15:38
2026-06-26
cryptobriefing.com
artificial-intelligence
MirrorCode evaluates AI’s long-horizon coding capabilities with 22 open-source tasks
METR and Epoch AI released MirrorCode, a benchmark testing AI agents' ability to reimplement entire software programs from source code. Claude Opus 4.6 rebuilt a 16,000-line bioinformatics toolkit in …