SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code

June 03, 2026 ยท Grace Period ยท ๐Ÿ› NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Natalia Tarasova, Enrique Balp-Straffon, Aleksei Iancheruk, Yevhenii Sielskyi, Nikita Kozodoi, Liam H. Byrne, Jack Butler, Dayuan Jiang, Marcin Czelej, Andrew Ang, Yash Shah, Roi Blanco, Sergei Ivanov arXiv ID 2606.05249 Category cs.SE: Software Engineering Citations 0 Venue NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle
Abstract
Building infrastructure-as-code (IaC) in cloud computing is a critical task, underpinning the reliability, scalability, and security of modern software systems. Despite the remarkable progress of large language models (LLMs) in software engineering -- demonstrated across many dedicated benchmarks -- their capabilities in developing IaC remain underexplored. Unlike existing IaC benchmarks that predominantly center on declarative paradigms such as Terraform and involve generating entire codebases from scratch, our benchmark reflects the incremental code edits common in enterprise development with imperative tools like the AWS CDK. We present SWE-InfraBench, a diverse evaluation dataset sourced from dozens of real-world IaC codebases that challenge LLMs to perform realistic code modifications in AWS CDK repositories. Each example requires models to implement changes to existing codebases based on natural language instructions, with success determined by passing provided test cases. These tasks demand sophisticated reasoning about cloud resource dependencies and implementation patterns beyond conventional code generation challenges. Our evaluation results reveal significant limitations in current LLMs showing that even state-of-the-art systems struggle with many tasks -- the best model, Sonnet 3.7, succeeds in only 34\% of cases, while specialized reasoning models like DeepSeek R1 achieve just 24% success. The SWE-InfraBench dataset is available at: https://www.kaggle.com/datasets/64e59070fd51c0278560b01eb5dc4f3c447d5268cdabe5a350d2969e4413fea5
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Software Engineering