Challenging Vision-Language Models with Surgical Data: A New Dataset and Broad Benchmarking Study

While traditional computer vision models have historically struggled to generalize to endoscopic domains, the emergence of foundation models has shown promising cross-domain performance. In this work, we present the first large-scale study assessing the capabilities of Vision Language Models (VLMs) for endoscopic tasks with a specific focus on laparoscopic surgery. Using a diverse set of state-of-the-art models, multiple surgical datasets, and extensive human reference annotations, we address three key research questions: (1) Can current VLMs solve basic perception tasks on surgical images? (2) Can they handle advanced frame-based endoscopic scene understanding tasks? and (3) How do specialized medical VLMs compare to generalist models in this context? Our results reveal that VLMs can effectively perform basic surgical perception tasks, such as object counting and localization, with performance levels comparable to general domain tasks. However, their performance deteriorates significantly when the tasks require medical knowledge. Notably, we find that specialized medical VLMs currently underperform compared to generalist models across both basic and advanced surgical tasks, suggesting that they are not yet optimized for the complexity of surgical environments. These findings highlight the need for further advancements to enable VLMs to handle the unique challenges posed by surgery. Overall, our work provides important insights for the development of next-generation endoscopic AI systems and identifies key areas for improvement in medical visual language models.

Bridging vision language model (VLM) evaluation gaps with a framework for scalable and cost-effective benchmark generation

Reliable evaluation of AI models is critical for scientific progress and practical application. While existing VLM benchmarks provide general insights into model capabilities, their heterogeneous designs and limited focus on a few imaging domains pose significant challenges for both cross-domain performance comparison and targeted domain-specific evaluation. To address this, we propose three key contributions: (1) a framework for the resource-efficient creation of domain-specific VLM benchmarks enabled by task augmentation for creating multiple diverse tasks from a single existing task, (2) the release of new VLM benchmarks for seven domains, created according to the same homogeneous protocol and including 162,946 thoroughly human-validated answers, and (3) an extensive benchmarking of 22 state-of-the-art VLMs on a total of 37,171 tasks, revealing performance variances across domains and tasks, thereby supporting the need for tailored VLM benchmarks. Adoption of our methodology will pave the way for the resource-efficient domain-specific selection of models and guide future research efforts toward addressing core open questions.