Utopai X, built on MiniMax H3, nears the top of Artificial Analysis text-to-video leaderboard
ArtificialAnlys · x · 2026-10-01
Artificial Analysis's updated AA-Video-T2V v2.0 text-to-video leaderboard (Elo from pairwise human preference votes) puts Utopai X (based on MiniMax H3) second at 1150 Elo, just behind Wan 3.0 (1157) and ahead of Dreamina Seedance 2.5 (1143) and MiniMax H3 768p (1138, $4.80/min).
By use case, Utopai X narrowly ranks first in Social Media & Creator Content and Architecture & Real Estate, second in Consumer. Other notables: FLUX 3 (1129), Gemini Omni Flash 1.1 (1120), grok-imagine-video-1.5 (1046); Kling 3.0 1080p (1000) anchors the scale. Utopai X has no API yet.
Related event: AA Text-to-Video Leaderboard v2.0: Wan 3.0 Tops, Utopai X Debuts Second(3 posts)→
More from Multimodal
- HeyGen Launches Its First General-Purpose Video Model at $0.01/s, Claiming to Beat Veo 3.1 — HeyGen · 2026-10-01
- ComfyUI launches Comfy API: deploy workflow JSONs as autoscaling endpoints — PurzBeats · 2026-10-01
- One prompt turns your photo library into a 60-second Ghibli-style AI short film via Hedra MCP — henloitsjoyce · 2026-10-01
- Runway launches Ads: autonomous performance-marketing engine claims 41% cheaper acquisition, $100M ARR — runwayml · 2026-10-01
- Full Talking Video From One Image in 30 Minutes for ~$5 — gorkem · 2026-10-01
- Ideogram 4.5 tested: natural-language image editing that keeps the style intact — gen_ericai · 2026-10-01