The rise of Multimodal Large Language Models (MLLMs) has significantly advanced the capabilities of AI systems to understand and generate content across diverse modalities such as text, images, audio, video, and sensory data. By leveraging the reasoning prowess of Large Language Models (LLMs), MLLMs unify multiple input formats into a coherent framework, enabling unprecedented performance in multimodal tasks. This survey provides a comprehensive overview of the architectural innovations, training paradigms, data resources, and evaluation benchmarks that have shaped the evolution of MLLMs. We rResearch goal: To what extent does modality imbalance affect the accuracy and routing stability of multimodal language models as measured by performance on MMBench and SEED-Bench evaluation suites?Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.8/10.