# The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages

arXiv: https://arxiv.org/abs/2607.22807 · HTML: https://mlsanity.com/paper/2607.22807/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 23 of 23)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [Multi-lingual Evaluation of Code Generation Models](https://mlsanity.com/paper/2210.14868/) (2022)
- [Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories](https://mlsanity.com/paper/2506.18824/) (2025)
- [Reducing Cost of LLM Agents with Trajectory Reduction](https://mlsanity.com/paper/2509.23586/) (2025)
- [How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks](https://mlsanity.com/paper/2604.22750/) (2026)
- [EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code](https://mlsanity.com/paper/2505.13004/) (2025)
- [ContextBench: A Benchmark for Context Retrieval in Coding Agents](https://mlsanity.com/paper/2602.05892/) (2026)
- [Process-Centric Analysis of Agentic Software Systems](https://mlsanity.com/paper/2512.02393/) (2025)
- [SWE-Explore: Benchmarking How Coding Agents Explore Repositories](https://mlsanity.com/paper/2606.07297/) (2026)
- [The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget](https://mlsanity.com/paper/2508.13666/) (2025)
- [Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering](https://mlsanity.com/paper/2601.14470/) (2026)
- [CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs](https://mlsanity.com/paper/2507.03254/) (2025)
- [More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents](https://mlsanity.com/paper/2510.16786/) (2025)
- [EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents](https://mlsanity.com/paper/2601.05777/) (2026)
- [Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment](https://mlsanity.com/paper/2508.04865/) (2025)
- [Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand](https://mlsanity.com/paper/2512.08266/) (2025)
- [Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages](https://mlsanity.com/paper/2606.20517/) (2026)
- [Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages](https://mlsanity.com/paper/2606.10933/) (2026)

## Built on by (most cited first, 1 of 1)

- [Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle](https://mlsanity.com/paper/2609.04681/) (2026)

## Abstract (arXiv)

Although coding agents are now very effective in a variety of programming languages, this paper first shows that the cost (in tokens) can very significantly by programming language. We evaluate five recent models on programming problems in Python, Java, Rust, and OCaml. We carefully control for problem difficulty, and show that there can be stark variation in token consumption that is consistent across models. To understand why, we analyze both the structure and content of agent trajectories. First, we re-execute every intermediate solution and abstract each trajectory as a sequence of test-outcome vectors, then label the work between successive solutions. This reveals agents repeatedly producing noncompiling solutions in unfamiliar languages and revising solutions that already pass. Second, we analyze trajectory text, finding that agents plan solutions in code comments, distrust the provided tests in favor of inputs they invent, and sidestep unfamiliar target languages by prototyping in Python. Our results show that by-language token efficiency is a metric that should be considered when benchmarking and developing multilingual agents, and, for the tokenmaxxer, a guide to the most expensive language to work in.