Skip to content

FLUX 3 Video

Black Forest Labs' FLUX 3 video model, which generates video with synchronized audio from text, keyframes or an existing clip. It is in the tied top group on LMArena text-to-video.

Black Forest LabsVideo modelReleased July 2026Data checked October 18, 2026

Where people rank it

#7

Turning images into video, 37,042 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

  • Tied for first on LMArena text-to-video
  • Sixth on Artificial Analysis' text-to-video arena
  • Cheaper draft mode ($0.06 per second) for previews
  • Its LMArena text-to-video score rests on only about 1,300 votes
  • Pricier than Gemini Omni Flash ($0.17 per second at HD vs about $0.10)

Best for

  • Text-to-video with sound
  • Animating keyframes you design

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 video1,493.1Arena score 1493.1 (95% CI 1475.8 to 1510.3); 1,302 votes; entry "flux-3-video"; position 3 of 48 on the full board
  • LMArena image to video1,449.4Arena score 1449.4 (95% CI 1444.5 to 1454.4); 37,042 votes; entry "flux-3-video-20260811"; position 9 of 48 on the full board
  • Artificial Analysis video arena1,146.3Elo 1146.2 (95% CI 1130.2 to 1162.2); 5,036 appearances; position 6 of 32 on the Artificial Analysis text-to-video arena
  • Price per minute of video (estimate)$17$17.40 per minute of video (Artificial Analysis estimate)

Compare with