The Aggregate - Personal Style Imitation (53 Texts): leaderboard
The Aggregate runs this evaluation itself. The site's author chose 53 of their longest English messages (chat replies, Discord posts and prompts typed to AI assistants), each reviewed as entirely their own words, and a separate model rewrote each one in plain, neutral English with the same content. Each model sees 30 other messages by the author as style samples and one neutral draft at a time, at its highest reasoning effort, and rewrites the draft so that it reads as if the author wrote it. A classifier trained on the author's other writing, against other people's ChatGPT prompts and chat messages and against GPT- and Claude-written text, gives the probability that the author wrote each rewrite; it sees function words, punctuation, capitalisation and word shapes, not topics. A rewrite that changes the meaning scores 0. The score is the mean probability as a percentage; the author's own held-out messages and the unchanged drafts, scored the same way, are shown as reference rows. One author and 53 messages: close scores do not establish an ordering.
Metric: Style match (%). Source: theaggregate.ai. Source: theaggregate.ai. Saturation forecast: Around October 2027. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 (Max) | 76.7 | #10 (Claude Fable 5.1) |
| 2 | GPT-6 Astra (Max) | 75.1 | #6 (GPT-6 Astra) |
| 3 | Claude Opus 5.5 (Max) | 73.7 | #3 (Claude Opus 5.5) |
| 4 | GPT-6.1 Sol (Max) | 72.5 | #7 (GPT-6.1 Sol) |
| 5 | GPT-6.1 Terra (Max) | 68.1 | #15 (GPT-6.1 Terra) |
| 6 | Claude Sonnet 5.5 (Max) | 67.4 | #14 (Claude Sonnet 5.5) |
| 7 | Gemini 4 Argon (High) | 66.2 | #9 (Gemini 4 Argon) |
| 8 | Muse Wonder (Max) | 64.9 | #18 (Muse Wonder) |
| 9 | Kimi K3.1 Pro (Max) | 63.1 | #17 (Kimi K3.1 Pro) |
| 10 | Grok 4.7 (xHigh) | 57.5 | #26 (Grok 4.7) |
| 11 | DeepSeek V4.1 Flash (1017) (Max) | 53.2 | #27 (DeepSeek V4.1 Flash (1017)) |
Method and evidence
Run by The Aggregate · Nov 4, 2026
Read method and notes
The site's author chose 53 of their longest English messages, 74 to 211 words each: chat replies, Discord posts and prompts typed to AI assistants between 2023 and 2026, every one reviewed by the author as entirely their own words. A separate model rewrote each one in plain, neutral English with the same content, and a second check dropped any draft that changed the meaning.
Each model sees 30 other messages by the author as samples of the style, then one neutral draft at a time, and is asked to rewrite it so that it reads as if the author wrote it, keeping the meaning. One request per model and message, at the highest reasoning effort each model supports, with a 32,768-token output cap including reasoning and no tools.
A classifier trained on the author's other English writing, against other people's ChatGPT prompts and chat messages and against GPT- and Claude-written text, gives the probability that the author wrote each rewrite. It sees function words, punctuation, capitalisation and word shapes, not topics. A rewrite that changes the meaning, answers the message or refuses scores 0. The score is the mean probability as a percentage; only models answering at least 90% of the messages are ranked.
The messages, the drafts and every rewrite are private; this page publishes the method and the scores.
- The author's own messages: 79.0%
- The neutral drafts, unchanged: 46.0%
- Two reference rows bound the scale: the author's own held-out messages, scored by the same classifier, and the neutral drafts left unchanged. A model that fully took on the author's voice would score near the first; one that only tidied the draft, near the second.
- One author's informal English: the board measures imitation of one person from 30 samples, not writing quality or style in general. Close scores do not establish an ordering.
Interactive version: theaggregate.ai/benchmark?slug=the-aggregate-personal-style-imitation-53-texts · How It Works · Data refreshed daily, snapshot 2026-11-05.