# Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting

arXiv: https://arxiv.org/abs/2603.29943 · HTML: https://mlsanity.com/paper/2603.29943/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 63 references that are in the map.
- First posted on arXiv 31 Mar 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, 8 of 8)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling](https://mlsanity.com/paper/2501.12386/) (2025)
- [TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting](https://mlsanity.com/paper/2204.01018/) (2022)
- [LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering](https://mlsanity.com/paper/2312.04817/) (2023)
- [OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos](https://mlsanity.com/paper/2407.17085/) (2024)

## Built on by (most cited first, 3 of 3)

- [EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding](https://mlsanity.com/paper/2605.09874/) (2026)
- [Conditional Multi-Event Temporal Grounding in Long-Form Video](https://mlsanity.com/paper/2606.15320/) (2026)
- [VidNum: Diagnosing VLM Failure Modes in Video-Grounded Numerical Reasoning](https://mlsanity.com/paper/2604.03701/) (2026)

## Abstract (arXiv)

Final-answer video QA can show whether a model predicts the right number, but not which instances it counted, when the supporting evidence occurs, or why it failed. We diagnose long-video quantitative reasoning in multimodal large language models (MLLMs) through three coupled abilities: enumerating query-relevant instances, temporally grounding supporting evidence, and aggregating the evidence into counts. To support this analysis, we build EC-Bench, an evidence-annotated evaluation suite with 152 untrimmed videos longer than 30 minutes, 1,699 open-ended queries across six reasoning categories, and human-verified evidence spans. We evaluate 22 open-source and proprietary MLLMs using timestamped visual frames and transcripts. The best average scores reach only 29.98% Enumeration F1 and 23.74% Counting accuracy, compared with human performance of 78.57% and 82.97%, respectively. Our analyses show that counting errors are rarely isolated arithmetic mistakes: Enumeration F1 is strongly associated with Counting accuracy, temporal grounding quality is associated with lower counting error, and Counting accuracy drops as supporting evidence becomes more distributed. These findings recast long-video counting as evidence retrieval, temporal grounding, deduplication, and aggregation across the video, rather than simple numerical prediction.