Benchmark RadarNetlistBench
NetlistBench evaluates LLM reliability in recognizing and manipulating SPICE netlists, covering parameter and connectivity recognition, edits, hierarchical operations, equivalence judgment, and compound editing, with deterministic structure-aware scoring.
- Released
- 2026-08-12
- Readiness
- Paper only
- Primary field
- Robotics & Autonomous Systems
Why it matters
It addresses the gap in assessing LLM reliability for simulator-facing netlist tasks, distinct from high-level design reasoning, and provides a structured evaluation to guide trustworthy circuit design automation.
Motivation
Large Language Models (LLMs) are increasingly used in circuit design workflows, yet their reliability on simulator-facing SPICE netlist recognition and manipulation remains poorly understood and is rarely separated from high-level design reasoning.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.