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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.03731")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mathllm/mathcoder officialmentioned in papermentioned on GitHub 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; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, 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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

load_jsonl mathllm/mathcoder/src/inference.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 17081a7b73a41850 · report
truncate_decimals mathllm/mathcoder/src/inference.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 36efc3181b04788b · report

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