Skip to content

Grok Imagine Video 1.5

SpaceXSI's (formerly xAI) Grok Imagine video model, which turns text or images into short videos. It ties for first on LMArena text-to-video and places eighth among all entries on LMArena image-to-video.

SpaceXSI (formerly xAI)Video modelReleased May 2026Data checked October 18, 2026

Where people rank it

#6

Turning images into video, 137,459 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
  • Large LMArena image-to-video sample (over 137,000 votes), so that score is stable
  • Low price, from $0.08 per second
  • Its top text-to-video score is listed under an 'agent' variant with only about 1,200 votes
  • Ranks tenth on Artificial Analysis' text-to-video arena

Best for

  • Quick, cheap social videos
  • Animating a still image

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 video1,492.3Arena score 1492.3 (95% CI 1474.0 to 1510.6); 1,218 votes; entry "grok-imagine-video-1.5-agent"; position 4 of 48 on the full board
  • LMArena image to video1,456Arena score 1456.0 (95% CI 1451.8 to 1460.2); 137,459 votes; entry "grok-imagine-video-1.5-720p"; position 8 of 48 on the full board
  • Artificial Analysis video arena1,060.1Elo 1060.1 (95% CI 1044.1 to 1076.1); 3,748 appearances; position 10 of 32 on the Artificial Analysis text-to-video arena
  • Price per minute of video (estimate)$15$15.00 per minute of video (Artificial Analysis estimate)

Compare with