agents benchmark
SWE-fficiency
SWE-fficiency is an open-source benchmark and workflow that evaluates language models on optimizing the runtime efficiency of real-world software engineering tasks, measuring how well agents can improve code performance autonomously.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
SWE-fficiency Ranking
Higher score ranks better on this benchmark.
| 01 | MI | 34.8% | 100.0% | 1 | C |
SWE-fficiency Highlights
The leading models and scores on this benchmark.
What is SWE-fficiency?
What SWE-fficiency measures and how its scores work.
SWE-fficiency is an open-source benchmark and workflow that evaluates language models on optimizing the runtime efficiency of real-world software engineering tasks, measuring how well agents can improve code performance autonomously.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SWE-fficiency
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- swe-fficiency|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about SWE-fficiency.
Which model scores highest on SWE-fficiency?
MiniMax M3 is currently ranked first with 34.8%.
What does SWE-fficiency measure?
SWE-fficiency is an open-source benchmark and workflow that evaluates language models on optimizing the runtime efficiency of real-world software engineering tasks, measuring how well agents can improve code performance autonomously.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.