Technical Report: Full-Stack Fine-Tuning for the Q Programming Language

TL;DR

This paper presents a comprehensive approach to adapt large language models for the Q programming language, including dataset creation, benchmarking, and training, achieving state-of-the-art accuracy in a specialized domain.

Contribution

It introduces a new dataset, benchmarks models, and develops a full training pipeline for fine-tuning LLMs on the niche Q language, outperforming existing models.

Findings

Best model achieves 59% pass@1 accuracy on Q benchmark.

All models outperform GPT-4.1 on the task.

Models surpass Claude Opus-4 by 29.5% in accuracy.

Abstract

Even though large language models are becoming increasingly capable, it is still unreasonable to expect them to excel at tasks that are under-represented on the Internet. Leveraging LLMs for specialized applications, particularly in niche programming languages and private domains, remains challenging and largely unsolved. In this work, we address this gap by presenting a comprehensive, open-source approach for adapting LLMs to the Q programming language, a popular tool in quantitative finance that is much less present on the Internet compared to Python, C, Java, and other ``mainstream" languages and is therefore not a strong suit of general-purpose AI models. We introduce a new Leetcode style evaluation dataset for Q, benchmark major frontier models on the dataset, then do pretraining, supervised fine tuning, and reinforcement learning to train a suite of reasoning and non-reasoning models based on the Qwen-2.5 series, spanning five parameter sizes (1.5B, 3B, 7B, 14B, 32B). Our best model achieves a pass@1 accuracy of 59 percent on our Q benchmark, surpassing the best-performing frontier model, Claude Opus-4 by 29.5 percent. Additionally, all models, even our 1.5B model, outperform GPT-4.1 on this task. In addition to releasing models, code, and data, we provide a detailed blueprint for dataset construction, model pretraining, supervised fine-tuning, and reinforcement learning. Our methodology is broadly applicable, and we discuss how these techniques can be extended to other tasks, including those where evaluation may rely on soft or subjective signals.