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 · 14 reports · 122 community posts · 136 of 149 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
- Nvidia-backed Lambda raises $1B debt for chip deal
- Developer fatigue with AI-generated specs and plans
- Meta researchers train 8B model to match Claude Opus 4.5
- Decathlon scales demand forecasting with Chronos-2 on AWS
- Salesforce achieves Multi-AZ HA with SageMaker Inference Components