Unverified50% confidenceFactExact time
Among mainstream AI models, only Gemini can natively understand video, because large-scale video data was incorporated during its pre-training phase.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/24/2026
First Seen
Valid until: 10/22/2026
Sources
6个开源工具系统补齐Claude Code五大短板
bilibiliNixAI7/8/2026
Related Claims
UnverifiedAmong mainstream AI models, only Gemini can natively understand video; Claude itself lacks native video understanding capability.84% similarUnverifiedGemini mixes text, image, audio, and video data as input from the pre-training stage to achieve native multimodal training.74% similarUnverifiedGemini的图像生成能力基于原生多模态架构，模型在训练阶段同时学习了文本和图像的表征72% similarUnverifiedGemini的视频生成能力基于Google DeepMind的Veo模型71% similarUnverifiedGoogle Gemini 1.5 Pro及后续版本采用原生多模态架构，能直接处理视频帧序列，具有百万级token上下文窗口70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/607437API
curl https://kongchang.com/api/v1/knowledge/claims/607437MCP
get_claim(id=607437)