# CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

arXiv: https://arxiv.org/abs/2603.14501 · HTML: https://mlsanity.com/paper/2603.14501/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [VerilogEval: Evaluating Large Language Models for Verilog Code Generation](https://mlsanity.com/paper/2309.07544/) (2023)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization](https://mlsanity.com/paper/2402.16694/) (2024)
- [A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages](https://mlsanity.com/paper/2410.03981/) (2024)
- [AVATAR: A Parallel Corpus for Java-Python Program Translation](https://mlsanity.com/paper/2108.11590/) (2021)
- [Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation](https://mlsanity.com/paper/2408.11053/) (2024)
- [CLEVER: A Curated Benchmark for Formally Verified Code Generation](https://mlsanity.com/paper/2505.13938/) (2025)
- [Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs](https://mlsanity.com/paper/2401.10065/) (2024)
- [CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation](https://mlsanity.com/paper/2504.15254/) (2025)
- [An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities](https://mlsanity.com/paper/2501.13742/) (2025)
- [VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation](https://mlsanity.com/paper/2406.04379/) (2024)
- [DocCGen: Document-based Controlled Code Generation](https://mlsanity.com/paper/2406.11925/) (2024)
- [ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation](https://mlsanity.com/paper/2501.18460/) (2025)
- [ClassEval-T: Evaluating Large Language Models in Class-Level Code Translation](https://mlsanity.com/paper/2411.06145/) (2024)
- [TeXpert: A Multi-Level Benchmark for Evaluating LaTeX Code Generation by LLMs](https://mlsanity.com/paper/2506.16990/) (2025)
- [Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling](https://mlsanity.com/paper/2511.03404/) (2025)
- [SolEval: Benchmarking Large Language Models for Repository-level Solidity Code Generation](https://mlsanity.com/paper/2502.18793/) (2025)
- [Do Current Language Models Support Code Intelligence for R Programming Language?](https://mlsanity.com/paper/2410.07793/) (2024)
- [Function-to-Style Guidance of LLMs for Code Translation](https://mlsanity.com/paper/2507.11083/) (2025)
- [MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks](https://mlsanity.com/paper/2507.12284/) (2025)
- [RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation](https://mlsanity.com/paper/2507.14791/) (2025)
- [Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks](https://mlsanity.com/paper/2410.14766/) (2024)

## Abstract (arXiv)

Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming languages primarily focuses on Domain-Specific Languages (DSLs), leaving general-purpose languages that suffer from data scarcity underexplored. To address this gap, we introduce CangjieBench, a contamination-free benchmark for Cangjie, a representative low-resource general-purpose language. The benchmark comprises 248 high-quality samples manually translated from HumanEval and ClassEval, covering both Text-to-Code and Code-to-Code tasks. We conduct a systematic evaluation of diverse LLMs under four settings: Direct Generation, Syntax-Constrained Generation, Retrieval-Augmented Generation (RAG), and Agent. Experiments reveal that Direct Generation performs poorly, whereas Syntax-Constrained Generation offers the best trade-off between accuracy and computational cost. Agent achieve state-of-the-art accuracy but incur high token consumption. Furthermore, we observe that Code-to-Code translation often underperforms Text-to-Code generation, suggesting a negative transfer phenomenon where models overfit to the source language patterns. We hope that our work will offer valuable insights into LLM generalization to unseen and low-resource programming languages. Our code and data are available at https://github.com/cjhCoder7/CangjieBench.