Google DeepMind's video generation model Gemini Omni Flash has claimed the top spot in both the Text-to-Video and Image-to-Video categories of the Video Arena run by Arena.ai (formerly LMArena). According to Arena.ai's disclosure on June 11, 2026, in Text-to-Video the model leads Veo 3.1 (1080p) by +158 points and the next-best Seedance 2.0 by +61 points. In Image-to-Video it posted a +77-point improvement over Veo 3.1, placing it at the top.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
