AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
SWE-Marathon
SWE-Marathon is an ultra-long-horizon software engineering benchmark covering tasks such as building compilers, optimizing kernels, and developing production-grade services. It measures whether agents can sustain quality across extremely long engineering trajectories.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 4
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| GLM-5.3 | 0.425 | Not recorded | Not recorded | 2026-08-14 · model_announcement | LLM Stats |
| Kimi K3 | 0.42 | Not recorded | Not recorded | 2026-07-16 · model_announcement | LLM Stats |
| Grok 4.5 | 0.29 | Not recorded | Not recorded | 2026-07-16 · model_announcement | LLM Stats |
| GLM-5.2 | 0.13 | Not recorded | Not recorded | 2026-06-16 · model_announcement | LLM Stats |