Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation
This work addresses the need for practical, application-driven benchmarks for LLM code generation in software development, though it is incremental as it focuses on a specific domain.
The paper tackled the problem of evaluating large language models (LLMs) in test-driven development (TDD) tasks by introducing the WebApp1K benchmark, which uses test cases as prompts and verification, and found that instruction following and in-context learning are critical for success, with performance bottlenecks identified across 19 models.
We introduce WebApp1K, a novel benchmark for evaluating large language models (LLMs) in test-driven development (TDD) tasks, where test cases serve as both prompt and verification for code generation. Unlike traditional approaches relying on natural language prompts, our benchmark emphasizes the ability of LLMs to interpret and implement functionality directly from test cases, reflecting real-world software development practices. Comprising 1000 diverse challenges across 20 application domains, the benchmark evaluates LLMs on their ability to generate compact, functional code under the constraints of context length and multi-feature complexity. Our findings highlight instruction following and in-context learning as critical capabilities for TDD success, surpassing the importance of general coding proficiency or pretraining knowledge. Through comprehensive evaluation of 19 frontier models, we reveal performance bottlenecks, such as instruction loss in long prompts, and provide a detailed error analysis spanning multiple root causes. This work underscores the practical value of TDD-specific benchmarks and lays the foundation for advancing LLM capabilities in rigorous, application-driven coding scenarios.