SWE-RPG Benchmark

What is SWE-RPG?

A repository-level dataset and protocol evaluating issue resolution through requirement clarification, implementation planning, code generation, and artifact…

Released

2026-08-10

Evaluates

Code, Code & Software, Code generation, Planning, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.09072

SWE-RPG paper and code

• Paper https://arxiv.org/abs/2608.09072
• Code https://github.com/Xin-Zhou-smu/SWE-RPG-Bench

Which sources cite SWE-RPG?

• SWE-RPG

Related Code, Code & Software, Code generation, Planning, Software & AI Compute benchmarks

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