DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain

TL;DR

DiningBench is a comprehensive, hierarchical benchmark for evaluating vision-language models in the food domain, emphasizing fine-grained classification, nutrition estimation, and visual question answering.

Contribution

It introduces a new multi-view, hierarchical dataset with rigorous nutritional data, and provides extensive evaluation revealing current models' limitations in fine-grained and nutritional reasoning.

Findings

Current VLMs excel at general reasoning but struggle with fine-grained visual discrimination.

Multi-view inputs and Chain-of-Thought reasoning impact model performance.

Identified five primary failure modes in food-centric VLMs.

Abstract

Recent advancements in Vision-Language Models (VLMs) have revolutionized general visual understanding. However, their application in the food domain remains constrained by benchmarks that rely on coarse-grained categories, single-view imagery, and inaccurate metadata. To bridge this gap, we introduce DiningBench, a hierarchical, multi-view benchmark designed to evaluate VLMs across three levels of cognitive complexity: Fine-Grained Classification, Nutrition Estimation, and Visual Question Answering. Unlike previous datasets, DiningBench comprises 3,021 distinct dishes with an average of 5.27 images per entry, incorporating fine-grained "hard" negatives from identical menus and rigorous, verification-based nutritional data. We conduct an extensive evaluation of 29 state-of-the-art open-source and proprietary models. Our experiments reveal that while current VLMs excel at general reasoning, they struggle significantly with fine-grained visual discrimination and precise nutritional reasoning. Furthermore, we systematically investigate the impact of multi-view inputs and Chain-of-Thought reasoning, identifying five primary failure modes. DiningBench serves as a challenging testbed to drive the next generation of food-centric VLM research. All codes are released in https://github.com/meituan/DiningBench.