OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks

TL;DR

OmniBrainBench is a comprehensive multimodal benchmark designed to evaluate large language models' understanding of brain imaging across multiple clinical tasks, revealing significant gaps compared to physicians.

Contribution

It introduces the first extensive multimodal VQA benchmark for brain imaging analysis, covering 15 modalities and 15 clinical tasks, enabling thorough assessment of MLLMs in medical contexts.

Findings

Proprietary MLLMs like GPT-5 outperform others but still lag behind physicians.

All models struggle with complex preoperative reasoning tasks.

Open-source models excel in specific tasks but lack general clinical understanding.

Abstract

Brain imaging analysis is crucial for diagnosing and treating brain disorders, and multimodal large language models (MLLMs) are increasingly supporting it. However, current brain imaging visual question-answering (VQA) benchmarks either cover a limited number of imaging modalities or are restricted to coarse-grained pathological descriptions, hindering a comprehensive assessment of MLLMs across the full clinical continuum. To address these, we introduce OmniBrainBench, the first comprehensive multimodal VQA benchmark specifically designed to assess the multimodal comprehension capabilities of MLLMs in brain imaging analysis with closed- and open-ended evaluations. OmniBrainBench comprises 15 distinct brain imaging modalities collected from 30 verified medical sources, yielding 9,527 validated VQA pairs and 31,706 images. It simulates clinical workflows and encompasses 15 multi-stage clinical tasks rigorously validated by a professional radiologist. Evaluations of 24 state-of-the-art models, including open-source general-purpose, medical, and proprietary MLLMs, highlight the substantial challenges posed by OmniBrainBench. Experiments reveal that proprietary MLLMs like GPT-5 (63.37%) outperform others yet lag far behind physicians (91.35%), while medical ones show wide variance in closed- and open-ended VQA. Open-source general-purpose MLLMs generally trail but excel in specific tasks, and all ones fall short in complex preoperative reasoning, revealing a critical visual-to-clinical gap. OmniBrainBench establishes a new standard to assess MLLMs in brain imaging analysis, highlighting the gaps against physicians. We publicly release our benchmark at link.