CUA-SWE Benchmark

What is CUA-SWE?

Software development requires more than editing code: developers repeatedly run software, interact with its interfaces, visually inspect its behavior, and use…

Released

2026-09-26

Evaluates

Agents & Tool Use, Code, General AI, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.32600

CUA-SWE paper and code

• Paper https://arxiv.org/abs/2609.32600
• Code https://github.com/kingofspace0wzz/cua-swe

Which sources cite CUA-SWE?

• CUA-SWE

Related Agents & Tool Use, Code, General AI, Software & AI Compute benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Real-World CAD Segmentation Benchmark
• A3S-Bench
• AARRI-Bench
• ABACUS