Code Generation 벤치마크
Code Generation on VerilogEval
Pass Rate
- 2025-02-26 — Nexus (Claude 3.5 Sonnet): Pass Rate 85.9
- 2025-09-10 — LLM-VeriPPA: Pass Rate 99.56
| Rank | Model | Pass Rate | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | LLM-VeriPPA 자동 추출 | 99.56 | LLM-VeriPPA: Power, Performance, and Area Optimization aware Verilog Code Generation with Large Language Models | 2025 | |
| 2 | COEVO 자동 추출 | 97.5 | COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation | 2026 | |
| 3 | REvolution 자동 추출 | 95.5 | REvolution: An Evolutionary Framework for RTL Generation driven by Large Language Models | 2025 | |
| 4 | Nexus (Claude 3.5 Sonnet) | 85.9 | Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation | PrimisAI/nexus | 2025 |
| 5 | ChipMATE 자동 추출 | 80.1 | ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation | 2026 |