MiniMax-H3 Tops Video Editing Leaderboard, Ties for 2nd in Text-to-Video
bdsqlsz · x · 2026-07-31
MiniMax officially confirmed that its latest video model, MiniMax-H3, is open-source. According to the Artificial Analysis leaderboard, the model shows top-tier performance:
- Video Editing (With Audio): Ranked #1 globally.
- Text to Video (With Audio): Tied for #2 globally alongside Google Gemini Omni Flash.
It also secured the #2 spot in Image to Video (No Audio), demonstrating comprehensive capabilities.
Related event: MiniMax H3 Tops Video Editing Chart, Announces Open Weights(7 posts)→
More from Multimodal
- Tessellation-free geometric queries on displaced surfaces cut caustics variance 10x — ssh4net · 2026-10-16
- Complex multi-link CAD mechanism finally animates, dev celebrates the breakthrough — zetalyrae · 2026-10-16
- OpenMOSS releases MOSS-Image-SFT: Apache 2.0 text-to-image model on Hugging Face — bdsqlsz · 2026-10-16
- Hyperflow open-sourced: 49 sampling steps down to 8, ~3x faster video generation — mhdfaran · 2026-10-16
- Cinematic 3D fantasy character prompt template with salvaged-robot armor — azed_ai · 2026-10-16
- Midjourney vintage woodcut style: --sref 2446102396 beaver with a cleaver — michaelrabone · 2026-10-16