HeyGen Avatar 6: 84.4% Turing-Test Pass, Beats Seedance and Wan in Blind Tests
HeyGen · x · 2026-11-21
HeyGen's Avatar 6 technical report: talking avatars generated from a single photo (optionally a voice recording as identity reference), native 2K (2880×1620), unlimited duration (25–28 min continuous generations shown), and motion-prompt control. In evaluations it ranks #1 among 9 commercial avatar products on all 6 criteria, passes a side-by-side Turing test 84.4% of the time, and in blind tests the real people themselves preferred it over Seedance 2.5 (86.5%) and Wan 3.0 (87.9%).
More from Multimodal
- NVIDIA ships Alpamayo 2 Edge, a 2B-parameter in-vehicle reasoning VLA model — NVIDIAAI · 2026-11-21
- Creator shows HeyGen-powered video edit: 'editing to another level' — aziz4ai · 2026-11-21
- AI-built oil painting engine: 2,300 commits in 8 days as Claude Code runs a 'studio' of sessions — FotoRe_store · 2026-11-21
- "AGI Before GTA6": AI-Generated Music Video Riffs on 13-Year GTA VI Wait — Yamapama · 2026-11-21
- Meta's AVTR adds visual imagination to multimodal reasoning, +4.5 pts across 16 benchmarks — liuzhuang1234 · 2026-11-21
- Genie 4 world model live on Comfy playground, early testers impressed — EnvironmentalDay7419 · 2026-11-21