English

LLM-as-a-Judge for Scalable Test Coverage Evaluation: Accuracy, Operational Reliability, and Cost

Software Engineering 2025-12-02 v1 Artificial Intelligence

Abstract

Assessing software test coverage at scale remains a bottleneck in QA pipelines. We present LLM-as-a-Judge (LAJ), a production-ready, rubric-driven framework for evaluating Gherkin acceptance tests with structured JSON outputs. Across 20 model configurations (GPT-4, GPT-5 with varying reasoning effort, and open-weight models) on 100 expert-annotated scripts over 5 runs (500 evaluations), we provide the first comprehensive analysis spanning accuracy, operational reliability, and cost. We introduce the Evaluation Completion Rate (ECR@1) to quantify first-attempt success, revealing reliability from 85.4% to 100.0% with material cost implications via retries. Results show that smaller models can outperform larger ones: GPT-4o Mini attains the best accuracy (6.07 MAAE), high reliability (96.6% ECR@1), and low cost (1.01per1K),yieldinga78xcostreductionvs.GPT5(highreasoning)whileimprovingaccuracy.Reasoningeffortismodelfamilydependent:GPT5benefitsfromincreasedreasoning(withpredictableaccuracycosttradeoffs),whereasopenweightmodelsdegradeacrossalldimensionsasreasoningincreases.Overall,costspans175x(1.01 per 1K), yielding a 78x cost reduction vs. GPT-5 (high reasoning) while improving accuracy. Reasoning effort is model-family dependent: GPT-5 benefits from increased reasoning (with predictable accuracy-cost tradeoffs), whereas open-weight models degrade across all dimensions as reasoning increases. Overall, cost spans 175x (0.45-$78.96 per 1K). We release the dataset, framework, and code to support reproducibility and deployment.

Keywords

Cite

@article{arxiv.2512.01232,
  title  = {LLM-as-a-Judge for Scalable Test Coverage Evaluation: Accuracy, Operational Reliability, and Cost},
  author = {Donghao Huang and Shila Chew and Anna Dutkiewicz and Zhaoxia Wang},
  journal= {arXiv preprint arXiv:2512.01232},
  year   = {2025}
}

Comments

7 pages, accepted by the AAAI 2026 Workshop on Next Gen Code Development with Collaborative AI Agents

R2 v1 2026-07-01T08:02:56.260Z