SWE-Explore Benchmark

What is SWE-Explore?

SWE-Explore evaluates repository exploration by coding agents: given a repository and an issue, an explorer returns a ranked list of relevant code regions…

Released

2026-06-05

Evaluates

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

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.07297

SWE-Explore paper and code

• Paper https://arxiv.org/abs/2606.07297
• Code https://github.com/Qiushao-E/SWE-Explore-Bench

Which sources cite SWE-Explore?

• SWE-Explore

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