xAI Grok Imagine Video 1.5 Takes Top Spot in Arena Rankings

Arena

May 31, 2026 · Updated Jun 13, 2026

xAI's Grok-Imagine-Video-1.5-Preview (720p) has reached the #1 position on the Arena Image-to-Video leaderboard with an Elo score of 1,473. The model unseated previous leaders from ByteDance and Alibaba, marking a significant jump in human-preferred video generation quality.

Arena.ai used blind human preference testing to find that xAI has secured the top ranking in its Image-to-Video Arena. The new grok-imagine-video-1.5-preview-720p achieved a 52-point improvement, reaching an Elo score (a relative rating system based on head-to-head wins) of 1,473.

Model: grok-imagine-video-1.5-preview-720p
Elo Score: 1473±9
Improvement: +52 points
Total Arena Votes: 1,155,731
Rank: 1

This shift places xAI ahead of established leaders like ByteDance's Dreamina Seedance 2.0 and Alibaba's HappyHorse. Based on over 1.1 million community votes, the ranking suggests xAI has closed motion and fidelity gaps that previously favored Chinese labs. It also outpaces Google's Veo 3.1 series in human preference for image-to-video tasks.

These capabilities are available through the Grok Build beta for X Premium+ subscribers. Developers can integrate the 720p preview to generate video from image prompts, utilizing the highest-rated visual consistency currently available. Third-party access is also supported through the Vercel AI Gateway generateVideo function and fal's serverless inference platform.

View the full update on arena.ai

Arena.ai

@arenaMay 31

Grok-Imagine-Video-1.5-Preview (720p) has landed #1 in the Image-to-Video Arena! This is a massive +52 pt improvement over Grok-Imagine-Video (720p), surpassing the best video models Seedance-2.0 and HappyHorse. Congrats to @xAI and @elonmusk on this big achievement! https://t.co/FB91ytZteF

1481.6k

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from Arena →

Keep reading

Arena.ai Ranks xAI's Grok Build 0.1 Above Grok 4.3 in Agent Arena

Arena.ai's new Agent Arena leaderboard places xAI's Grok Build 0.1 at #15 and Grok 4.3 (High) at #17. Grok Build 0.1 demonstrates improved bash capability and looks to be successfully completing tasks more often overall than Grok 4.3, though it is slightly less steerable and more prone to tool hallucinations.

Artificial Analysis Ranks xAI Grok Imagine Quality in Top Five

Artificial AnalysisJun 1

Artificial Analysis Ranks xAI Grok Imagine Quality in Top Five

Artificial Analysis has ranked xAI's high-fidelity image model as the leading alternative to OpenAI and Google offerings. The model delivers top-tier visual quality and editing capabilities at a significantly lower price point than its primary competitors.

xAIApr 3

xAI Launches Quality Mode for Grok Imagine with Improved Text and Physics

xAI introduced a new Quality mode for Grok Imagine that prioritizes visual detail and accurate text rendering over generation speed. This update addresses common AI image generation failures by improving the model's understanding of physics, brand references, and complex object relationships.

Vercel Adds xAI Grok Imagine Video 1.5 for Terminal Generation

VercelJun 4

Vercel Adds xAI Grok Imagine Video 1.5 for Terminal Generation

Vercel has integrated xAI's Grok Imagine Video 1.5 model into its AI CLI, enabling users to generate videos directly from the terminal. This update expands the CLI's multimodal capabilities, offering a command-line interface for creating video content using an initial image and a text prompt. It provides developers and AI agents with direct access to a high-performing video generation model for programmatic workflows.