# MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding

arXiv: https://arxiv.org/abs/2607.01751 · HTML: https://mlsanity.com/paper/2607.01751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [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)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?](https://mlsanity.com/paper/2501.05510/) (2025)
- [Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding](https://mlsanity.com/paper/2510.08668/) (2025)
- [Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer](https://mlsanity.com/paper/2206.11053/) (2022)
- [CholecTriplet2021: A benchmark challenge for surgical action triplet recognition](https://mlsanity.com/paper/2204.04746/) (2022)
- [The TUM LapChole dataset for the M2CAI 2016 workflow challenge](https://mlsanity.com/paper/1610.09278/) (2016)
- [LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning](https://mlsanity.com/paper/2408.07981/) (2024)
- [PitVQA: Image-grounded Text Embedding LLM for Visual Question Answering in Pituitary Surgery](https://mlsanity.com/paper/2405.13949/) (2024)
- [V2T-CoT: From Vision to Text Chain-of-Thought for Medical Reasoning and Diagnosis](https://mlsanity.com/paper/2506.19610/) (2025)
- [Beyond N-grams: A Hierarchical Reward Learning Framework for Clinically-Aware Medical Report Generation](https://mlsanity.com/paper/2512.02710/) (2025)
- [MedHorizon: Towards Long-context Medical Video Understanding in the Wild](https://mlsanity.com/paper/2605.06537/) (2026)
- [SurgOnAir: Hierarchy-Aware Real-Time Surgical Video Commentary](https://mlsanity.com/paper/2605.21132/) (2026)

## Abstract (arXiv)

Existing medical video benchmarks primarily evaluate whether a model produces the correct answer, but rarely assess whether it answers at the right time. In real clinical settings, AI systems must decide not only what to predict, but also when to answer, defer judgment, or proactively raise alerts. This creates a critical gap between benchmark evaluation and deployment requirements. We present MedStreamBench, a benchmark for time-aware medical video understanding. MedStreamBench integrates 22 medical datasets and 5,419 QA instances across four temporal settings: retrospective, present, future, and proactive. Unlike conventional benchmarks that assume full-video access, MedStreamBench restricts models to temporally bounded evidence windows and supports both single-turn and streaming evaluation. We further introduce a proactive monitoring setting that requires models to determine whether and when clinically relevant alerts should be triggered. Beyond answer correctness, MedStreamBench evaluates temporal behavior through responsiveness and post-evidence stability. Experiments on leading general-purpose and medical vision-language models reveal a substantial gap between offline recognition and temporally grounded decision-making, with performance dropping markedly in streaming and proactive settings. Our benchmark is available at https://huggingface.co/datasets/Venn2024/MedStreamBench.