StreamingBench

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding 🏠 Project Page | 📄 arXiv Paper | 📦 Dataset | 🏅Leaderboard StreamingBench evaluates Multimodal Large Language Models (MLLMs) in real-time, streaming video understanding tasks. 🌟 [NEW! 2025.05.15] 🔥: Seed1.5-VL achieved ALL model S

Papers using StreamingBench (4)

Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models2026WAT: Online Video Understanding Needs Watching Before Thinking2026FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding2026Vista: Scene-Aware Optimization for Streaming Video Question Answering under Post-Hoc Queries2026