Benchmark
SWE-Marathon Benchmark
What is SWE-Marathon?
Ultra long-horizon software engineering tasks; the score depends on the agent's loop budget as much as on coding skill.
- Evaluates
- coding agent
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://github.com/abundant-ai/swe-marathon
SWE-Marathon code
SWE-Marathon results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Hy4 preview | Tencent | 31.9 | 2026-08-28 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite SWE-Marathon?
- Hy4 preview Tencent, 2026-08-28