E2E-SWE Benchmark

What is E2E-SWE?

Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories.

Released

2026-09-29

Evaluates

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

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.38335

E2E-SWE paper

• Paper https://arxiv.org/abs/2609.38335

Which sources cite E2E-SWE?

• E2E-SWE

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

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