Unverified50% confidenceFactExact time
DeepSeek系列模型在视觉能力上一直存在相对短板
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/19/2026
First Seen
Valid until: 11/17/2026
Sources
Related Claims
UnverifiedDeepSeek falls somewhat short of Gemini in multimodal (especially visual) capabilities.75% similarUnverifiedDeepThink has released a multimodal model and related technical report, focusing on the shortcomings of multimodal large models in cross-perceptual-domain reasoning chains.74% similarPartially VerifiedDeepSeek's current primary model does not support image recognition (multimodal) and has not yet opened an API interface for image understanding.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/774262API
curl https://kongchang.com/api/v1/knowledge/claims/774262MCP
get_claim(id=774262)