Towards Video-LLM Driven Workflow for Behavioral Segmentation and Scoring in Mice Performing a Skilled Water Reaching Task: An Evaluation of Recent LLM Models
Bibliographic record
Abstract
Abstract Significance Behavior 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. Aim We 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. Approach Videos 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 mouse’s actions over time. Results Gemini 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. Conclusions Video-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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".