VerilogEval v-2

'VerilogEval v-2' is a benchmark dataset that contains a set of problems used to evaluate the performance of LLM-based electronic design automation (EDA) agents in generating and debugging digital front-end designs.

Papers using VerilogEval v-2 (3)

LEGO: An LLM Skill-Based Front-End Design Generation Platform2026HDLFORGE: A Two-Stage Multi-Agent Framework for Efficient Verilog Code Generation with Adaptive Model Escalation2026SiliconMind-V1: Multi-Agent Distillation and Debug-Reasoning Workflows for Verilog Code Generation2026