# Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models

arXiv: https://arxiv.org/abs/2409.00084 · HTML: https://mlsanity.com/paper/2409.00084/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 7 of its 44 references that are in the map.
- First posted on arXiv 25 Aug 2024.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 7 of 7)

- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Evaluating Quantized Large Language Models](https://mlsanity.com/paper/2402.18158/) (2024)
- [Large Language Models for Medicine: A Survey](https://mlsanity.com/paper/2405.13055/) (2024)
- [What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation](https://mlsanity.com/paper/2403.06408/) (2024)
- [DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text](https://mlsanity.com/paper/2310.20170/) (2023)

## Built on by (most cited first, 7 of 7)

- [LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation](https://mlsanity.com/paper/2410.21520/) (2024)
- [Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy](https://mlsanity.com/paper/2506.09958/) (2025)
- [Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models](https://mlsanity.com/paper/2503.18562/) (2025)
- [TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought](https://mlsanity.com/paper/2602.22828/) (2026)
- [CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance](https://mlsanity.com/paper/2604.01113/) (2026)
- [Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure?](https://mlsanity.com/paper/2606.16583/) (2026)
- [Latent Confidence Alignment for LLM Self-Assessment](https://mlsanity.com/paper/2606.21937/) (2026)

## Abstract (arXiv)

Background and Aims: This study evaluates the medical reasoning performance of large language models (LLMs) and vision language models (VLMs) in gastroenterology. Methods: We used 300 gastroenterology board exam-style multiple-choice questions, 138 of which contain images to systematically assess the impact of model configurations and parameters and prompt engineering strategies utilizing GPT-3.5. Next, we assessed the performance of proprietary and open-source LLMs (versions), including GPT (3.5, 4, 4o, 4omini), Claude (3, 3.5), Gemini (1.0), Mistral, Llama (2, 3, 3.1), Mixtral, and Phi (3), across different interfaces (web and API), computing environments (cloud and local), and model precisions (with and without quantization). Finally, we assessed accuracy using a semiautomated pipeline. Results: Among the proprietary models, GPT-4o (73.7%) and Claude3.5-Sonnet (74.0%) achieved the highest accuracy, outperforming the top open-source models: Llama3.1-405b (64%), Llama3.1-70b (58.3%), and Mixtral-8x7b (54.3%). Among the quantized open-source models, the 6-bit quantized Phi3-14b (48.7%) performed best. The scores of the quantized models were comparable to those of the full-precision models Llama2-7b, Llama2--13b, and Gemma2-9b. Notably, VLM performance on image-containing questions did not improve when the images were provided and worsened when LLM-generated captions were provided. In contrast, a 10% increase in accuracy was observed when images were accompanied by human-crafted image descriptions. Conclusion: In conclusion, while LLMs exhibit robust zero-shot performance in medical reasoning, the integration of visual data remains a challenge for VLMs. Effective deployment involves carefully determining optimal model configurations, encouraging users to consider either the high performance of proprietary models or the flexible adaptability of open-source models.