SuperCLUE I2V Image-to-Video Leaderboard: MiniMax H3 Tops Domestic Rankings with 71.46 Points
In the overall I2V image-to-video model leaderboard updated by SuperCLUE on October 23, MiniMax's H3 ranked first domestically with a total score of 71.46, and its application capability score of 75.82 was the highest on the entire leaderboard. Alibaba's Wan 3.0 placed second with 66.63 points, with its foundational capability score of 68.51 overtaking MiniMax H3; ByteDance's Seedance 2.5 and Kuaishou's Kling V3 Pro tied for third with 64.63 and 64.06 points. Overseas models are included only for reference and are not ranked: Gemini Omni 1.1 Flash scored 67.38 and Grok Imagine Video 1.5 scored 65.79.
Body · AI translation
English text is being prepared.
This ranking was updated on October 23, and there is a key point in the rules: overseas models are used only for comparison and are not counted in the official ranking, and models whose score gap is within 1 point are counted as tied.
MiniMax H3 not only has a high total score; looking at its two sub-capabilities, it scored 67.10 in basic capability and shot straight up to 75.82 in application capability, the highest application capability score in the table.
Ranked second domestically is Alibaba's Wan 3.0, with a total score of 66.63. Its basic capability performance is strong, scoring 68.51, a bit higher than MiniMax H3, but its application capability held it back somewhat, at only 64.75.
Third place is a tie between two models: ByteDance's Seedance 2.5 scored 64.63, and Kuaishou's Kling V3 Pro got 64.06.
Further down, AiShi Technology's PixVerse V6 and Shengshu Technology's Vidu Q3 Pro tied for 4th place.
The ranking also includes several overseas models for reference: Google's Gemini Omni 1.1 Flash has a total score of 67.38, and X.AI's Grok Imagine Video 1.5 has a score of 65.79; neither is counted in the official ranking.
The notes at the end also make it clear that several models are subject to rule restrictions. For example, Seedance 2.5, Gemini Omni 1.1 Flash, and PixVerse V6 encounter constraints such as restrictions on real people appearing on camera, generation duration limits, and content moderation, so some questions cannot produce results normally and are directly counted as 0 points, which affects the final scores.
However, this is only a benchmark score; a high score does not mean the model works well in all scenarios. When actually creating content, everyone should still choose a suitable model according to their own needs.