Streaming Video Understanding on StreamingBench
93.55OverallHuman
Evaluation Results
| Method | Links | |||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Human# of Frames=-2026.03 | 93.55 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 88.8 | 90.4 | 95 | 100 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Human2025.08 | 93.55 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 88.8 | 90.4 | 95 | 100 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Human+2025.01 | 91.66 | 89.47 | 92 | 93.6 | 91.47 | 95.65 | 92.52 | 88 | 88.75 | 89.74 | 91.3 | 88 | 88.24 | 93.6 | 90.27 | 88.8 | 90.4 | 95 | 100 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Human# of Frames=-2026.03 | 91.66 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Human2025.08 | 91.66 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Human2026.05 | 91.5 | 89.5 | 92 | 93.6 | 91.5 | 95.7 | 92.5 | 88 | 88.8 | 89.7 | 91.3 | — | — | — | — | — | — | — | 100 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HumanParams=-2026.05 | 91.46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Human# of Frames=-2026.03 | 90.26 | — | — | — | — | — | — | — | — | — | — | 88 | 88.24 | 93.6 | 90.27 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Human2025.08 | 90.26 | — | — | — | — | — | — | — | — | — | — | 88 | 88.24 | 93.6 | 90.27 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SELECTSTREAM-Qwen3-VL-8B#Frames=1 fps2026.06 | 82.67 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SELECTSTREAM-Qwen2.5-VL-7B#Frames=1 fps2026.06 | 81.42 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VL-8B + 4f#Frames=1fps2026.06 | 80.59 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VST-7BVenue=-, Execution Mode=Online, Model Accessibility=Open-source2026.03 | 79.5 | 85.4 | 82 | 86.4 | 89.1 | 74.2 | 87.2 | 82.4 | 73.1 | 73.9 | 47.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HERMES-7B#Frames=1 fps2026.06 | 79.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| QSVideoLLM=8B, Frames=162026.07 | 79.36 | 84.47 | 82.81 | 88.96 | 84.31 | 81.99 | 85.05 | 75 | 74.39 | 77.34 | 44.56 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2.5-VL-7B + 4f#Frames=1fps2026.06 | 78.47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| QSVideoLLM=8B, Frames=82026.07 | 77.68 | 83.11 | 79.69 | 86.12 | 83.66 | 80.12 | 83.49 | 76.85 | 72.76 | 74.22 | 44.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Response-G1Params=8B2026.05 | 77.5 | 84 | 78.1 | 88 | 84.6 | 74.8 | 83.5 | 83.3 | 63 | 69.3 | 58 | — | — | — | — | — | — | — | 44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Streamforest-7BVenue=NeurIPS’25, Execution Mode=Online, Model Accessibility=Open-source2026.03 | 77.3 | 83.1 | 82.8 | 82.7 | 84.3 | 77.5 | 78.2 | 76.9 | 69.1 | 75.6 | 54.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StreamForest-7B#Frames=1 fps2026.06 | 77.26 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StreamForestLLM=7B, Frames=1fps2026.07 | 77.26 | 83.11 | 82.81 | 82.65 | 84.26 | 77.5 | 78.19 | 76.85 | 69.11 | 75.64 | 54.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| InfiniPot-VLLM=7B, Frames=0.5fps2026.07 | 76.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| R3-Streaming-7B|4B-ThinkingParams=7B/4B, Evaluation Mode=Streaming MLLMs, Visual-token reduction ratio=95%↓2026.05 | 76.36 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini 1.5 proVenue=-, Execution Mode=Offline, Model Accessibility=Proprietary2026.03 | 75.7 | 79 | 80.5 | 83.5 | 79.7 | 80 | 84.7 | 77.8 | 64.2 | 72 | 48.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini 1.5 pro2026.05 | 75.7 | 79 | 80.5 | 83.5 | 79.7 | 80 | 84.7 | 77.8 | 64.2 | 72 | 48.7 | — | — | — | — | — | — | — | 45.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TimeChatOnline-7BVenue=MM’25, Execution Mode=Online, Model Accessibility=Open-source2026.03 | 75.4 | 80.2 | 82 | 79.5 | 83.3 | 76.1 | 78.5 | 78.7 | 64.6 | 69.6 | 58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TimeChat-OnlineParams=7B2026.05 | 75.4 | 80.2 | 82 | 79.5 | 83.3 | 76.1 | 78.5 | 78.7 | 64.6 | 69.6 | 58 | — | — | — | — | — | — | — | 28.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TimeChat-Online-7B#Frames=1 fps2026.06 | 75.28 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ThinkStream-7B#Frames=1 fps2026.06 | 75 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2.5-VL-7BMode=Traditional Streaming Prefill (Baseline), acn=∞, ur=∞, s=–2026.06 | 74.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| R3-Streaming-3B|4B-ThinkingParams=3B/4B, Evaluation Mode=Streaming MLLMs, Visual-token reduction ratio=95%↓2026.05 | 74.36 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StreamAgentParams=7B2026.05 | 74.3 | 79.6 | 78.3 | 79.3 | 75.9 | 74.7 | 76.9 | 82.9 | 66.3 | 73.7 | 55.4 | — | — | — | — | — | — | — | 28.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StreamAgentParams=7B, Evaluation Mode=Streaming MLLMs2026.05 | 74.28 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Claude 3.5Frames=202026.07 | 74.04 | 82.45 | 73.77 | 82.43 | 82.4 | 76.39 | 85.56 | 61.68 | 60.73 | 67.88 | 47.62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| QueryStreamLLM=7B, Frames=1fps2026.07 | 74.04 | 82.11 | 83.59 | 78.23 | 82.69 | 75.47 | 80.06 | 79.63 | 63.01 | 67.9 | 42.55 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| R3-Streaming-3B|7B-InstructParams=3B/7B, Evaluation Mode=Streaming MLLMs, Visual-token reduction ratio=95%↓2026.05 | 73.84 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-OVLLM=7B, Frames=162026.07 | 73.76 | 79.56 | 79.69 | 82.65 | 83.66 | 73.29 | 74.77 | 72.22 | 69.11 | 69.97 | 40.93 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2.5-VL-7BVenue=-, Execution Mode=Offline, Model Accessibility=Open-source2026.03 | 73.7 | 78.3 | 80.5 | 78.9 | 80.5 | 76.7 | 78.5 | 79.6 | 63.4 | 66.2 | 53.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Response-G1Architecture=Qwen3-VL-8B2026.05 | 73.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 44 | — | — | — | — | — | — | — | — | — | — | — | 77.5 | — | — | — | — | |
| TimeChat-Online-7BParams=7B, Evaluation Mode=Streaming MLLMs, Visual-token reduction ratio=83%↓2026.05 | 73.64 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2.5-VL-7B#Frames=1 fps2026.06 | 73.31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-4oVenue=-, Execution Mode=Offline, Model Accessibility=Proprietary2026.03 | 73.3 | 77.1 | 80.5 | 83.9 | 76.5 | 70.2 | 83.8 | 66.7 | 62.2 | 69.1 | 49.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-4o2026.05 | 73.3 | 77.1 | 80.5 | 83.9 | 76.5 | 70.2 | 83.8 | 66.7 | 62.2 | 69.1 | 49.2 | — | — | — | — | — | — | — | 56.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-4oParams=-, Evaluation Mode=Proprietary MLLMs2026.05 | 73.28 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2.5-VL-7BParams=7B, Evaluation Mode=Offline Video MLLMs2026.05 | 73.28 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VL-4B-ThinkingParams=4B, Evaluation Mode=Offline Video MLLMs2026.05 | 73.16 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AURAModel Accessibility=Open-Source Models2026.04 | 73.1 | 87.5 | 84.4 | 93.4 | 89.5 | 83.2 | 87.9 | 86.1 | 76.4 | 82.4 | 47.7 | — | 48.4 | 62.8 | 80.4 | 70.8 | 54.8 | 57.2 | 53.2 | — | — | — | — | — | — | — | — | — | — | — | 83.2 | 56.4 | 62 | 59 | — | |
| Seed1.5-VLThinking mode=true, Evaluation frame rate=1 FPS2025.05 | 72.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Claude 3.5 SonnetParams=-, Evaluation Mode=Proprietary MLLMs2026.05 | 72.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Claude 3.5 Sonnet2026.05 | 72.4 | 80.5 | 77.3 | 82 | 81.7 | 72.3 | 75.4 | 61.1 | 61.8 | 69.3 | 43.1 | — | — | — | — | — | — | — | 64.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-OVLLM=7B, Frames=82026.07 | 72.12 | 79.29 | 72.66 | 82.97 | 82.35 | 72.67 | 69.16 | 75 | 68.29 | 69.12 | 37.31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-7B, acn=8, ur=64, s=0.25 (↓48.4%)2026.06 | 71.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-7B, acn=4, ur=64, s=0.25 (↓48.0%)2026.06 | 71.64 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-7B, acn=8, ur=32, s=0.25 (↓48.4%)2026.06 | 71.48 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-7B, acn=4, ur=32, s=0.25 (↓48.0%)2026.06 | 71.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Seed1.5-VLThinking mode=false, Evaluation frame rate=1 FPS2025.05 | 71.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Response-G1Architecture=LLaVA-OV-1.5-8B2026.05 | 71.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 35.6 | — | — | — | — | — | — | — | — | — | — | — | 74.8 | — | — | — | — | |
| LLaVA-OneVisionParams=7B, Evaluation Mode=Offline Video MLLMs2026.05 | 71.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-OneVision-7B#Frames=322026.06 | 71.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-OV-7BVenue=TMLR’25, Execution Mode=Offline, Model Accessibility=Open-source2026.03 | 71.1 | 80.4 | 74.2 | 76 | 80.7 | 72.7 | 71.7 | 67.6 | 65.5 | 65.7 | 45.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-OneVisionParams=7B2026.05 | 71.1 | 80.4 | 74.2 | 76 | 80.7 | 72.7 | 71.7 | 67.6 | 65.5 | 65.7 | 45.1 | — | — | — | — | — | — | — | 29.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TimeChat-Online2026.05 | 70.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.8 | — | — | — | — | — | — | — | — | — | — | — | 75.4 | — | — | — | — | |
| VITA-1.5LLM=7B, Frames=162026.07 | 70.88 | 77.66 | 82.81 | 82.33 | 79.34 | 72.67 | 71.34 | 67.59 | 62.2 | 69.12 | 32.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-3B, acn=4, ur=32, s=0.25 (↓57.6%)2026.06 | 70.68 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-3B, acn=8, ur=64, s=0.25 (↓57.3%)2026.06 | 70.52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| InternVL2LLM=8B, Frames=162026.07 | 70.52 | 75.2 | 64.84 | 75.08 | 84.97 | 75.16 | 72.9 | 73.15 | 65.85 | 64.59 | 42.49 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-3B, acn=8, ur=32, s=0.25 (↓57.3%)2026.06 | 70.48 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-3B, acn=4, ur=64, s=0.25 (↓57.6%)2026.06 | 70.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-7B, acn=8, ur=32, s=0.1 (↓70.5%)2026.06 | 70.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-7B, acn=8, ur=64, s=0.1 (↓70.5%)2026.06 | 70.42 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2.5-VL-3BMode=Traditional Streaming Prefill (Baseline), acn=∞, ur=∞, s=–2026.06 | 70.32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini 1.5 ProRegime=Offline, Category=Closed-source2026.03 | 70.26 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 54.8 | — | — | 67.8 | — | 77.39 | 45.1 | — | — | — | — | — | — | — | — | — | — | — | |
| MiniCPM-V 2.6LLM=8B, Frames=162026.07 | 70.24 | 75.2 | 71.09 | 83.28 | 80.39 | 68.94 | 68.85 | 70.37 | 59.76 | 66.29 | 46.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StreamAgent2026.05 | 70.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.9 | — | — | — | — | — | — | — | — | — | — | — | 74.3 | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-7B, acn=4, ur=64, s=0.1 (↓70.6%)2026.06 | 69.71 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-7B, acn=4, ur=32, s=0.1 (↓70.6%)2026.06 | 69.56 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2-VLParams=7B, Evaluation Mode=Offline Video MLLMs2026.05 | 69.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2-VL-7B#Frames=642026.06 | 69.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen2-VLParams=7B2026.05 | 69 | 75.2 | 82.8 | 73.2 | 77.5 | 68.3 | 71 | 72.2 | 61.2 | 61.5 | 46.1 | — | — | — | — | — | — | — | 22.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-4oEvaluation frame rate=1 FPS2025.05 | 68.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| InternVL2LLM=8B, Frames=82026.07 | 68.52 | 76.02 | 60.94 | 72.24 | 82.35 | 68.94 | 70.72 | 72.22 | 66.67 | 60.62 | 41.97 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-3B, acn=4, ur=64, s=0.1 (↓72.9%)2026.06 | 68.32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-3B, acn=4, ur=32, s=0.1 (↓72.9%)2026.06 | 68.28 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-3B, acn=8, ur=32, s=0.1 (↓72.9%)2026.06 | 67.68 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DispiderParams=7B, Evaluation Mode=Streaming MLLMs2026.05 | 67.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Dispider-7B#Frames=1 fps2026.06 | 67.63 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Dispider-8BVenue=CVPR’25, Execution Mode=Online, Model Accessibility=Open-source2026.03 | 67.6 | 74.9 | 75.5 | 74.1 | 73.1 | 74.4 | 59.9 | 76.1 | 62.9 | 62.2 | 45.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DispiderParams=7B2026.05 | 67.6 | 74.9 | 75.5 | 74.1 | 73.1 | 74.4 | 59.9 | 76.1 | 62.9 | 62.2 | 45.8 | — | — | — | — | — | — | — | 25.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MiniCPM-V 2.6Params=8B, Evaluation Mode=Offline Video MLLMs2026.05 | 67.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MiniCPM-v2.6-7BVenue=COLM’24, Execution Mode=Offline, Model Accessibility=Open-source2026.03 | 67.4 | 71.9 | 71.1 | 77.9 | 75.8 | 64.6 | 65.7 | 70.4 | 56.1 | 62.3 | 53.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MiniCPM-V-2.6Params=8B2026.05 | 67.4 | 71.9 | 71.1 | 77.9 | 75.8 | 64.6 | 65.7 | 70.4 | 56.1 | 62.3 | 53.4 | — | — | — | — | — | — | — | 22.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ViCoStreamBackbone=Qwen2.5-VL-3B, acn=8, ur=64, s=0.1 (↓73.0%)2026.06 | 67.39 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini-1.5-ProModel Accessibility=Proprietary Models2026.04 | 67.1 | 79 | 80.5 | 83.5 | 79.7 | 80 | 84.7 | 77.8 | 64.2 | 72 | 48.7 | — | 39.6 | 74.9 | 80 | 40.7 | 51.4 | 54.8 | 45.1 | — | — | — | — | — | — | — | — | — | — | — | 75.7 | 46.8 | 60.2 | 48.7 | — | |
| Gemini 1.5 proFrames=1 fps2025.01 | 67.07 | 79.02 | 80.47 | 83.54 | 79.67 | 80 | 84.74 | 77.78 | 64.23 | 71.95 | 48.7 | 46.8 | 39.6 | 74.9 | 80 | 51.41 | 40.73 | 54.8 | 45.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini 1.5 pro# of Frames=1 FPS2026.03 | 67.07 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini 1.5 proFrames=1 fps2025.08 | 67.07 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-NeXT-VideoParams=32B2026.05 | 67 | 78.2 | 70.3 | 73.8 | 76.8 | 63.4 | 69.8 | 57.4 | 56.1 | 64.3 | 38.9 | — | — | — | — | — | — | — | 18.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-NeXT-VideoParams=32B, Evaluation Mode=Offline Video MLLMs2026.05 | 66.96 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MiniCPM-V 2.6LLM=8B, Frames=82026.07 | 66.36 | 70.3 | 65.62 | 79.5 | 76.8 | 67.08 | 67.29 | 66.67 | 55.28 | 59.49 | 45.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MiniCPM-o 2.6LLM=8B, Frames=162026.07 | 65.12 | 69.21 | 77.34 | 76.66 | 72.22 | 72.67 | 64.17 | 56.48 | 58.54 | 62.89 | 31.61 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |