According to the SuperCLUE I2V Image-to-Video Model Overall Ranking, MiniMax H3 from MiniMax (Xiru Technology) secured the top spot in China with a total score of 71.46, including an application capability score of 75.82 (the highest on the list) and a foundational capability score of 67.10. Alibaba's Wan 3.0 ranked second domestically with a total score of 66.63, featuring a foundational capability score of 68.51 (slightly higher than MiniMax H3) but an application capability score of 64.75. ByteDance's Seedance 2.5 and Kuaishou's Kling V3 Pro tied for third place domestically, while Aishi Technology's PixVerse V6 and Shengshu Technology's Vidu Q3 Pro tied for fourth. Overseas models such as Google Gemini Omni 1.1 Flash and X.AI Grok Imagine Video 1.5 were included only for comparison and were not officially ranked. Due to constraints like restrictions on real-person appearances, maximum generation duration, and content moderation, some models were unable to produce results for certain questions and were scored as 0, affecting their final scores. Currently, the overall performance of domestic AI video models is on par with their overseas counterparts, with several models surpassing them in individual metrics.