INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance

Chenwei Lin, Hanjia Lyu, Xian Xu, Jiebo Luo

Keywords: large vision-language model, insurance, multimodal

Abstract: Large Vision-Language Models (LVLMs) have demonstrated outstanding performance in various general multimodal applications such as image recognition and visual reasoning, and have also shown promising potential in specialized domains. However, the application potential of LVLMs in the insurance domain—characterized by rich application scenarios and abundant multimodal data—has not been effectively explored. There is no systematic review of multimodal tasks in the insurance domain, nor a benchmark specifically designed to evaluate the capabilities of LVLMs in insurance. This gap hinders the development of LVLMs within the insurance domain. In this paper, we systematically review and distill multimodal tasks for four representative types of insurance: auto insurance, property insurance, health insurance, and agricultural insurance. We propose INS-MMBench, the first comprehensive LVLMs benchmark tailored for the insurance domain. INS-MMBench comprises a total of 2.2K thoroughly designed multiple-choice questions, covering 12 meta-tasks and 22 fundamental tasks. Furthermore, we evaluate multiple representative LVLMs, including closed-source models such as GPT-4o and open-source models like BLIP-2. This evaluation not only validates the effectiveness of our benchmark but also provides an in-depth performance analysis of current LVLMs on various multimodal tasks in the insurance domain. We hope that INS-MMBench will facilitate the further application of LVLMs in the insurance domain and inspire interdisciplinary development.

Primary Area: datasets and benchmarks

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3987