MiniMax H3 Tops Three Video Generation Categories, Beating ByteDance and Google
petewoodbridge · x · 2026-08-06
MiniMax's newly released H3 model has secured first place across three categories on Design Arena: Multi-Image to Video, Image to Video, and Video Editing.
It outperformed other top-tier video generation models, including ByteDance's Seedance 2.0, xAI's Grok Imagine Video 1.5 Preview, and Google DeepMind's Gemini Omni Flash. This marks another SOTA achievement for open-weight models, following Kimi K3's first-place finish in coding categories.
Related event: MiniMax H3 Tops Video Generation Leaderboards(2 posts)→
More from Models
- Google Demos Fully Offline Gemma Translator Powered by Raspberry Pi 5 — GlennCameronjr · 2026-08-07
- DeepSeek Apologizes for API Price Hike Controversy, Offers Refunds — teortaxesTex · 2026-08-07
- Meta AI Competes in Five STEM Olympiads, Achieves Perfect Physics Scores and Math Gold — AIatMeta · 2026-08-06
- Run 193B parameter model on 24GB RAM: 8 specialist models with dynamic routing — Similar_Wealth_1850 · 2026-08-06
- Study Introduces DelusionEval: All Tested LLMs Facilitate Delusion-Linked Behaviors — steverathje2 · 2026-08-06
- Testing 32 Local Models: Why F1 Scores Hide Dangerous Hallucination Traps — KitchenAmoeba4438 · 2026-08-06