ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development
This addresses a gap in benchmarking for AI agents in practical backend engineering, though it is incremental as it builds on existing evaluation methods by adding dynamic, full-process requirements.
The authors tackled the lack of benchmarks for evaluating autonomous AI agents in real-world backend coding by introducing ABC-Bench, which tests 224 tasks across multiple languages and frameworks, revealing that state-of-the-art models struggle with reliable performance in holistic development workflows.
The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks predominantly evaluate code logic in static contexts, neglecting the dynamic, full-process requirements of real-world engineering, particularly in backend development which demands rigorous environment configuration and service deployment. To address this gap, we introduce ABC-Bench, a benchmark explicitly designed to evaluate agentic backend coding within a realistic, executable workflow. Using a scalable automated pipeline, we curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories. Distinct from previous evaluations, ABC-Bench require the agents to manage the entire development lifecycle from repository exploration to instantiating containerized services and pass the external end-to-end API tests. Our extensive evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks, highlighting a substantial disparity between current model capabilities and the demands of practical backend engineering. Our code is available at https://github.com/OpenMOSS/ABC-Bench.