cff-version: 1.2.0
message: "If you use this systematization of knowledge, the benchmark catalog, or the evaluation framework in your research, please cite it as below."
title: "Systematizing the Evaluation of Generalist Multimodal Large Language Models: Benchmarks, Metrics, and Protocols Across Modalities"
authors:
  - family-names: "Abbaszadeh"
    given-names: "Alireza"
    affiliation: "Department of Computer Engineering, Islamic Azad University, Mashhad, Iran"
year: 2026
preferred-citation:
  type: article
  authors:
    - family-names: "Abbaszadeh"
      given-names: "Alireza"
      affiliation: "Department of Computer Engineering, Islamic Azad University, Mashhad, Iran"
  title: "Systematizing the Evaluation of Generalist Multimodal Large Language Models: Benchmarks, Metrics, and Protocols Across Modalities"
  journal: "ACM Computing Surveys (CSUR) / arXiv preprint"
  year: 2026
  pages: "1--57"
  url: "https://github.com/alirezaabbaszadeh/mllm-eval-sok"
keywords:
  - "Multimodal Large Language Models"
  - "Systematization of Knowledge (SoK)"
  - "Benchmark Evaluation"
  - "PRISMA 2020"
  - "Evaluation Dark Matter"
  - "Data Contamination"
  - "Pareto Efficiency"