---
title: "HeyGen's Avatar 6 scored 84% on realism, but its 42.2% pick rate was below chance"
description: "Avatar 6 launched November 17, 2026, with an 84% realism figure and first place in a blind arena; the score doubles a below-chance pick rate, and the arena capped 97% of clips at 35 seconds. That is the evidence base under a company claiming $200 million of annual revenue."
publisher: "The Inference"
section: "Model"
published: 2026-11-18T18:20:06.405Z
modified: 2026-11-18T18:20:06.405Z
canonical: https://theinference.org/article/heygen-s-avatar-6-scored-84-on-realism-but-its-42-2-pick-rate-was-below-chance
language: en
keywords: "HeyGen, AI Video, Benchmarks, AI Models, Avatar"
---

# HeyGen's Avatar 6 scored 84% on realism, but its 42.2% pick rate was below chance

> Avatar 6 launched November 17, 2026, with an 84% realism figure and first place in a blind arena; the score doubles a below-chance pick rate, and the arena capped 97% of clips at 35 seconds. That is the evidence base under a company claiming $200 million of annual revenue.

## The 84 percent, taken apart

[HeyGen](https://theinference.org/markets/companies/heygen) launched Avatar 6 on November 17, 2026, an audio-driven avatar model that reads a script and times the gestures to the words [1]. The headline evidence: 84% of participants in a Turing-style test found the avatar as realistic as the person it represents [1]. Chief executive Joshua Xu sells trust, and names the stake: "People decide in seconds whether a video feels like a person talking to them, and when it doesn't, they stop listening" [1].

## Of 270 side-by-side answers, 42.2% picked the avatar

The [technical report](https://www.unite.ai/heygen-launches-avatar-6-with-script-aware-gestures-and-2k-video/) published the same day scores indistinguishability at 84.4% and shows the arithmetic underneath: outside raters chose Avatar 6 as the real recording in 42.2% of 270 side-by-side answers, below the 50% a coin flip delivers, and the headline score doubles that share [2]. A separate single-clip test had 65.1% of answers calling Avatar 6 real, against 78.9% for genuine recordings [2]. Doubling a below-chance pick rate does not move it above chance.

*Chart: **Raters judged the real person real more often than the avatar** Bar chart of shares of answers judging a clip real: genuine recording 78.9%, Avatar 6 with its own voice 65.1%, Avatar 6 in side-by-side testing 42.2%, against a 50% coin-flip line.*

*Share of answers judging a clip real in HeyGen's external-rater tests, November 2026. The report's 84.4% indistinguishability headline doubles the 42.2% head-to-head pick rate. Source: HeyGen technical report via Unite.AI [2]. [2]*

## First place, measured on half-minute clips

The independent evidence is real but short. [New Measure](https://newmeasure.ai/avatar-arena)'s Avatar Arena, blind votes across eight avatar providers from October 27 to November 16, ranks Avatar 6 first in both categories, Elo 1,197 for personal avatars and 1,237 for stock presenters against a 1,000 average [3].

The same [results page](https://newmeasure.ai/avatar-arena) draws its own fence: the typical script ran 62 words, 97% of comparisons had both videos at 35 seconds or shorter, and the round cannot say which provider wins a two-minute explanation, let alone a long lesson [3]. HeyGen's demonstrations run 25 to 28 minutes [2]. Renders typically took about three minutes against roughly one for Runway's GWM-1 avatars, and one in ten HeyGen videos ran past 9.5 minutes [3]. Even the runner-up ran partly on HeyGen: Creatify's personal-avatar voice used HeyGen's voice clone [3].

## The number that survives, on HeyGen's own metric

One result holds up on any reading: HeyGen's editor regenerates only the edited span, changing 34.4% of frames on average across 20 edits, while MiniMax's H3-max, [Alibaba](https://theinference.org/markets/companies/alibaba)'s Wan 3.0, [ByteDance](https://theinference.org/markets/companies/bytedance)'s Seedance 2.5 and HappyHorse Edit rewrote 99.7% to 100%, the whole take [2]. Against general video models the edge narrows: 50.1% versus Wan 3.0 from a photo, a tie by HeyGen's own label, 54.9% versus Kuaishou's Kling 4.0 and 72.4% versus Seedance 2.5 [2].

*Chart: **HeyGen's editor rewrites a third of the frames; four rivals rewrite nearly all** Bar chart of share of frames rewritten after 20 edits: MiniMax H3-max 100%, Alibaba Wan 3.0 100%, HappyHorse Edit 100%, ByteDance Seedance 2.5 99.7%, HeyGen Avatar 6 editor 34.4%.*

*Share of frames rewritten after 20 edits, HeyGen's own external-rater test, November 2026. HeyGen's editor regenerates only the edited span; the four competitors rewrote 99.7% to 100% of the take. Source: HeyGen technical report via Unite.AI [2]. [2]*

*Chart: **Against general video models, Avatar 6's edge runs from a tie to 72%** Column chart of Avatar 6 head-to-head preference shares among raters with a preference: 72.4% versus Seedance 2.5, 54.9% versus Kling 4.0, 50.1% versus Wan 3.0, against an even-split line at 50%.*

*Share of head-to-head answers won by Avatar 6 among raters expressing a preference, HeyGen's own external-rater tests, November 2026. Wan 3.0 compared from a photo; Kling 4.0 and Seedance 2.5 from footage. Source: HeyGen technical report via Unite.AI [2]. [2]*

## The private mark, and the listed labs it benchmarks

HeyGen is private, last priced at $500 million in June 2024 on $35 million of annual recurring revenue, and says it passed $200 million in June 2026, doubled in eight months, an unaudited run rate [1] [4].

Public money sits in its comparison table: MiniMax, which floated in Hong Kong in January and opened H3's weights within days of release, is now graded on an edit metric written by a company that shipped on ByteDance's Seedance 2.0 in April and now [sells its own avatar, video and voice stack](https://theinference.org/article/heygen-gives-its-voice-model-away-free-charges-99-a-month-to-clone-yours-elevenlabs-valued-at-22-billion) [5] [6]. The consent story has a seam, too: [the release requires explicit consent for realistic videos of real people](https://www.prnewswire.com/news-releases/heygen-introduces-avatar-6-an-audio-driven-context-aware-ai-model-that-alleviates-repetitive-or-unnatural-motion-in-ai-generated-video-302942527.html), while the [API documentation](https://developers.heygen.com/docs/models/avatar-6) restricts realistic video references to enterprises and lets some contracts skip the consent step [1] [7].

## Watch the long-form round

The open question is duration. Until a long-form round of the arena runs, a product demonstrated at 28 minutes is being marked on evidence gathered 35 seconds at a time [3].

## Takeaway

HeyGen's headline 84% realism score is double a 42.2% head-to-head pick rate that falls below a coin flip, and the blind arena that ranks Avatar 6 first tested clips of 35 seconds or less.

## Sources

1. [PR Newswire, HeyGen Introduces Avatar 6, an Audio-Driven, Context-Aware AI Model, 17 November 2026](https://www.prnewswire.com/news-releases/heygen-introduces-avatar-6-an-audio-driven-context-aware-ai-model-that-alleviates-repetitive-or-unnatural-motion-in-ai-generated-video-302942527.html)
2. [Unite.AI, HeyGen Launches Avatar 6 with Script-Aware Gestures and 2K Video, 17 November 2026](https://www.unite.ai/heygen-launches-avatar-6-with-script-aware-gestures-and-2k-video/)
3. [New Measure, Which AI avatar do creators prefer? Avatar Arena results, 18 November 2026](https://newmeasure.ai/avatar-arena)
4. [The Inference, HeyGen gives its voice model away free, charges $99 a month to clone yours; ElevenLabs valued at $22 billion, 10 October 2026](https://theinference.org/article/heygen-gives-its-voice-model-away-free-charges-99-a-month-to-clone-yours-elevenlabs-valued-at-22-billion)
5. [Reuters via Yahoo Finance, China's MiniMax releases H3 video model, 31 July 2026](https://finance.yahoo.com/news/chinas-minimax-releases-h3-video-044250156.html)
6. [HeyGen Blog, product index including Introducing Seedance 2.0 x HeyGen (7 April 2026) and the in-house model lineup, fetched 18 November 2026](https://www.heygen.com/blog)
7. [HeyGen Documentation, Avatar 6 (API reference media and consent tiers), fetched 18 November 2026](https://developers.heygen.com/docs/models/avatar-6)


---

HeyGen's Avatar 6 scored 84% on realism, but its 42.2% pick rate was below chance — The Inference. Canonical: https://theinference.org/article/heygen-s-avatar-6-scored-84-on-realism-but-its-42-2-pick-rate-was-below-chance
