WANG, Wenjie et al. OmniBench: A Comprehensive Benchmark Integrating Real-World, Time-sensitive, and Multi-Hop Questions with a Multi-Dimensional Hybrid Evaluation Framework. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 40, p. 33657–33665, 2026. DOI: 10.1609/aaai.v40i40.40655. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40655. Acesso em: 14 may. 2026.