reasoning benchmark
Multi-SWE-Bench Leaderboard
Multi-SWE-Bench is a multilingual benchmark for evaluating Large Language Models' ability to resolve software issues across Java, TypeScript, JavaScript, Go, Rust, C, and C++.
Updated Sep 5, 2026
Models6
Model coverage6
MetricScore
EvidenceB
Multi-SWE-Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score52.70% | Percentile100.00% | Participants6 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score51.30% | Percentile80.00% | Participants6 | EvidenceC | Evaluated |
| Rank03 | ModelMI | Score49.40% | Percentile60.00% | Participants6 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score41.90% | Percentile40.00% | Participants6 | EvidenceC | Evaluated |
| Rank05 | ModelMI | Score36.20% | Percentile20.00% | Participants6 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score25.80% | Percentile0.00% | Participants6 | EvidenceC | Evaluated |
Multi-SWE-Bench Highlights
The leading models and scores on this benchmark.
Multi-SWE-Bench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Multi-SWE-Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Multi-SWE-Bench?
What Multi-SWE-Bench measures and how its scores work.
Multi-SWE-Bench is a benchmark covering 1,632 software issue instances annotated by 68 expert annotators across seven programming languages.
It measures software issue resolution ability using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Multi-SWE-Bench
- Modality
- text
- Primary category
- reasoning
- 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 Multi-SWE-Bench.
Which model scores highest on Multi-SWE-Bench?
MiniMax M2.7 is currently ranked first with 52.70%.
What are the top three models on Multi-SWE-Bench?
The current leaders are MiniMax M2.7 (52.70%), MiniMax M2.5 (51.30%), and MiniMax M2.1 (49.40%).
Which Multi-SWE-Bench model has the lowest official input price?
MiniMax M2.7 has the lowest matched official input price at $0.30 input / $1.2 output per 1M tokens.
Which models are fastest among Multi-SWE-Bench results?
The fastest matched records are MiniMax M2.5 (100.00 tok/s via MiniMax), MiniMax M2.1 (100.00 tok/s via MiniMax), and MiniMax M2 (70.00 tok/s via MiniMax).
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.