// AI vs Humans
No AI agent scores above 12% on SemiAnalysis' eight-hour real-work benchmark
GDPx puts agents inside chip design tools, data rooms and live systems for up to eight hours. Opus 5.5 leads at 12%, and critics say the numbers are noisy.
// TAG
GDPx puts agents inside chip design tools, data rooms and live systems for up to eight hours. Opus 5.5 leads at 12%, and critics say the numbers are noisy.