# NeuroVLM-Bench: Evaluation of Vision-Enabled Large Language Models for Clinical Reasoning in Neurological Disorders

arXiv: https://arxiv.org/abs/2603.24846 · HTML: https://mlsanity.com/paper/2603.24846/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 15 of its 67 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## 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, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [Med-HALT: Medical Domain Hallucination Test for Large Language Models](https://mlsanity.com/paper/2307.15343/) (2023)
- [MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks](https://mlsanity.com/paper/2505.23802/) (2025)
- [Capabilities of GPT-5 on Multimodal Medical Reasoning](https://mlsanity.com/paper/2508.08224/) (2025)
- [Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach](https://mlsanity.com/paper/2502.00577/) (2025)
- [DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?](https://mlsanity.com/paper/2505.24173/) (2025)
- [MedSG-Bench: A Benchmark for Medical Image Sequences Grounding](https://mlsanity.com/paper/2505.11852/) (2025)
- [OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks](https://mlsanity.com/paper/2511.00846/) (2025)
- [Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities](https://mlsanity.com/paper/2508.07031/) (2025)
- [Benchmarking GPT-5 for Zero-Shot Multimodal Medical Reasoning in Radiology and Radiation Oncology](https://mlsanity.com/paper/2508.13192/) (2025)
- [Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks](https://mlsanity.com/paper/2509.22258/) (2025)
- [Structured Prompts Improve Evaluation of Language Models](https://mlsanity.com/paper/2511.20836/) (2025)
- [Zero-Shot Multi-modal Large Language Model v.s. Supervised Deep Learning: A Comparative Study on CT-Based Intracranial Hemorrhage Subtyping](https://mlsanity.com/paper/2505.09252/) (2025)

## Built on by (most cited first, 1 of 1)

- [BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning](https://mlsanity.com/paper/2610.06571/) (2026)

## Abstract (arXiv)

Recent advances in multimodal large language models enable new possibilities for image-based decision support. However, their reliability and operational trade-offs in neuroimaging remain insufficiently understood. We present a comprehensive benchmarking study of vision-enabled large language models for 2D neuroimaging using curated MRI and CT datasets covering multiple sclerosis, stroke, brain tumors, other abnormalities, and normal controls. Models are required to generate multiple outputs simultaneously, including diagnosis, diagnosis subtype, imaging modality, specialized sequence, and anatomical plane. Performance is evaluated across four directions: discriminative classification with abstention, calibration, structured-output validity, and computational efficiency. A multi-phase framework ensures fair comparison while controlling for selection bias. Across twenty frontier multimodal models, the results show that technical imaging attributes such as modality and plane are nearly solved, whereas diagnostic reasoning, especially subtype prediction, remains challenging. Tumor classification emerges as the most reliable task, stroke is moderately solvable, while multiple sclerosis and rare abnormalities remain difficult. Few-shot prompting improves performance for several models but increases token usage, latency, and cost. Gemini-2.5-Pro and GPT-5-Chat achieve the strongest overall diagnostic performance, while Gemini-2.5-Flash offers the best efficiency-performance trade-off. Among open-weight architectures, MedGemma-1.5-4B demonstrates the most promising results, as under few-shot prompting, it approaches the zero-shot performance of several proprietary models, while maintaining perfect structured output. These findings provide practical insights into performance, reliability, and efficiency trade-offs, supporting standardized evaluation of multimodal LLMs in neuroimaging.