Journal article · 2026 · Open access
PROBE: Benchmarking code generation in large language models
Empirical Software Engineering, 32(1) · Published 15 August 2026 · DOI 10.1007/s10664-026-10904-5
In brief
“PROBE: Benchmarking code generation in large language models” is a 2026 journal article by Rodrigo Pato Nogueira and 2 co-authors, published in Empirical Software Engineering. OpenAlex counts 2 citations as of 19 November 2026, which puts it in the top 6% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Empirical Software Engineering.
- Citations
- 2
- Most cited in
- 2026 (2)
- Field-weighted impact
- 5.26
- References
- 23
- Authors
- 3
Abstract
Large Language Models (LLMs) are increasingly being used in everyday software engineering tasks, particularly in automated code generation. Despite their widespread adoption, these models remain far from perfect, making systematic and fair evaluation essential to understand their strengths and limitations. In the context of code generation, existing benchmarks are limited: they often target a single programming language and rely primarily on unit test outcomes, while overlooking other critical dimensions such as the overall quality of the generated code and its closeness to a valid solution. To address these gaps, we introduce , an extensible benchmark framework that, unlike prior work, establishes a systematic structure built on diverse and well-defined metrics, representative workloads, varied prompt templates, and a robust experimental procedure. In practice, the code generated by the LLMs is evaluated along three complementary dimensions: functional correctness, proximity to valid solutions, and code quality, enabling a comprehensive assessment of performance. We use to evaluate four open-source and two proprietary models under three prompting strategies across five programming languages. We further complement this analysis with a study of common errors in the code and provide concrete examples, offering clearer insight into where LLMs tend to struggle. Our findings show that, while LLMs achieve promising results, they struggle with harder problems and, in the case of smaller models, with programming languages that have fewer available resources for training, and they often fail due to fundamental and easily avoidable errors that underscore the unreliability of automatically generated code.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Nogueira, R. P., Vieira, M., & Campos, J. R. (2026). PROBE: Benchmarking code generation in large language models. Empirical Software Engineering, 32(1). https://doi.org/10.1007/s10664-026-10904-5
MLA 9
Nogueira, Rodrigo Pato, et al. “PROBE: Benchmarking code generation in large language models.” Empirical Software Engineering, vol. 32, no. 1, 2026. https://doi.org/10.1007/s10664-026-10904-5.
Chicago
Nogueira, Rodrigo Pato, Marco Vieira, and João R. Campos. 2026. “PROBE: Benchmarking code generation in large language models.” Empirical Software Engineering 32 (1). https://doi.org/10.1007/s10664-026-10904-5.
Harvard
Nogueira, R. P., Vieira, M. and Campos, J. R. (2026) ‘PROBE: Benchmarking code generation in large language models’, Empirical Software Engineering, 32(1). doi:10.1007/s10664-026-10904-5.
IEEE
R. P. Nogueira, M. Vieira, and J. R. Campos, “PROBE: Benchmarking code generation in large language models,” Empirical Software Engineering, vol. 32, no. 1, 2026, doi: 10.1007/s10664-026-10904-5.
BibTeX
@article{nogueira2026probe,
title = {{PROBE: Benchmarking code generation in large language models}},
author = {Nogueira, Rodrigo Pato and Vieira, Marco and Campos, João R.},
journal = {Empirical Software Engineering},
year = {2026},
volume = {32},
number = {1},
doi = {10.1007/s10664-026-10904-5},
url = {https://doi.org/10.1007/s10664-026-10904-5}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- large language models
- automatic code generation
- benchmarking framework
- functional correctness
- code quality
- prompt strategies
- programming languages
- model comparison
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Nogueira, R. P., Vieira, M., & Campos, J. R. (2026). PROBE: Benchmarking code generation in large language models. Empirical Software Engineering, 32(1). https://doi.org/10.1007/s10664-026-10904-5
How many times has this paper been cited?
2 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Empirical Software Engineering: sign in and open the PDF from this page.
Who wrote this paper?
Rodrigo Pato Nogueira, Marco Vieira, João R. Campos.
What is the DOI of this paper?
10.1007/s10664-026-10904-5, permanently at https://doi.org/10.1007/s10664-026-10904-5. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.