Towards Video-LLM Driven Workflow for Behavioral Segmentation and Scoring in Mice Performing a Skilled Water Reaching Task: An Evaluation of Recent LLM Models

Abstract

SignificanceBehavior scoring is labor-intensive and subjective, introducing variability in results. Large Language Models (LLMs) capable of video understanding offer a transformative solution to manual scoring, crucial for accelerating and standardizing neuroscience workflows. AimWe sought to benchmark state-of-the-art video LLMs (Gemini 2.5 Pro, Qwen3-VL, and VideoLLaMA3) for automated behavioural segmentation and scoring of mice performing a water-reaching task. ApproachVideos of mice performing water reaching from the front view were analysed by the LLMs. Accuracy was compared across different models and against prompt adjustments within Gemini. To assess classification determinants, video fidelity was altered through pixel interpolation and key regions blurred (paws/snout-mouth). In addition, the models were asked to describe the mouses actions over time. ResultsGemini 2.5 Pro (0.74 {+/-} 0.12 accuracy) and Qwen3-VL-30B (0.67 {+/-} 0.13) exhibited ability to classify trial outcomes. Reliable classification required a minimum pixel resolution of 0.28 mm per pixel. Accuracy is significantly reduced upon obscuring the snout-mouth area. In 549/1058 of videos, Gemini 2.5 Pro also provided completely accurate frame-to-frame behaviour segmentations. ConclusionsVideo-LLMs offer potential to accelerate neuroscience by providing scalable, objective quantification of goal-directed behaviors. By producing temporal annotations, Gemini enables fast first-pass labelling that markedly streamlines manual dataset curation.