MiniMax H3 open-weight omni-modal model tops video benchmarks

MiniMax released H3, a 33B-parameter open-weight omni-modal model handling text, image, video, and audio, 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, and SOTA in both Arena and Artificial Analysis benchmarks.
How this story unfolded
4 weeks · 6 reports · 107 community posts · 113 of 125 shown
- Jul 31
- Aug 1
- Aug 2
- Aug 3
- Aug 4
- Aug 5
- Aug 6
- Aug 7
- Aug 8
- Aug 10
- Aug 11
- Aug 13
- Aug 14
- Aug 21
- Aug 22
- Aug 23
- Aug 24
- Aug 25
- Aug 26
- Aug 27
- Aug 28
MiniMax by email
Get an email when MiniMax has news
No news that day, no email.
More stories today
- Uber builds uReview, a multi-agent code review engine
- Mistral shows how to build HTML5 games with agents
- YouTube restricts views of AI music, Suno users report
- Defining an AI Kill Switch Is Hard, But Necessary
- AI-driven hiring freeze leaves job seekers rejected