SWE Bench Multilingual
A benchmark of 300 software engineering tasks across 42 repositories and 9 programming languages: C, C++, Go, Java, JavaScript, TypeScript, PHP, Ruby, and Rust. Each instance is derived from a real GitHub pull request, following the same format and evaluation protocol as SWE-b…
- Domain
- rl-env
- License
- unknown
- Published
- Jan 2026
Cite
Notes
Only stored in your browser.
Top score 74.1 by MiniMax M2.5 - 8 models reporting (2 frontier)
Score history
3Top models
8
FAQ
- What is SWE Bench Multilingual?
- A benchmark of 300 software engineering tasks across 42 repositories and 9 programming languages: C, C++, Go, Java, JavaScript, TypeScript, PHP, Ruby, and Rust. Each instance is derived from a real GitHub pull request, following the same format and evaluation protocol as SWE-b…
- What is the current top score on SWE Bench Multilingual?
- The top reported score is 74.1 by MiniMax M2.5, across 8 models reporting (2 from frontier labs).
- What license is SWE Bench Multilingual under?
- SWE Bench Multilingual is available under unknown.