Benchmark Almanac

The Aggregate Personal Style Imitation

Claude Fable 5.1 76.7% leads since November 2026
Not in model cards

Models rewrite 53 neutral drafts in one person's style using 30 other messages as examples. An authorship classifier scores each rewrite.

The maker ranks 18 models. Rewrites that change the meaning score zero. The author's original messages averaged 79% on the same classifier.

Released
November 2026
Kind
Creative writing
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Tasks
Kept private
Measures
Capability
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
18
Entries on its own leaderboard, 17 models we track

Claude Fable 5.1 leads with 76.7% Claude Fable 5.1 leads with 76.7%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

  1. 1 Claude Fable 5.1 max reasoning, 30 samples 76.7%
  2. 2 GPT-6 Astra Pro max reasoning, 30 samples 75.6%
  3. 3 GPT-6.2 Astra max reasoning, 30 samples 75.5%
  4. 4 GPT-6.1 Pro Sol max reasoning, 30 samples 75.4%
  5. 5 GPT-6 Astra max reasoning, 30 samples 75.1%
  6. 6 GPT-6.2 Sol max reasoning, 30 samples 75.1%
  7. 7 Claude Opus 5.5 max reasoning, 30 samples 73.7%
  8. 8 Claude Fable 5.2 max reasoning, 30 samples 73%
  9. 9 GPT-6.1 Sol max reasoning, 30 samples 72.5%
  10. 10 GPT-6.1 Terra max reasoning, 30 samples 68.1%
  11. 11 Claude Sonnet 5.5 max reasoning, 30 samples 67.4%
  12. 12 Gemini 4 Carbon high reasoning, 30 samples 67%
  13. 13 Gemini 4 Argon high reasoning, 30 samples 66.2%
  14. 14 Muse Wonder max reasoning, 30 samples 64.9%
  15. 15 Kimi K3.1 Pro max reasoning, 30 samples 63.1%
  16. 16 Gemini 4 Hydrogen high reasoning, 30 samples 61.3%
  17. 17 Grok 4.7 xhigh reasoning, 30 samples 57.5%
  18. 18 DeepSeek V4.1 Flash 1017 max reasoning, 30 samples 53.2%

Source: Official The Aggregate Personal Style Imitation leaderboard

#EntryScoreSettingReleasedRun onSource
1 Claude Fable 5.1 76.7% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
2 GPT-6 Astra Pro 75.6% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
3 GPT-6.2 Astra 75.5% max reasoning, 30 samples Nov 2026 Nov 2026 Official leaderboard
4 GPT-6.1 Pro Sol 75.4% max reasoning, 30 samples Nov 2026 Official leaderboard
5 GPT-6 Astra 75.1% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
6 GPT-6.2 Sol 75.1% max reasoning, 30 samples Nov 2026 Nov 2026 Official leaderboard
7 Claude Opus 5.5 73.7% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
8 Claude Fable 5.2 73% max reasoning, 30 samples Nov 2026 Nov 2026 Official leaderboard
9 GPT-6.1 Sol 72.5% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
10 GPT-6.1 Terra 68.1% max reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
11 Claude Sonnet 5.5 67.4% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
12 Gemini 4 Carbon 67% high reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
13 Gemini 4 Argon 66.2% high reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
14 Muse Wonder 64.9% max reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
15 Kimi K3.1 Pro 63.1% max reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
16 Gemini 4 Hydrogen 61.3% high reasoning, 30 samples Nov 2026 Nov 2026 Official leaderboard
17 Grok 4.7 57.5% xhigh reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
18 DeepSeek V4.1 Flash 1017 53.2% max reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 Claude Fable 5.1 76.7% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
2 GPT-6 Astra Pro 75.6% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
3 GPT-6.2 Astra 75.5% max reasoning, 30 samples Nov 2026 Nov 2026 Official leaderboard
4 GPT-6 Astra 75.1% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
5 GPT-6.2 Sol 75.1% max reasoning, 30 samples Nov 2026 Nov 2026 Official leaderboard
6 Claude Opus 5.5 73.7% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
7 Claude Fable 5.2 73% max reasoning, 30 samples Nov 2026 Nov 2026 Official leaderboard
8 GPT-6.1 Sol 72.5% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
9 GPT-6.1 Terra 68.1% max reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
10 Claude Sonnet 5.5 67.4% max reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
11 Gemini 4 Carbon 67% high reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
12 Gemini 4 Argon 66.2% high reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
13 Muse Wonder 64.9% max reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
14 Kimi K3.1 Pro 63.1% max reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard
15 Gemini 4 Hydrogen 61.3% high reasoning, 30 samples Nov 2026 Nov 2026 Official leaderboard
16 Grok 4.7 57.5% xhigh reasoning, 30 samples Sep 2026 Nov 2026 Official leaderboard
17 DeepSeek V4.1 Flash 1017 53.2% max reasoning, 30 samples Oct 2026 Nov 2026 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Own leaderboard 1 leader

Source: Official The Aggregate Personal Style Imitation leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Claude Fable 5.1 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Claude Fable 5.1

Source: Official The Aggregate Personal Style Imitation leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Writing and taste

All 65 in Writing and taste
  • Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
  • WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
  • Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing. MiniMax-Text-01 81.3%
  • DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate. DeepSeek-V4-Pro 62.6%
  • Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
  • Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right. Muse Spark 0.21

Data audit

All 11 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (18 entries).
  • Pass Models scored 17 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
  • Pass Frontier models 10 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Pass Headroom The best is 76.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on theaggregate.ai: 17 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check