Expired85% confidenceFactTime unknown
Gemini 3.5 Pro scored 82.1 on the Video ModeM multimodal video understanding benchmark, significantly leading other models
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe video generation capability of Gemini 3.1 Pro is powered by Google's Veo series of video generation models.77% similarUnverifiedThe video generation feature of Gemini 3.1 Pro supports the generation of 8-second cinematic short clips.77% similarUnverifiedIn neutral mode, Gemini 3.1 Pro Preview achieved an end-to-end accuracy of 40.8%.76% similarUnverifiedIn the SimpleQA benchmark, Gemini 3.1 Pro leads with a score of 75.6, while DeepSeek V4 Pro scored 57.9.76% similarUnverifiedGemini 3.7 Flash多模态长视频理解得分85.4%，长上下文记忆保持率高达97%74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13608API
curl https://kongchang.com/api/v1/knowledge/claims/13608MCP
get_claim(id=13608)