HeyGen Video 1 tops Artificial Analysis text-to-video blind test at $2.40/min
toolstelegraph · x · 2026-10-24
HeyGen says its first general-purpose video model, HeyGen Video 1, ranked #1 in Artificial Analysis's blind text-to-video arena (Elo 1160, later shown as 1144 in a quality-vs-price chart).
- The scatter plot shows Wan 3.0 (1134, $12/min) costs 5x as much and Dreamina Seedance 2.5 (1104, $34.12/min) costs 14.2x, while MiniMax H3 (1120, $4.80/min) costs 2x.
- At $2.40/min, HeyGen claims "no model scores higher, at any price."
- The AA-Video-T2V v2.1 leaderboard is based on Elo from pairwise human preference votes for video with audio; 9 models were added in the last 30 days.
Related event: HeyGen's First General Video Model Tops Text-to-Video Blind Test(3 posts)→
More from Models
- Blogger clarifies review wasn't paid: new model still falls short of Opus 5.5, weak rate limits — Angaisb_ · 2026-10-24
- NVIDIA ships Nemotron 3.5 Bolt E4B, a 4GB open model for robots and on-device agents — AIFlow_ML · 2026-10-24
- Meta releases Muse Spark Open, an 816B-parameter MoE model with 1M-token context — dl_weekly · 2026-10-24
- Users find OpenAI products harder to recommend as everyday tasks falter — mark_k · 2026-10-24
- ByteDance training-sabotage engineer breaks silence: months of debugging 'purgatory' — teortaxesTex · 2026-10-24
- Codex users report recurring 'model at capacity' errors breaking overnight agent runs — CtrlAltDwayne · 2026-10-24