SWE-Marathon Benchmark
Explore score history ↗SWE-Marathon evaluates AI agents on 20 ultra-long-horizon software engineering tasks, each with a unique executable environment, a human-written reference solution, and a multi-layer verification suite. Tasks average 27.2M tokens per logged agent attempt, requiring sustained progress over hours and millions of tokens.
- Released
- 2026-06-05
- Institutions
- Gujarat Technological University · Harvard University · University of Waterloo
- Evaluates
- Code, Code & Software, Software & AI Compute
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SWE-Marathon paper
No reported scores are on record for this benchmark yet.