SWE-Gate Benchmark

What is SWE-Gate?

Evaluates repository-level repair agents on both functional correctness and adherence to review-derived constraints, using 303 instances with separate…

Released

2026-09-03

Evaluates

Code, Code & Software, General AI, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.04167

SWE-Gate paper and code

• Paper https://arxiv.org/abs/2609.04167
• Code https://github.com/DeepSoftwareAnalytics/SWE-Gate

Which sources cite SWE-Gate?

• SWE-Gate

Related Code, Code & Software, General AI, Software & AI Compute benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• Active-SWE
• ActiveSciBench