Utopai X, Post-Trained on MiniMax H3, Debuts at #2 on Artificial Analysis Text-to-Video Leaderboard
ArtificialAnlys · x · 2026-10-01
Utopai X, the new video model from AI-native studio Utopai Studios post-trained on MiniMax H3, debuts at #2 on Artificial Analysis' refreshed AA-Video-T2V v2.0 leaderboard, behind only Wan 3.0 and ahead of Dreamina Seedance 2.5. It is the highest-ranked MiniMax H3-based model, beating MiniMax H3 itself and fal's MiniMax H3 Max. It launches today inside Utopai's PAI storytelling platform at 93 credits per second of video (no public API); plans start at $15/month for 1,000 credits. Utopai has three theatrical films and two series slated for 2027.
Related event: AA Text-to-Video Leaderboard v2.0: Wan 3.0 Tops, Utopai X Debuts Second(3 posts)→
More from Multimodal
- Hand-editing 0.2% of weights plus 100 CPU-minutes turns an English TTS model into an 18MB Sanskrit one — kastnerkyle · 2026-11-16
- Zyphra open-sources textnorm tool, lifting TTS structured-data accuracy by up to 22 points — kastnerkyle · 2026-11-16
- Testing Qwen Image 2.1 and Minimax H3 on anime-to-photo conversion and film photo restoration — Ant_6431 · 2026-11-16
- Second take of a 'Cubee run' video generated with Minimax H3 — JahJedi · 2026-11-16
- Non-artist builds 14-chapter hand-painted storybook game with Fable 5.2 in 4 hours — jradoff · 2026-11-16
- Subject LoRAs on Minimax H3 Image learn poor likenesses while identical datasets excel on Qwen 2.1 — Ad_Organic · 2026-11-16