StabilizerBench: A Benchmark for AI-Assisted Quantum Error Correction Circuit Synthesis

TL;DR

StabilizerBench is a comprehensive benchmark suite designed to evaluate AI agents on the synthesis, optimization, and fault-tolerant construction of quantum error correction circuits, facilitating progress measurement in quantum programming automation.

Contribution

It introduces a novel, scalable benchmark with scoring metrics for AI-generated stabilizer circuits across multiple tasks and code sizes, filling a gap in quantum error correction research.

Findings

Benchmark discriminates AI model performance effectively.

AI agents show significant room for improvement.

The suite enables scalable verification via Gottesman Knill theorem.

Abstract

As quantum hardware scales toward fault tolerant operation, the demand for correct quantum error correction (QEC) circuits far outpaces manual design capacity. AI agents offer a promising path to automating this synthesis, yet no benchmark exists to measure their progress on the specialized task of generating QEC circuits. We introduce StabilizerBench, a benchmark suite of 192 stabilizer codes spanning 12 families, 4-196 qubits, and distances 2-21, organized into three tasks of increasing difficulty: state preparation circuit generation, circuit optimization under semantic constraints, and fault tolerant circuit synthesis. Although motivated by QEC, stabilizer circuits exercise core competencies required for general quantum programming, including gate decomposition, qubit routing, and semantic preserving transformations, while admitting efficient verification via the Gottesman Knill theorem, enabling the benchmark to scale to large codes without the exponential cost of full unitary comparison. We define a unified generator weighted scoring system with two tiers: a capability score measuring breadth of success and a quality score capturing circuit merit. We also introduce continuous fault tolerance and optimization metrics that grade error resilience and circuit improvements beyond binary pass or fail. Following the design of classical benchmarks such as SWE-bench, StabilizerBench specifies inputs, verification oracles, and scoring but leaves prompts and agent strategies open. We evaluate three frontier AI agents and find the benchmark discriminates across models and tasks with substantial headroom for improvement.