Multi-SWE Bench
A multi-language software-engineering benchmark that measures repository-level bug fixing and implementation across more than one programming ecosystem.
Data verified 33 confirmed releases in the last 30 daysSee provider release alertsBenchmark score on Multi-SWE Bench — September 15, 2026
We mirror the published score view for Multi-SWE Bench. MiniMax M2.7 leads the public snapshot at 52.7%. We do not use these results to rank models overall.
1 modelCodingCurrentDisplay onlyUpdated September 15, 2026
Benchmark score table (1 model)
ScoreAbout Multi-SWE Bench
Year
2026
Tasks
Multi-language repo tasks
Format
Repository task completion
Difficulty
Professional software engineering
MiniMax positions Multi-SWE Bench as a benchmark closer to real engineering work than isolated code generation, emphasizing multi-language repository workflows.
BenchLM freshness & provenance
Version
Multi-SWE Bench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does Multi-SWE Bench measure?
A multi-language software-engineering benchmark that measures repository-level bug fixing and implementation across more than one programming ecosystem.
Which model scores highest on Multi-SWE Bench?
MiniMax M2.7 by MiniMax currently leads with a score of 52.7% on Multi-SWE Bench.
How many models are evaluated on Multi-SWE Bench?
1 AI models have been evaluated on Multi-SWE Bench on BenchLM.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.