SWE Refactor Bench

SWE Refactor Bench is a benchmark for how well a model works as an autonomous coding agent. The official description says: "Agentic software refactoring benchmark; agent harness Claude Code 2.1.220 at 200K context". Below we describe in simple words what benchmarks of this type generally examine.

SWE Refactor Bench measures how well a model works as an autonomous coding agent. In detail, it checks:

• fixing real, open bugs from real software repositories
• planning multi-step changes, running commands and editing files by itself
• passing the project's test suite after its changes
• handling whole repositories, not just small isolated code snippets

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: Agentic software refactoring benchmark; agent harness Claude Code 2.1.220 at 200K context. Introduced on the MiniMax M3.1-Flash release card (M3.1-Flash + frontier competitor scores).

What is the SWE Refactor Bench benchmark?

SWE Refactor Bench is a benchmark for how well a model works as an autonomous coding agent. The official description says: 'Agentic software refactoring benchmark; agent harness Claude Code 2.1.220 at 200K context'. Below we describe in simple words what benchmarks of this type generally examine.

What does SWE Refactor Bench test?

SWE Refactor Bench mainly measures how well a model works as an autonomous coding agent. Concretely, it checks: fixing real, open bugs from real software repositories; planning multi-step changes, running commands and editing files by itself; passing the project's test suite after its changes.

How is the SWE Refactor Bench score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get SWE Refactor Bench data and scores?

The official source is https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/swe-refactor-bench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.