SWE-Marathon v1.1

Twenty multi-hour programming jobs — rebuilding a library, cloning a product, training a model, making something faster. A run counts only when every check passes, hidden tests and interface review included. Higher is better.

Grok 4.7 by SpaceXAI holds the best SWE-Marathon v1.1 result among tracked models, at 46% (released Sep 21 2026). Higher scores are better on this benchmark.

1. Grok 4.7 (SpaceXAI) — 46%; 2. Grok 4.6 (SpaceXAI) — 31.9%.

2 tracked models have a published SWE-Marathon v1.1 score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.