Skip to content

Gemini Omni Flash

Google's Omni video model, first shown at I/O 2026, which generates and edits video with native audio; the 1.1 Flash version became generally available in the Gemini API on August 27, 2026. It has the highest score on LMArena text-to-video and is second on image-to-video.

GoogleVideo modelReleased August 2026Data checked October 18, 2026

Where people rank it

#1

Creating video (tied), 26,576 votes

#3

Turning images into video, 87,155 votes

From blind votes on LMArena, where people pick the better of two anonymous answers. See the full tables on the AI leaderboard.

Strengths and weaknesses

  • Highest LMArena text-to-video score (statistically tied with FLUX 3 Video and Grok Imagine Video 1.5)
  • Second-highest score on LMArena image-to-video
  • Cheap: about $0.10 per second of 720p video on the Gemini API
  • Ranks only eighth on Artificial Analysis' text-to-video arena, a clear disagreement between the two arenas
  • The 1.1 version's LMArena text-to-video score rests on fewer than 2,000 votes

Best for

  • Short videos with sound from a text prompt
  • Editing and extending video clips
  • YouTube Shorts and social clips

Every score we have

Each bar compares this model with the best result any model on this page has on the same test.

  • LMArena text to video1,516.2Arena score 1516.2 (95% CI 1500.8 to 1531.7); 1,784 votes; entry "gemini-omni-1.1-flash"; position 1 of 48 on the full board
  • LMArena image to video1,488.5Arena score 1488.5 (95% CI 1477.6 to 1499.4); 3,734 votes; entry "gemini-omni-1.1-flash"; position 2 of 48 on the full board
  • Artificial Analysis video arena1,132.1Elo 1132.1 (95% CI 1117.1 to 1147.1); 6,302 appearances; position 8 of 32 on the Artificial Analysis text-to-video arena
  • Price per minute of video (estimate)$9.12$9.12 per minute of video (Artificial Analysis estimate)

Compare with