Utopai X, post-trained on MiniMax H3, takes #2 on Image-to-Video leaderboard
ArtificialAnlys · x · 2026-10-30
Artificial Analysis reports that Utopai X, a video model from Utopai Studios post-trained on MiniMax H3, ranks #2 on AA-Video-I2V v2.1 behind only Dreamina Seedance 2.5 — and is the only model in the top 2 of both the T2V and I2V leaderboards, outranking MiniMax H3 itself.
- Capabilities: leads Physics and Multi-Scene & Narrative; close to frontier on Audio Synchronization, Spatio-Temporal Consistency and Text Rendering; weakest at Dialogue & Lip Sync and Human Anatomy. Beats its MiniMax H3 (768p) base on 7 of 10 capabilities.
- Use cases: leads UI/UX & Motion Design and Productivity & Knowledge Work, narrowly leads Frontier and Retail & Ecommerce; trails most on Live-Action Film (-73).
- Availability: only inside Utopai's PAI platform at 93 credits per second of 1080p video, no public API; plans from $15/month for 1,000 credits.
More from Models
- DeepSeek V4.1 Flash tops open-model usage among research agents, index data shows — AkariAsai · 2026-10-30
- Dev claims Gemini Argon makes 'researcher-level jumps' other models miss as 'carbon' looms — vitaliychiley · 2026-10-30
- Meta's Alexandr Wang touts Muse: 6.7x more concise than ChatGPT at answering the same question — alexandr_wang · 2026-10-30
- OpenAI's subsidy shift rewrites the score-vs-cost Pareto frontier, analysis finds — RexDouglass · 2026-10-30
- Phonic tops VAmoS benchmark for agentic speech-to-speech models — graceisford · 2026-10-30
- DeepSeek Frontend Leaks cyber-v3/v4 Keys; Still Hiring Attackers as V4 Excels at Security — teortaxesTex · 2026-10-30