# An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run

> Epoch AI's new MirrorCode benchmark tests whether AI models can recreate entire programs on their own. Claude Opus 4. 7 leads with 56 percent, but every model still fails on the most complex tasks.

- **Source:** [The-decoder](https://the-decoder.com/an-ai-model-programmed-nonstop-for-19-days-on-a-single-mirrorcode-task-that-cost-2600-to-run/?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=6a4021fdd2e4a413fa9a3301)
- **Published:** 2026-06-27
- **Category:** AI & Bots
- **Tags:** #gemini #claude #ai
- **Canonical:** http://localhost:4321/a/6a4021fdd2e4a413fa9a3301

---

_GearOpen's distilled summary. The full original article is published at The-decoder (source link above); GearOpen does not republish the source's full text._