MiniMax H3 open weights top Video Arena

MiniMax released H3, a 33B-parameter omni-modal model generating video with native stereo audio up to 2K and 15 seconds. It is now the #1 open model in Video Arena for text-to-video and image-to-video, tied for #3 overall.
How this story unfolded
4 weeks · 7 reports · 112 community posts · 119 of 128 shown
- Jul 31
- Aug 1
- Aug 2
- Aug 3
- Aug 4
- Aug 5
- Aug 6
- Aug 7
- Aug 10
- Aug 11
- Aug 13
- Aug 14
- Aug 21
- Aug 22
- Aug 23
- Aug 24
- Aug 25
- Aug 26
- Aug 27
- Aug 28
- Aug 29
MiniMax by email
Get an email when MiniMax has news
No news that day, no email.
More stories today
- Skeptic shares first impressions of ChatGPT Plus
- Hard sci-fi authors largely oppose LLMs, survey finds
- Anthropic tests folderless Claude Code sessions on Desktop and iOS
- Ethan Mollick: Using weaker AI for human-facing content may soon be disrespectful
- Pocket TTS training stack open-sourced