Today for AI
HOT RADAR
llmHEAT 26.2°

AI CURATED HOT STORY · 10/30/2026

Utopai X Ranks #2 on AA-Video-I2V v2.1 via MiniMax H3 Fine-tuning

1 reports archived1 independent sourcesupdated 10/30/2026, 10:13:45
Synthesis & Latest Updates
1 Sources Cross-Validated

Utopai Studios' video model Utopai X ranks #2 on the Artificial Analysis Image-to-Video (I2V) v2.1 benchmark, trailing only Dreamina Seedance 2.5. Post-trained on MiniMax H3, it is the only model in the top 2 for both Text-to-Video and I2V categories, excelling in physics simulation and multi-scene narratives. Access is currently restricted to the PAI platform with no public API.

LATEST/Utopai Studios' video model Utopai X ranks #2 on the Artificial Analysis Image-to-Video (I2V) v2.1 benchmark, trailing only Dreamina Seedance 2.5. Post-trained on MiniMax H3, it is the only model in the top 2 for both Text-to-Video and I2V categories, excelling in physics simulation and multi-scene narratives. Access is currently restricted to the PAI platform with no public API.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. Artificial Analysis (@ArtificialAnlys)T1·68 pts

    Utopai X Ranks #2 on AA-Video-I2V v2.1 via MiniMax H3 Fine-tuning

    • Utopai X, post-trained on MiniMax H3, ranks #2 on AA-Video-I2V v2.1, surpassing the native MiniMax H3 and other derivatives.
    • It is the only model in the top 2 that appears on both Text-to-Video (T2V) and Image-to-Video (I2V) leaderboards.
    • The model performs best on prompts testing physics, multi-scene narratives, and UI/UX design use cases.
    • Currently available only via the PAI platform on a credit-based system (93 credits/sec @1080p), with no public API.