New benchmark for LLM performance on incremental AWS CDK infrastructure code edits shows top models succeed in 34% of cases.
arXiv preprint arXiv:2411.06145 (2024) Cited on p
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code
New benchmark for LLM performance on incremental AWS CDK infrastructure code edits shows top models succeed in 34% of cases.