Google DeepMind·· 2026-09-02
Introducing agentic video understanding with Gemini
Introducing agentic video understanding with Gemini
AI summary
Google DeepMind introduced agentic video understanding for Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite, reducing video analysis token use by up to 88% and costs by up to 66%, while improving accuracy by up to 7%.
Selection record
Threshold 60Official, first-handFirst 78Second 74
AdmittedSum of both 152 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：Gemini发布智能体视频理解AI功能
- Why it was chosen
- Official figures for token savings, cost reductions and accuracy changes show how long-video analysis costs may shift.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Google DeepMind · deepmind.google