SemiAnalysis benchmark: no AI agent tops 12%

SemiAnalysis launched the GDPx benchmark testing AI agents on simulated knowledge work from chip design to quant trading. No model exceeded 12%, with Claude Opus 5.5 narrowly ahead of Gemini 4 Carbon; critics cite few tasks per domain and uneven conditions.

• NVIDIA: full-stack codesign tackles AI memory challenge2026-11-05
• Preprint probes how source attribution shifts LLM argument ratings2026-11-04
• User has Claude hand-edit Gemma neurons to tune Italian translation2026-11-03
• StateBench tests long-context state tracking in LLMs2026-11-03
• Claude Opus 5.5 Can Draw Permit-Level Architectural Drawings2026-11-02