SWE-InfraBench

What is SWE-InfraBench?

A benchmark of incremental infrastructure-as-code modifications in real-world AWS CDK repositories, evaluated through provided test cases.

Released

2026-06-03

Evaluates

Code & Software, Software & AI Compute, cs.SE

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.05249

SWE-InfraBench paper

• Paper https://arxiv.org/abs/2606.05249

Which sources cite SWE-InfraBench?

• SWE-InfraBench

Related Code & Software, Software & AI Compute, cs.SE benchmarks

• Active-SWE
• AFT-Bench
• Agent App Benchmark
• Agent Retrieval Bench
• Agent Systems Benchmark (ASB)
• Agentic Evaluation in 2D Mazes
• Agentic Security Benchmark
• AgentInfraBench