MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation

By Federico Cassano, John Gouwar, Daniel Nguyen, S. Nguyen, Luna Phipps-Costin, Donald Pinckney, Ming-Ho Yee, Yangtian Zi, Carolyn Jane Anderson, Molly Q. Feldman and 3 more. 2022

167 citations recorded by the source corpus.

Large language models have demonstrated the ability to generate both natural language and programming language text. Such models open up the possibility of multi-language code generation: could code generation models generalize knowledge from one language to another? Although contemporary code generation models can generate semantically correct Python code, little is known about their abilities with other languages. We propose MultiPL-E, a system for translating unit test-driven code generation benchmarks to new languages. We create the first massively multilingual code generation benchmark by using MultiPL-E to translate two popular Python code generation benchmarks to 18 additional programming languages. We use MultiPL-E to extend the HumanEval benchmark and MBPP benchmark to 18 languages that encompass a range of programming paradigms and popularity. Using these new parallel benchmarks, we evaluate the multi-language performance of three state-of-the-art code generation models: Codex, CodeGen, and InCoder. We find that Codex matches or even exceeds its performance on Python for several other languages. The range of programming languages represented in MultiPL-E allow us to explore the impact of language frequency and language features on model performance. Finally, the MultiPL-E approach of compiling code generation benchmarks to new programming languages is both scalable and extensible, making it straightforward to evaluate new models, benchmarks, and languages.

Subfields: Artificial Intelligence, Information Systems, Materials Chemistry, Evaluation & Benchmarks, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Materials Chemistry

Fei Huang

In Evaluation & Benchmarks

In Code Generation & Program Synthesis

Citations in the corpus

LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code (2024, background): “Their variants have been proposed to cover more languages, (Wang et al., 2022a; Zheng et al., 2023; Cassano et al., 2022; Athiwaratkun et al., 2022).”
Reflexion: language agents with verbal reinforcement learning (2023, unknown): “For Rust, HumanEval is the hardest 50 problems from HumanEval Python translated to Rust with MultiPL-E [3].”
Qwen2.5-Coder Technical Report (2024, methodology): “5-Coder’s proficiency in handling multiple programming languages, we selected the MultiPL-E (Cas-sano et al., 2022) and choose to evaluate eight mainstream languages from these benchmark, including Python, C++, Java, PHP, TypeScript, C#, Bash and JavaScript.”
CodeMind: A Framework to Challenge Large Language Models for Code Reasoning (2024, unknown): “…several existing benchmarks (Wang et al., 2022; Athiwaratkun et al., 2022; Chen et al., 2021; Liu et al., 2023; Gu et al., 2024; Zheng et al., 2023; Cassano et al., 2022; Jimenez et al., 2023; Du et al., 2023; Odena et al., 2021; Puri et al., 2021; Ahmad et al., 2021), we chose the programs in…”
Recall Before Rerank: Benchmarking Deep Learning Models for Large-Scale Code-to-Code Retrieval (2026, unknown): “MultiPL-E [4], e.g., notes that models are sensitive to prompt design and comment style, though type annotations do not affect Python performance.”