James Meaden, Markus Borg. COMPASS: A Psychometrics-Guided Multi-Dimensional Benchmark for Code Generation Evaluation. In Proceedings of the 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering, FORGE 2026, Rio de Janeiro, Brazil, April 12-13, 2026. pages 213-217, ACM, 2026. [doi]
Abstract is missing.