Video Question Answering on Video-ChatGPT
62.7Average ScoreVideoLLaMA3 + ReFoCUS
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VideoLLaMA3 + ReFoCUSLLM=7B2025.06 | 62.7 | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VL + ReFoCUSLLM=8B2025.06 | 62.3 | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-OV + ReFoCUSLLM=7B2025.06 | 61.4 | — | — | — | — | — | — | — | — | — | — | — | |
| InternVL3 + ReFoCUSLLM=8B2025.06 | 61 | — | — | — | — | — | — | — | — | — | — | — | |
| InternVL3.5 + ReFoCUSLLM=8B2025.06 | 60.8 | — | — | — | — | — | — | — | — | — | — | — | |
| VideoLLaMA3LLM=7B, Sampling=Uniform2025.06 | 60.3 | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-VLLLM=8B, Sampling=Uniform2025.06 | 60.3 | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-OVLLM=7B, Sampling=Uniform2025.06 | 59.9 | — | — | — | — | — | — | — | — | — | — | — | |
| InternVL3.5LLM=8B, Sampling=Uniform2025.06 | 59.5 | — | — | — | — | — | — | — | — | — | — | — | |
| InternVL3LLM=8B, Sampling=Uniform2025.06 | 59.4 | — | — | — | — | — | — | — | — | — | — | — | |
| GPT4-VVision Encoder=GPT-42025.01 | 4.06 | — | — | — | — | — | 4.09 | — | 4.02 | 3.94 | 4.37 | 3.88 | |
| ViLL-EModel category=Temporally-Specialized Video LLMs2026.04 | 3.7 | — | — | — | — | — | — | — | — | — | — | — | |
| LLaVA-VideoModel category=General Video LLMs2026.04 | 3.5 | — | — | — | — | — | — | — | — | — | — | — | |
| PLLaVA 34BVision Encoder=ViT-L, LLM Size=34B2024.04 | 3.48 | 3.6 | 3.2 | 3.9 | 2.67 | 3.25 | — | — | — | — | — | — | |
| LLaVA-STModel category=Temporally-Specialized Video LLMs2026.04 | 3.3 | — | — | — | — | — | — | — | — | — | — | — | |
| PLLaVA 13BVision Encoder=ViT-L, LLM Size=13B2024.04 | 3.27 | 3.27 | 2.99 | 3.66 | 2.47 | 3.09 | — | — | — | — | — | — | |
| LLaVA-OctopusVision Encoder=SIGLIP, LLM Size=7B2025.01 | 3.19 | — | — | — | — | — | 3.43 | — | 3.24 | 2.65 | 3.68 | 2.95 | |
| IG-VLM GPT-4VVision Encoder=Unk, LLM Size=GPT-42024.04 | 3.17 | 3.4 | 2.8 | 3.61 | 2.89 | 3.13 | — | — | — | — | — | — | |
| ST-LLMVision Encoder=BLIP2, LLM Size=7B2024.04 | 3.15 | 3.23 | 3.05 | 3.74 | 2.93 | 2.81 | — | — | — | — | — | — | |
| ST-LLMModel category=Temporally-Specialized Video LLMs2026.04 | 3.15 | — | — | — | — | — | — | — | — | — | — | — | |
| ST-LLMVision Encoder=BLIP2, LLM Size=7B2025.01 | 3.15 | — | — | — | — | — | 3.23 | — | 2.81 | 2.93 | 3.74 | 3.05 | |
| VideoLLaMA2Vision Encoder=ViT-L, LLM Size=7B2025.01 | 3.13 | — | — | — | — | — | 3.16 | — | 3.14 | 2.56 | 3.69 | 3.08 | |
| PLLaVA 7BVision Encoder=ViT-L, LLM Size=7B2024.04 | 3.12 | 3.21 | 2.86 | 3.62 | 2.33 | 2.93 | — | — | — | — | — | — | |
| IG-VLM LLaVA 34BVision Encoder=ViT-L, LLM Size=34B2024.04 | 3.09 | 3.21 | 2.87 | 3.54 | 2.51 | 3.34 | — | — | — | — | — | — | |
| IG-VLM LLaVA 13BVision Encoder=ViT-L, LLM Size=13B2024.04 | 3.05 | 3.17 | 2.79 | 3.52 | 2.51 | 3.25 | — | — | — | — | — | — | |
| LITAVision Encoder=CLIP-L, LLM Size=7B2024.04 | 3.04 | 2.94 | 2.98 | 3.43 | 2.68 | 3.19 | — | — | — | — | — | — | |
| IG-VLM CogAgentVision Encoder=CLIP-E, LLM Size=7B2024.04 | 3.04 | 3.26 | 2.76 | 3.57 | 2.34 | 3.28 | — | — | — | — | — | — | |
| IG-VLM LLaVA 7BVision Encoder=ViT-L, LLM Size=7B2024.04 | 3.03 | 3.11 | 2.78 | 3.51 | 2.44 | 3.29 | — | — | — | — | — | — | |
| LLaVA-Octopus†Vision Encoder=SIGLIP, LLM Size=7B, Training data source=same as Video-LLaVA [36]2025.01 | 3.03 | — | — | — | — | — | 3.24 | — | 3.06 | 2.6 | 3.51 | 2.76 | |
| MomentorModel category=Temporally-Specialized Video LLMs2026.04 | 3 | — | — | — | — | — | — | — | — | — | — | — | |
| Chat-UniViVision Encoder=ViT-L, LLM Size=7B2024.04 | 2.99 | 2.89 | 2.91 | 3.46 | 2.89 | 2.81 | — | — | — | — | — | — | |
| Chat-UniViVision Encoder=ViT-L, LLM Size=7B2025.01 | 2.99 | — | — | — | — | — | 2.89 | — | 2.81 | 2.89 | 3.46 | 2.91 | |
| PLLaVAVision Encoder=ViT-L, LLM Size=7B2025.01 | 2.99 | — | — | — | — | — | 3.21 | — | 2.93 | 2.33 | 3.62 | 2.86 | |
| VideoChat2Vision Encoder=UMT-L, LLM Size=7B2024.04 | 2.98 | 3.02 | 2.88 | 3.51 | 2.66 | 2.81 | — | — | — | — | — | — | |
| VideoChat2-HDVision Encoder=UMT-L, LLM Size=7B2025.01 | 2.98 | — | — | — | — | — | 3.02 | — | 2.81 | 2.66 | 3.51 | 2.88 | |
| VTimeLLMModel category=Temporally-Specialized Video LLMs2026.04 | 2.9 | — | — | — | — | — | — | — | — | — | — | — | |
| LLaMA-VID†Vision Encoder=CLIP-G, LLM Size=7B, Training data source=same as Video-LLaVA [36]2025.01 | 2.9 | — | — | — | — | — | 2.96 | — | 2.51 | 2.46 | 3.53 | 3 | |
| LLAMA-VIDVision Encoder=CLIP-G, LLM Size=13B2024.04 | 2.89 | 2.96 | 3 | 3.53 | 2.46 | 2.51 | — | — | — | — | — | — | |
| VideoLLaMA2†Vision Encoder=ViT-L, LLM Size=7B, Training data source=same as Video-LLaVA [36]2025.01 | 2.82 | — | — | — | — | — | 2.98 | — | 2.97 | 2.33 | 3.25 | 2.58 | |
| MovieChatVision Encoder=CLIP-G, LLM Size=7B2024.04 | 2.67 | 2.76 | 2.93 | 3.01 | 2.24 | 2.42 | — | — | — | — | — | — | |
| MovieChatVision Encoder=CLIP-G, LLM Size=7B2025.01 | 2.67 | — | — | — | — | — | 2.76 | — | 2.42 | 2.24 | 3.01 | 2.93 | |
| Vista-LLaMAVision Encoder=CLIP-G, LLM Size=7B2024.04 | 2.57 | 2.44 | 2.64 | 3.18 | 2.26 | 2.31 | — | — | — | — | — | — | |
| Vista-LLaMAVision Encoder=CLIP-G, LLM Size=7B2025.01 | 2.57 | — | — | — | — | — | 2.44 | — | 2.31 | 2.26 | 3.18 | 2.64 | |
| Video-ChatGPTVision Encoder=ViT-L, LLM Size=7B2024.04 | 2.42 | 2.5 | 2.57 | 2.69 | 2.16 | 2.2 | — | — | — | — | — | — | |
| Video-ChatGPTVision Encoder=ViT-L, LLM Size=7B2025.01 | 2.42 | — | — | — | — | — | 2.5 | — | 2.2 | 2.16 | 2.69 | 2.57 | |
| VideoChatVision Encoder=ViT-L, LLM Size=7B2025.01 | 2.31 | — | — | — | — | — | 2.33 | — | 2.24 | 1.94 | 2.53 | 2.5 | |
| TimeChatModel category=Temporally-Specialized Video LLMs2026.04 | 2.3 | — | — | — | — | — | — | — | — | — | — | — | |
| VideoChatVision Encoder=CLIP-G, LLM Size=7B2024.04 | 2.29 | 2.23 | 2.5 | 2.53 | 1.94 | 2.24 | — | — | — | — | — | — | |
| VideoChatVision Encoder=CLIP-G, LLM Size=7B2025.01 | 2.29 | — | — | — | — | — | 2.23 | — | 2.24 | 1.94 | 2.53 | 2.5 | |
| BT-AdapterVision Encoder=CLIP-G, LLM Size=7B2025.01 | 2.2 | — | — | — | — | — | 2.68 | — | 2.46 | 2.34 | 3.27 | 2.69 | |
| LLaMA-AdapterVision Encoder=ViT-B, LLM Size=7B2024.04 | 2.16 | 2.03 | 2.32 | 2.3 | 1.98 | 2.15 | — | — | — | — | — | — | |
| LLaMA-AdapterVision Encoder=ViT-B, LLM Size=7B2025.01 | 2.16 | — | — | — | — | — | 2.03 | — | 2.15 | 1.98 | 2.3 | 2.32 | |
| Video-LLaMAVision Encoder=CLIP-G, LLM Size=7B2024.04 | 1.98 | 1.96 | 2.18 | 2.16 | 1.82 | 1.79 | — | — | — | — | — | — | |
| Video-LLaMAVision Encoder=CLIP-G, LLM Size=7B2025.01 | 1.98 | — | — | — | — | — | 1.96 | — | 1.79 | 1.82 | 2.16 | 2.18 | |
| BT-Adapter0-shot=true, LLM=Vicuna-7B2024.06 | — | — | — | — | — | — | 2.68 | 2.69 | 3.27 | 2.34 | 2.46 | — | |
| Chat-UniViModel Size=7B, # Frames=82024.06 | — | — | — | — | — | — | 2.89 | — | 2.81 | 2.89 | 3.46 | 2.91 | |
| GPT4-V2024.06 | — | — | — | — | — | — | 4.09 | — | 4.02 | 3.94 | 4.37 | 3.88 | |
| LLaMa-VID0-shot=true, LLM=Vicuna-7B2024.06 | — | — | — | — | — | — | 2.96 | 3 | 3.53 | 2.46 | 2.51 | — | |
| LLaMA-VIDParams=13B2024.05 | — | 3.07 | 3.05 | 3.6 | 2.58 | 2.63 | — | — | — | — | — | — | |
| LLaMA-VIDModel Size=7B, # Frames=1 fps2024.06 | — | — | — | — | — | — | 2.96 | — | 2.51 | 2.46 | 3.53 | 3 | |
| LLaVA-NeXT-Videoframes=322024.06 | — | — | — | — | — | — | 3.39 | 3.29 | 3.12 | 2.6 | 3.92 | — | |
| LLaVA-NeXT-VideoModel Size=7B, # Frames=322024.06 | — | — | — | — | — | — | 3.39 | — | 3.12 | 2.6 | 3.92 | 3.29 | |
| LongVAframes=82024.06 | — | — | — | — | — | — | 3.09 | 3.14 | 3.73 | 2.39 | 3.72 | — | |
| LongVAframes=162024.06 | — | — | — | — | — | — | 3.13 | 3.15 | 3.61 | 2.4 | 3.75 | — | |
| LongVAframes=322024.06 | — | — | — | — | — | — | 3.08 | 3.1 | 3.65 | 2.28 | 3.74 | — | |
| LongVAframes=642024.06 | — | — | — | — | — | — | 3.05 | 3.09 | 3.64 | 2.44 | 3.77 | — | |
| LongVA-DPOframes=322024.06 | — | — | — | — | — | — | 3.55 | 3.32 | 4.07 | 2.86 | 4.09 | — | |
| LongVLMParams=7B2024.05 | — | 2.76 | 2.86 | 3.34 | 2.39 | 3.11 | — | — | — | — | — | — | |
| MiCo-Chat-7B0-shot=true, LLM=Vicuna-7B2024.06 | — | — | — | — | — | — | 3 | 3.01 | 3.61 | 2.49 | 2.71 | — | |
| MovieChatParams=7B2024.05 | — | 2.76 | 2.93 | 3.01 | 2.24 | 2.67 | — | — | — | — | — | — | |
| Pegasus-12024.06 | — | — | — | — | — | — | 3.79 | — | 4.03 | 3.34 | 4.29 | 3.76 | |
| PLLAVAParams=13B2024.05 | — | 3.27 | 2.99 | 3.66 | 2.47 | 3.09 | — | — | — | — | — | — | |
| PLLAVAModel Size=34B, # Frames=162024.06 | — | — | — | — | — | — | 3.6 | — | 3.25 | 2.67 | 3.9 | 3.2 | |
| Video-ChatGPT0-shot=true, LLM=Vicuna-7B2024.06 | — | — | — | — | — | — | 2.4 | 2.52 | 2.62 | 1.98 | 2.37 | — | |
| Video-ChatGPTModel Size=7B, # Frames=82024.06 | — | — | — | — | — | — | 2.5 | — | 2.2 | 2.16 | 2.69 | 2.57 | |
| Video-LLaMAParams=7B2024.05 | — | 1.96 | 2.18 | 2.16 | 1.82 | 1.79 | — | — | — | — | — | — | |
| Video-LLaVAModel Size=7B, # Frames=82024.06 | — | — | — | — | — | — | 2.87 | — | 2.51 | 2.45 | 3.44 | 2.94 | |
| VideoChatParams=7B2024.05 | — | 2.23 | 2.5 | 2.53 | 1.94 | 2.24 | — | — | — | — | — | — | |
| VideoChat0-shot=true, LLM=Vicuna-7B2024.06 | — | — | — | — | — | — | 2.23 | 2.5 | 2.53 | 1.94 | 2.24 | — | |
| VideoChatModel Size=7B, # Frames=82024.06 | — | — | — | — | — | — | 2.23 | — | 2.24 | 1.94 | 2.53 | 2.5 | |
| VideoChat2Model Size=7B, # Frames=162024.06 | — | — | — | — | — | — | 3.02 | — | 2.81 | 2.66 | 3.51 | 2.88 | |
| VideoChatGPTParams=7B2024.05 | — | 2.4 | 2.52 | 2.62 | 1.98 | 2.37 | — | — | — | — | — | — | |
| VideoLLaMA0-shot=true, LLM=Vicuna-7B2024.06 | — | — | — | — | — | — | 1.96 | 2.18 | 2.16 | 1.82 | 1.79 | — | |
| VideoLLaMAModel Size=7B, # Frames=82024.06 | — | — | — | — | — | — | 1.96 | — | 1.79 | 1.82 | 2.16 | 2.18 | |
| VideoLLaMA 2Model Size=7B, # Frames=82024.06 | — | — | — | — | — | — | 3.09 | — | 3.25 | 2.63 | 3.68 | 3.09 | |
| VideoLLaMA 2Model Size=7B, # Frames=162024.06 | — | — | — | — | — | — | 3.16 | — | 3.14 | 2.56 | 3.69 | 3.08 | |
| VideoLLaMA 2Model Size=8x7B, # Frames=82024.06 | — | — | — | — | — | — | 3.08 | — | 3.26 | 2.67 | 3.64 | 3.11 | |
| VideoLLaMA 2Model Size=72B, # Frames=82024.06 | — | — | — | — | — | — | 3.23 | — | 3.12 | 2.62 | 3.71 | 3.11 | |
| VideoLLaMA 2.1Model Size=7B, # Frames=162024.06 | — | — | — | — | — | — | 3.3 | — | 3.2 | 2.66 | 3.78 | 3.18 | |
| VideoStreamingParams=7B+1.3B2024.05 | — | 3.33 | 3.27 | 3.73 | 2.74 | 3.15 | — | — | — | — | — | — |