# To Code, or Not To Code? Exploring Impact of Code in Pre-training

arXiv: https://arxiv.org/abs/2408.10914 · HTML: https://mlsanity.com/paper/2408.10914/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 67 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 30 of 45)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [The Stack: 3 TB of permissively licensed source code](https://mlsanity.com/paper/2211.15533/) (2022)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)

## Built on by (most cited first, 30 of 47)

- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [Organize the Web: Constructing Domains Enhances Pre-Training Data Curation](https://mlsanity.com/paper/2502.10341/) (2025)
- [MegaMath: Pushing the Limits of Open Math Corpora](https://mlsanity.com/paper/2504.02807/) (2025)
- [Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective](https://mlsanity.com/paper/2412.14135/) (2024)
- [Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models](https://mlsanity.com/paper/2411.12580/) (2024)
- [Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset](https://mlsanity.com/paper/2508.15096/) (2025)
- [Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases](https://mlsanity.com/paper/2502.19249/) (2025)
- [EuroBERT: Scaling Multilingual Encoders for European Languages](https://mlsanity.com/paper/2503.05500/) (2025)
- [On Linear Representations and Pretraining Data Frequency in Language Models](https://mlsanity.com/paper/2504.12459/) (2025)
- [Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training](https://mlsanity.com/paper/2509.26625/) (2025)
- [Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training](https://mlsanity.com/paper/2506.01732/) (2025)
- [IPO: Your Language Model is Secretly a Preference Classifier](https://mlsanity.com/paper/2502.16182/) (2025)
- [Could Thinking Multilingually Empower LLM Reasoning?](https://mlsanity.com/paper/2504.11833/) (2025)
- [Tiny Aya: Bridging Scale and Multilingual Depth](https://mlsanity.com/paper/2603.11510/) (2026)
- [General Intelligence Requires Reward-based Pretraining](https://mlsanity.com/paper/2502.19402/) (2025)
- [Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions](https://mlsanity.com/paper/2503.03862/) (2025)
- [One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers](https://mlsanity.com/paper/2506.10766/) (2025)
- [AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages](https://mlsanity.com/paper/2601.06395/) (2026)
- [CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning](https://mlsanity.com/paper/2410.02229/) (2024)
- [Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources](https://mlsanity.com/paper/2504.04152/) (2025)
- [Procedural Pretraining: Warming Up Language Models with Abstract Data](https://mlsanity.com/paper/2601.21725/) (2026)
- [ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models](https://mlsanity.com/paper/2505.12534/) (2025)
- [Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning](https://mlsanity.com/paper/2505.22308/) (2025)
- [FLARE: Faithful Logic-Aided Reasoning and Exploration](https://mlsanity.com/paper/2410.11900/) (2024)
- [FastDraft: How to Train Your Draft](https://mlsanity.com/paper/2411.11055/) (2024)
- [Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data](https://mlsanity.com/paper/2412.10654/) (2024)
- [Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepali](https://mlsanity.com/paper/2412.13860/) (2024)
- [How Programming Concepts and Neurons Are Shared in Code Language Models](https://mlsanity.com/paper/2506.01074/) (2025)
- [Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research](https://mlsanity.com/paper/2509.22831/) (2025)
- [Will it Merge? On The Causes of Model Mergeability](https://mlsanity.com/paper/2601.06672/) (2026)

## Abstract (arXiv)

Including code in the pre-training data mixture, even for models not specifically designed for code, has become a common practice in LLMs pre-training. While there has been anecdotal consensus among practitioners that code data plays a vital role in general LLMs' performance, there is only limited work analyzing the precise impact of code on non-code tasks. In this work, we systematically investigate the impact of code data on general performance. We ask "what is the impact of code data used in pre-training on a large variety of downstream tasks beyond code generation". We conduct extensive ablations and evaluate across a broad range of natural language reasoning tasks, world knowledge tasks, code benchmarks, and LLM-as-a-judge win-rates for models with sizes ranging from 470M to 2.8B parameters. Across settings, we find a consistent results that code is a critical building block for generalization far beyond coding tasks and improvements to code quality have an outsized impact across all tasks. In particular, compared to text-only pre-training, the addition of code results in up to relative increase of 8.2% in natural language (NL) reasoning, 4.2% in world knowledge, 6.6% improvement in generative win-rates, and a 12x boost in code performance respectively. Our work suggests investments in code quality and preserving code during pre-training have positive impacts.