Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Models
This work addresses the need for evaluation tools in quantum software development, specifically for generative AI applications, though it is incremental as it adapts an existing benchmark to a new domain.
The authors tackled the problem of benchmarking large language models (LLMs) for generating quantum code by introducing the Qiskit HumanEval dataset, a hand-curated collection of over 100 quantum computing tasks, and found that LLMs can feasibly produce executable quantum code, establishing a new benchmark for the field.
Quantum programs are typically developed using quantum Software Development Kits (SDKs). The rapid advancement of quantum computing necessitates new tools to streamline this development process, and one such tool could be Generative Artificial intelligence (GenAI). In this study, we introduce and use the Qiskit HumanEval dataset, a hand-curated collection of tasks designed to benchmark the ability of Large Language Models (LLMs) to produce quantum code using Qiskit - a quantum SDK. This dataset consists of more than 100 quantum computing tasks, each accompanied by a prompt, a canonical solution, a comprehensive test case, and a difficulty scale to evaluate the correctness of the generated solutions. We systematically assess the performance of a set of LLMs against the Qiskit HumanEval dataset's tasks and focus on the models ability in producing executable quantum code. Our findings not only demonstrate the feasibility of using LLMs for generating quantum code but also establish a new benchmark for ongoing advancements in the field and encourage further exploration and development of GenAI-driven tools for quantum code generation.