VerilogEval-Human

The 'VerilogEval Human' dataset/benchmark contains human-annotated examples used to evaluate the accuracy and performance of automated Verilog code generation systems.

Papers using VerilogEval-Human (2)

HDLFORGE: A Two-Stage Multi-Agent Framework for Efficient Verilog Code Generation with Adaptive Model Escalation2026Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation2025