MiniMax H3: An Open Model Breaking the Boundaries Between Tasks and Modalities

MiniMax released MiniMax H3, an open-weights model that ranks #1 for video editing with audio and #2 for text-to-video with audio on Artificial Analysis's video leaderboard, offering commercial-grade generation and cost efficiency. The model's parameter count and weight availability were not disclosed in the announcement.

MiniMax H3: Omni-Reference, Commercial-Grade Generation, Unbeatable Cost Efficiency, Open Weights - As I said, MiniMax-H3 is Open 1 Video Editing With Audio 2 Text to Video With Audio 2 Image to Video No Audio artificialanalysis.ai/video/leaderbo… https://artificialanalysis.ai/video/leaderboard/text-to-video - Are the weights already out? Couldn’t find any links in the article - please tell us how many parameters this model has, i just want to know if i need a supercomputer or not Join the conversation