TGViewer
Artificial Intelligence Artificial Intelligence @machinelearning_deeplearning · 56.3K subscribers
Post #1730 5.27K
Kandinsky 5.0 Video Lite and Kandinsky 5.0 Video Pro generative models on the global text-to-video landscape

🔘Pro is currently the #1 open-source model worldwide
🔘Lite (2B parameters) outperforms Sora v1.
🔘Only Google (Veo 3.1, Veo 3), OpenAI (Sora 2), Alibaba (Wan 2.5), and KlingAI (Kling 2.5, 2.6) outperform Pro — these are objectively the strongest video generation models in production today. We are on par with Luma AI (Ray 3) and MiniMax (Hailuo 2.3): the maximum ELO gap is 3 points, with a 95% CI of ±21.

Useful links
🔘Full leaderboard: LM Arena
🔘Kandinsky 5.0 details: technical report
🔘Open-source Kandinsky 5.0: GitHub and Hugging Face
  • ❤ 2
Open in Telegram All posts from @machinelearning_deeplearning
More from @machinelearning_deeplearning
  1. Sep 22, 2026🚀 Welcome back to our AI Engineer Roadmap! ❤️ In the previous posts, we learned about fun…
  2. Sep 21, 2026🚀 Welcome back to our AI Engineer Roadmap! ❤️ In the previous post, we explored functions…
  3. Sep 20, 2026In the previous post, we learned how conditional statements allow Python programs to make…
  4. Sep 19, 2026In the previous post, we explored Python operators and even tested ourselves with some tri…
  5. Sep 18, 2026In the previous post, we learned how to convert one data type into another using Type Cast…
  6. Sep 17, 2026In the previous post, we learned how to take input from users and display output. One impo…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →