BREAKING: Seedance 2.5 by @BytePlusGlobal ranks 1st in Multi-Image to Video on Design Arena with an Elo of 1400. Open-weight MiniMax H3 by @MiniMax_AI takes 2nd with an Elo of 1355, the top open source video model. Unlike standard image-to-video, this leaderboard gives models multiple reference images and compares their final video outputs. This tests how well models combine different visual inputs while preserving subjects, styles, and scene continuity - a critical capability for controlled video creation. Congratulations to both teams!

BREAKING: Seedance 2.5 by @BytePlusGlobal places 4th overall on Video Arena with an Elo of 1302. It is now ByteDance’s highest-ranked video model, with four Seedance models placing in the top 10. Congratulations to the team on the release!

We're launching our 3rd Availability Zone in the BytePlus Hong Kong region on Aug 24! The new 3AZ architecture brings greater storage capacity, and multi-AZ deployment with intra-city disaster recovery — keeping mission-critical workloads always-on for industry customers, especially banking, insurance, public utilities, and more. AI cloud native infrastructure provider, built for the agent era.

Ryan Ng is speaking at Money Frontier 2026. Ryan Ng is BytePlus @BytePlusGlobal Hong Kong AI Ecosystem Hong Kong AI Ecosystem Lead, focusing on AI ecosystem development and partner collaboration in Hong Kong. Join him at Money Frontier 2026. Get your tickets and learn more:

Last chance to join live — The Future of AI-Native Video Production with the AZ8 Co-Founder and 2xLabs Creative Director starts in minutes! This is your chance to hear directly from AZ8, 2xLabs, and BytePlus on how AI video is being used in real creative workflows — from platform-level creation to creator practice and hands-on demo insights. August 13 11:00 BST | 12:00 CEST | 18:00 BJT Watch live:

When customer feedback arrives at scale, the challenge is getting each message to the right team quickly. Powered by BytePlus ModelArk, @PT_Transjakarta's TARA categorizes incoming feedback and routes reports to relevant field teams, helping cut response times from around one hour to one minute. Hear more from Mr. Raditya Maulana Rusdi, Director of Information Technology Systems and Services on how TARA supports TransJakarta’s customer service operations.

Before production begins, what if you could explore multiple creative directions in minutes? James Liu, Senior Solution Architect at BytePlus, shares how Seedance 2.5 is helping enterprises accelerate video creation through rapid prototyping, creative variations, localization, and practical AI workflows. Watch the full episode to see how AI video is reshaping enterprise content creation.

BREAKING: MiniMax H3 by @MiniMax_AI is 1st across 3 Video categories (Multi-Image to Video, Image to Video, and Video Editing) on Design Arena. MiniMax H3’s performance in Video Arena puts it ahead of other top performing models like Seedance 2.0 by @BytePlusGlobal, Grok Imagine Video 1.5 Preview by @SpaceXAI, and Gemini Omni Flash by @GoogleDeepMind. This marks another category to be led by open-weight models, following Kimi K3’s first place in our coding categories. Congratulations to the @MiniMax_AI team for establishing a new SOTA in video generation!

MiniMax H3 by @MiniMax_AI is 2nd overall on Video Arena with an Elo of 1325. This is a 209 Elo increase from @MiniMax_AI’s previous video model, MiniMax Hailuo-2.3 (Pro), putting them behind Gemini Omni Flash by @GoogleDeepMind and ahead of Seedance 2.0 Mini by @BytePlusGlobal. With this performance, they establish themselves as the 2nd video lab overall. Among open weights, the model is 1st overall, ahead of LTX 2.3 by @Lightricks and Kandinsky 5.0 Pro by AI-Forever. By a substantial gap, MiniMax has set a new SOTA on open weight video generation. Congratulations to the @MiniMax_AI team on the achievement!

BREAKING: ImagineArt 2.0 Edit by @ImagineArt_X is 15th overall on Image Editing Arena with an Elo of 1182. It is in the same performance band as Seedream 4.5 Edit by @BytePlusGlobal and UNI-1.1 Max by @LumaLabsAI. ImagineArt 2.0 Edit places @ImagineArt_X among the top 8 labs overall for image editing models. Congratulations to the @ImagineArt_X team on the accomplishment!