# NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions

arXiv: https://arxiv.org/abs/2407.12843 · HTML: https://mlsanity.com/paper/2407.12843/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 4 Jul 2024.

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2305.11747/) (2023)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [FELM: Benchmarking Factuality Evaluation of Large Language Models](https://mlsanity.com/paper/2310.00741/) (2023)
- [A Survey on Food Computing](https://mlsanity.com/paper/1808.07202/) (2018)
- [Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food](https://mlsanity.com/paper/2103.03375/) (2021)
- [Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering](https://mlsanity.com/paper/2403.04890/) (2024)
- [Computer vision-based food calorie estimation: dataset, method, and experiment](https://mlsanity.com/paper/1705.07632/) (2017)
- [Multi-Task Learning for Calorie Prediction on a Novel Large-Scale Recipe Dataset Enriched with Nutritional Information](https://mlsanity.com/paper/2011.01082/) (2020)
- [UMDFood: Vision-language models boost food composition compilation](https://mlsanity.com/paper/2306.01747/) (2023)
- [NutritionVerse-Synth: An Open Access Synthetically Generated 2D Food Scene Dataset for Dietary Intake Estimation](https://mlsanity.com/paper/2312.06192/) (2023)
- [NutritionVerse-Real: An Open Access Manually Collected 2D Food Scene Dataset for Dietary Intake Estimation](https://mlsanity.com/paper/2401.08598/) (2023)
- [NutritionVerse-Direct: Exploring Deep Neural Networks for Multitask Nutrition Prediction from Food Images](https://mlsanity.com/paper/2405.07814/) (2024)

## Built on by (most cited first, 17 of 17)

- [Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs](https://mlsanity.com/paper/2509.01790/) (2025)
- [HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models](https://mlsanity.com/paper/2504.14594/) (2025)
- [RHealthTwin: Towards Responsible and Multimodal Digital Twins for Personalized Well-being](https://mlsanity.com/paper/2506.08486/) (2025)
- [Evaluation of LLMs in retrieving food and nutritional context for RAG systems](https://mlsanity.com/paper/2603.09704/) (2026)
- [BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity](https://mlsanity.com/paper/2603.18019/) (2026)
- [FAM-Bench: A Multimodal Benchmark for Condition-Aware Food-as-Medicine Reasoning](https://mlsanity.com/paper/2605.31410/) (2026)
- [NutriMLLM: Multimodal Large Language Models for Dietary Micronutrient Analysis](https://mlsanity.com/paper/2606.08948/) (2026)
- [Evaluating Gemini LLM in Food Image-Based Recipe and Nutrition Description with EfficientNet-B4 Visual Backbone](https://mlsanity.com/paper/2511.08215/) (2025)
- [Wrist Photoplethysmography Predicts Dietary Information](https://mlsanity.com/paper/2511.19260/) (2025)
- [From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation](https://mlsanity.com/paper/2607.12687/) (2026)
- [Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition](https://mlsanity.com/paper/2607.12911/) (2026)
- [Statistically Supported LLM Ingredient and Recipe Data Collection in Computational Nutrition](https://mlsanity.com/paper/2607.23273/) (2026)
- [Nutrition Data Infrastructure for the AI Era: Operationalizing FAIR for Agent-Mediated Research](https://mlsanity.com/paper/2608.10363/) (2026)
- [FlavourBench: Executable Culinary Reward Maps for Language Model Evaluation and Post-Training](https://mlsanity.com/paper/2608.20574/) (2026)
- [PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consulting](https://mlsanity.com/paper/2608.24907/) (2026)
- [Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge](https://mlsanity.com/paper/2608.29249/) (2026)
- [Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition](https://mlsanity.com/paper/2609.32803/) (2026)

## Abstract (arXiv)

Accurate nutrition estimation helps people make informed dietary choices and is essential in the prevention of serious health complications. We present NutriBench, the first publicly available natural language meal description nutrition benchmark. NutriBench consists of 11,857 meal descriptions generated from real-world global dietary intake data. The data is human-verified and annotated with macro-nutrient labels, including carbohydrates, proteins, fats, and calories. We conduct an extensive evaluation of NutriBench on the task of carbohydrate estimation, testing twelve leading Large Language Models (LLMs), including GPT-4o, Llama3.1, Qwen2, Gemma2, and OpenBioLLM models, using standard, Chain-of-Thought and Retrieval-Augmented Generation strategies. Additionally, we present a study involving professional nutritionists, finding that LLMs can provide comparable but significantly faster estimates. Finally, we perform a real-world risk assessment by simulating the effect of carbohydrate predictions on the blood glucose levels of individuals with diabetes. Our work highlights the opportunities and challenges of using LLMs for nutrition estimation, demonstrating their potential to aid professionals and laypersons and improve health outcomes. Our benchmark is publicly available at: https://mehak126.github.io/nutribench.html