AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

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

Chenwei Lin, Hanjia Lyu, Xian Xu, Jiebo Luo

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Benchmarks and analysis of MLLMs · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add insurance-related information to the prompt (crop growth stage) (ablation)GPT-4V · Crop growth stage detectionaccuracy (%): 22.00 -> 52.00Improved
add insurance-related information to the prompt (house damage type) (ablation)GPT-4o · House damage type detectionaccuracy (%): 48.00 -> 57.00Improved
add insurance-related information to the prompt (vehicle damage severity) (ablation)Qwen-VL-Max · Vehicle damage severity detectionaccuracy (%): 72.00 -> 61.00Hurt
add insurance-related information to the prompt (vehicle damage severity) (ablation)Qwen-VL-Plus · Vehicle damage severity detectionaccuracy (%): 68.00 -> 58.00Hurt
add insurance-related information to the prompt (vehicle damage severity) (ablation)Gemini 1.5 Flash · Vehicle damage severity detectionaccuracy (%): 68.00 -> 68.00No clear effect
use distractors from Claude 3.5 Haiku or DeepSeek-V3 instead of GPT-4o (ablation)INS-MMBench multiple-choice questions · three tasks, 1,500 questionsaccuracyNo clear effect
scenario task multi-step reasoning vs fundamental tasksGPT-4o, Qwen-VL-Max, Gemini 1.5 Flash · INS-MMBench scenario tasksaccuracyHurt
open-source Qwen-2.5-VL-32B vs closed-source modelsQwen-2.5-VL-32B · INS-MMBench fundamental tasksaverage accuracy: 64.10 vs 69.70 (GPT-4o)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy