AI Reimplements 16,000-Line Bioinformatics Toolkit in 14 Hours for $251

What's the largest software project AI can complete on its own?

Epoch AI and METR introduce MirrorCode, a benchmark testing AI on long-horizon coding tasks by reimplementing entire programs from scratch. With a generous inference budget, AI models work for days, and one model, Claude Opus 4.7, recreated gotree, a 16,000-line Go toolkit, in 14 hours at a cost of $251—a task estimated to take humans 2–17 weeks. The benchmark is cheat-resistant and includes held-out tests, though data contamination remains a concern.