MirrorCode

A long-horizon SWE benchmark for autonomous coding runs.

A long-horizon software-engineering benchmark in which models reimplement real programs from specifications without internet access and are evaluated on hidden held-out tests.

Recent stories

1 linked story

releasePRIMARY2026-06-26

Epoch releases MirrorCode with 25 long-horizon SWE tasks and a 56% score

Epoch introduced MirrorCode, a benchmark where models reimplement real programs from specs with no internet and hidden held-out tests; the best current score is 56%. The setup matters because it scales inference into multi-day runs and targets software jobs estimated to take humans weeks.