CapBench: A Multi-PDK Dataset for Machine-Learning-Based Post-Layout Capacitance Extraction

CapBench is a fully reproducible, multi-PDK dataset for capacitance extraction. The dataset is derived from open-source designs, including single-core, SoCs and discrete accelerators. All designs are fully placed and routed using the open-source OpenROAD flow across three technology nodes: ASAP7, NanGate45, and SkyWater130HD. From these layouts, we extract 75,000 windows across three size tiers to enable transfer learning and scalability studies. High-fidelity capacitance labels are generated using RWCap, a state-of-the-art random-walk solver, and subsequently validated against the industry-standard Raphael.