# VidNum: Diagnosing VLM Failure Modes in Video-Grounded Numerical Reasoning

arXiv: https://arxiv.org/abs/2604.03701 · HTML: https://mlsanity.com/paper/2604.03701/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 10 of 10)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos](https://mlsanity.com/paper/2506.05349/) (2025)
- [AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs](https://mlsanity.com/paper/2506.05328/) (2025)
- [OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos](https://mlsanity.com/paper/2407.17085/) (2024)
- [SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance](https://mlsanity.com/paper/2603.12703/) (2026)
- [Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting](https://mlsanity.com/paper/2603.29943/) (2026)

## Abstract (arXiv)

Video-grounded numerical reasoning requires Vision-Language Models (VLMs) to identify, track, and combine quantitative evidence across frames, actions, and scene changes. Existing benchmarks provide fragmented coverage: general VideoQA includes counting among broader tasks, while dedicated benchmarks focus on repetition counting, ultra-long-video enumeration, or instructional mathematics. We introduce VidNum, a manually curated and independently verified benchmark containing 1,167 multiple-choice questions. Its three task groups distinguish Direct and Distinct Enumeration, Conditioned and Structured Enumeration, and Compositional Quantitative Reasoning. Question-level annotations further identify the evidence target, counting structure, and required reasoning operation. The best evaluated VLM reaches 59.8% accuracy, compared with 98.2% for human annotators, and no evaluated open-weight model exceeds 45%. Stratified analyses reveal that failures are not uniformly distributed: structured target construction and action-grounded compositional reasoning form recurring bottlenecks across models. Zero-shot chain-of-thought prompting is not a reliable remedy: it recovers some errors but breaks previously correct answers, with effects that vary across models and task structures. VidNum therefore supports diagnostic analysis beyond a single aggregate score.