EUVIMEDEUVIMED entdecken
Crossref

MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models

Jiacheng Ruan, Dan Jiang, Xian Gao, Ting Liu, Yuzhuo Fu, Yangyang Kang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (11) · 8760-8768

DOI: 10.1609/aaai.v40i11.37829 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiacheng Ruan und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, multimodal large language models (MLLMs) have achieved significant advancements across various domains, and corresponding evaluation benchmarks have been continuously refined and improved. In this process, benchmarks in the scientific domain have played an important role in assessing the reasoning capabilities of MLLMs. However, existing benchmarks still face three key challenges: 1) Insufficient evaluation of models' reasoning abilities in multilingual scenarios; 2) Inadequate assessment of MLLMs' comprehensive modality coverage; 3) Lack of fine-grained annotation of scientific knowledge points. To address these gaps, we propose MME-SCI, a comprehensive and challenging benchmark. We carefully collected 1,019 high-quality question-answer pairs, which involve 3 distinct evaluation modes. These pairs cover four subjects, namely mathematics, physics, chemistry, and biology, and support five languages: Chinese, English, French, Spanish, and Japanese. We conducted extensive experiments on 16 open-source models and 4 closed-source models, and the results demonstrate that MME-SCI is widely challenging for existing MLLMs. For instance, under the Image-only evaluation mode, o4-mini achieved accuracy of only 52.11%, 24.73%, 36.57%, and 29.80% in mathematics, physics, chemistry, and biology, respectively, indicating a significantly higher difficulty level compared to existing benchmarks. More importantly, using MME-SCI's multilingual and fine-grained knowledge attributes, we analyzed existing models' performance in depth and identified their weaknesses in specific domains. For example, in questions related to "Magnetic Field", o4-mini correctly answered only 5 out of 33 questions, thereby fine-grainedly exposing the model's vulnerabilities. These findings highlight the urgent need to enhance the scientific reasoning capabilities of MLLMs.

Zitieren

APA

Ruan, J., Jiang, D., Gao, X., Liu, T., Fu, Y., & Kang, Y. (2026). MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(11), 8760-8768. https://doi.org/10.1609/aaai.v40i11.37829

Vancouver

Ruan J, Jiang D, Gao X, Liu T, Fu Y, Kang Y. MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(11):8760-8768. doi:10.1609/aaai.v40i11.37829

BibTeX
@article{Ruan2026,
  author = {Ruan, Jiacheng and Jiang, Dan and Gao, Xian and Liu, Ting and Fu, Yuzhuo and Kang, Yangyang},
  title = {MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {11},
  pages = {8760--8768},
  doi = {10.1609/aaai.v40i11.37829}
}
Kostenlos starten →