# CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning

arXiv: https://arxiv.org/abs/2609.03526 · HTML: https://mlsanity.com/paper/2609.03526/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 10 of 10)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking](https://mlsanity.com/paper/2402.09369/) (2024)
- [CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge](https://mlsanity.com/paper/2404.06664/) (2024)
- [MultiNRC: A Challenging and Native Multilingual Reasoning Evaluation Benchmark for LLMs](https://mlsanity.com/paper/2507.17476/) (2025)
- [Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing](https://mlsanity.com/paper/2402.06015/) (2024)
- [IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs](https://mlsanity.com/paper/2605.10267/) (2026)
- [IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products](https://mlsanity.com/paper/2606.14383/) (2026)

## Abstract (arXiv)

Multimodal language models achieve near-ceiling scores on food recognition benchmarks, yet it remains unclear whether this success reflects genuine cultural understanding or mere visual matching. To probe this distinction, we introduce CulturalMenuBench, a benchmark of 4,870 items in 10 languages across 18 regions; its 10 tasks pair final-dish and step-by-step cooking images with ingredients, procedural text, and regional labels, spanning basic recognition to process-grounded cultural attribution. Evaluating 12 models exposes a substantial knowledge-application gap: models exceeding 94% on standard multiple-choice tasks drop to at most 56% when attributing dishes to Chinese regional cuisines, despite an identical four-way format. Diagnostic analyses explain why: error patterns are consistent with random guessing, accuracy tracks visual distinctiveness rather than cultural structure, and models classify cuisines more accurately from dish names alone than from images (+7-18 points). The knowledge is thus present but cannot be activated through visual input. An ablation confirms these tasks genuinely require procedural evidence: removing sequential cooking images selectively degrades process-grounded tasks while others remain stable. Overall, CulturalMenuBench shows that near-perfect recognition can conceal an inability to apply cultural knowledge, motivating training that explicitly connects perception, procedure, and cultural context. Code and data are publicly available.