| StreamReady: Learning What to Answer and When in Long Streaming Videos | | 63.9 | StreamReady | 2026-03-09 |
| StreamForest: Efficient Online Video Understanding with Persistent Event Memory | ✓ Link | 61.6 | StreamForest (FT-drive) | 2025-09-29 |
| StreamForest: Efficient Online Video Understanding with Persistent Event Memory | ✓ Link | 60.5 | StreamForest | 2025-09-29 |
| Seed1.5-VL Technical Report | | 60.0 | Seed1.5-VL | 2025-05-11 |
| VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding | | 60.0 | VideoChat3-4B | 2026-07-16 |
| Online Video Understanding: OVBench and VideoChat-Online | ✓ Link | 54.9 | VideoChat-Online (4B) | 2024-12-31 |
| FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding | | 50.82 | Qwen2VL-7B + FreshMem | 2026-02-02 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context | ✓ Link | 50.7 | Gemini-1.5-Flash | 2024-03-08 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 49.7 | Qwen2-VL (7B) | 2024-09-18 |
| LLaVA-OneVision: Easy Visual Task Transfer | ✓ Link | 49.5 | LLaVA-OneVision (7B) | 2024-08-06 |
| Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling | ✓ Link | 48.7 | InternVL2 (7B) | 2024-12-06 |
| FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding | | 47.44 | InternVL2-2B + FreshMem | 2026-02-02 |
| Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding | | 46.8 | LyraV | 2026-06-05 |
| Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling | ✓ Link | 44.1 | InternVL2 (4B) | 2024-12-06 |
| Long Context Transfer from Language to Vision | ✓ Link | 43.6 | LongVA (7B) | 2024-06-24 |
| LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models | ✓ Link | 41.9 | LLaMA-VID (7B) | 2023-11-28 |
| | 39.1 | MiniCPM-V 2.6 (7B) | |
| VTimeLLM: Empower LLM to Grasp Video Moments | ✓ Link | 33.1 | VTimeLLM (7B) | 2023-11-30 |
| Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams | ✓ Link | 31.2 | Flash-Vstream (7B) | 2024-06-12 |
| MovieChat: From Dense Token to Sparse Memory for Long Video Understanding | ✓ Link | 30.9 | MovieChat (7B) | 2023-07-31 |
| LITA: Language Instructed Temporal-Localization Assistant | ✓ Link | 20.4 | LITA (7B) | 2024-03-27 |
| TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding | ✓ Link | 12.8 | TimeChat (7B) | 2023-12-04 |
| VideoLLM-online: Online Video Large Language Model for Streaming Video | | 9.6 | VideoLLM-Online (7B) | 2024-06-17 |