy 45.2 #64 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-CL-34B Parameters (Billions) 34 #64 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-L-34B Accuracy 45.1 #65 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-L-34B Parameters (Billions) 34 #65 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-CL-13B Accuracy 35.9 #79 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-CL-13B Parameters (Billions) 13 #79 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-CL-7B Accuracy 30.2 #88 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-CL-7B Parameters (Billions) 7 #88 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-L-13B Accuracy 29.9 #89 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-L-13B Parameters (Billions) 13 #89 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-L-7B Accuracy 23.3 #98 of 135 Archive leaderboard report
Math Word Problem Solving MATH MathCoder-L-7B Parameters (Billions) 7 #98 of 135 Archive leaderboard report
Math Word Problem Solving SVAMP MathCoder-L-70B Execution Accuracy 84.9 #6 of 26 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 EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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