Published 2025 | Version v1

Leveraging Large Language Models (LLM) for Python Unit Test

Description

Abstract

This study evaluates the capability of six state-of-the-art Large Language Models (LLMs): Perplexity AI, Claude Sonnet 4.5, Gemini 2.5 Pro, ChatGPT (GPT-5), DeepSeek-V3.2-Exp, and Llama-4-Maverick, to generate production-quality Python code with comprehensive unit tests.

Files

Files (72.7 kB)