AI's Progress in Circuit Board Design Demonstrated with EEBench Benchmarking

OpenAI demonstrated GPT-6 Astra working on circuit board design in KiCad, highlighting advancements in AI's ability to handle electronics tasks.

The EEBench tool measures the effectiveness of AI-generated circuits by simulating real-world conditions and checking performance against specifications. Current AI models, such as Claude Opus 5 and Grok 4.6, have shown promising results, scoring 61.6% and 57.1% respectively in EEBench V1.

EEBench focuses on analog and digital design verification, assessing factors like voltage behavior and component tolerances. It aims to provide a more objective grading of engineering work compared to traditional design tools.

Despite the progress, AI models like GPT-5.5 and GPT-5.6 scored lower, indicating that more development is needed. Future iterations, including Grok 4.7, are anticipated to enhance engineering capabilities further.

The ongoing development of EEBench and its integration into AI model evaluations suggests a growing interest in the intersection of AI and electronics engineering.