agents benchmark
SWE Refactor Bench Leaderboard
SWE Refactor Bench is a repository-level software refactoring benchmark.
Updated Oct 23, 2026
Models1
Model coverage1
MetricScore
EvidenceB
SWE Refactor Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score23.00% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
SWE Refactor Bench Highlights
The leading models and scores on this benchmark.
The Top AI Models for SWE Refactor Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis swe refactor bench AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MIMiniMax
- Score
- 23.00%
- Price
- $0.15 input / $0.60 output per 1M tokens
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures SWE Refactor Bench, not total model capability
Selection summary
Best AI Models for SWE Refactor Bench
MiniMax M3.1 Flash currently leads SWE Refactor Bench with 23.00%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is SWE Refactor Bench?
What SWE Refactor Bench measures and how its scores work.
SWE Refactor Bench is a benchmark for repository-level software refactoring, with evaluations reported by MiniMax using the official setup with the Claude Code harness.
It measures Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SWE Refactor Bench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about SWE Refactor Bench.
Which model scores highest on SWE Refactor Bench?
MiniMax M3.1 Flash is currently ranked first with 23.00%.
What are the top three models on SWE Refactor Bench?
The current leaders are MiniMax M3.1 Flash (23.00%).
Which SWE Refactor Bench model has the lowest official input price?
MiniMax M3.1 Flash has the lowest matched official input price at $0.15 input / $0.60 output per 1M tokens.
Which models are fastest among SWE Refactor Bench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.