MiniMax H3 Tops Video Editing Leaderboard, Open Weights Coming Soon
multimodalart · x · 2026-07-31
According to Artificial Analysis, the latest MiniMax video model, H3, ranks #1 in video editing and secures top 3 spots in both Text-to-Video and Image-to-Video.
The multimodal model accepts text, images, videos, and audio to generate 5-15s clips with native audio. MiniMax plans to release the model's weights under a community license, potentially making it the leading open-weight video model available.
Related event: MiniMax-H3 Tops Video Editing Leaderboard and Plans Open Source(6 posts)→
More from Models
- Kimi K3 Outperforms Claude Opus and Shows Superior Context Efficiency — casper_hansen_ · 2026-07-31
- More GB300s Online on LightningAI; Pangram 4 Hits 99% AI Text Detection Accuracy — LightningAI · 2026-07-31
- ChatGPT still cites old URL 2 weeks after redirect, search updated in 24h — lilyraynyc · 2026-07-31
- Specific Prompt Bypasses Guardrails to Unlock Claude Opus Base Model — paul_cal · 2026-07-31
- OpenAI Price Cuts and DeepSeek Update Expose Anthropic's Model Pricing Dilemma — kimmonismus · 2026-07-31
- DeepSeek-V4-Flash Runs at 400 tps for Just $10/hour on Inference Endpoints — ben_burtenshaw · 2026-07-31