Claude Fable 5.1

Anthropic, closed weights, released Aug 2026, run at provider defaults through the Anthropic API. It built the same five pages as every model on season 0.5 of the Rams Index, and Rams graded each one at desktop and phone size.

Rams Index, 0 to 100

58.9

95% interval 52.0–65.9

Rank: 10of 14 models by Index; the paired intervals allow 5 to 13
Cost per page: $0.87Generation only, list price on run day
Second judge: 77.1GPT-5.6 Terra places it sixth of 14. The Claude judge: ninth.
Grade sum: 23.50Seven 1–5 grades, out of 35
Pages judged: 1010 judge passes, 2 builds per brief
Defects per page: 3.8Tap targets under 24px on the phone (10 of 10)

Rank 10 of 14; the data allows anywhere from 5 to 13. Within noise of Claude Sonnet 5.5, Gemini 4 Argon, Muse Wonder, Claude Opus 5.5, GPT-5.6 Sol, Claude Fable 5, Gemini 3.8 Flash and DeepSeek V4 Pro: the gap to each sits inside the noise, so the board can't order them yet. Clearly behind GPT-6 Astra, Grok 4.7, GPT-6.1 Sol and GPT-6 Luna. Clearly ahead of Claude Opus 4.8.

Designer check pending · read Nov 6Season 0.5Provisional: 1.0 judge passes per page, protocol 2

Grades by dimension

The seven grades behind the Index, 1 to 5, mean of desktop and phone. The tick is the mean across all 14 models.

Hierarchy3.459 of 14
Typography3.357 of 14
Spacing3.1011 of 14
Color3.358 of 14
Components3.3510 of 14
Composure3.506 of 14
Craft3.406 of 14

Bars start at 2.8 and end at 4.2, the range the board uses, so small differences show.

Index by brief

The same Index on each of the five briefs, and where the model places on that brief among all 14.

Landing67.95 of 14
Dashboard58.07 of 14
Settings50.98 of 14
Pricing50.010 of 14
Article67.911 of 14

Bars run from 40 to 90.

How it ran

Every model runs at its provider's default settings, through the same harness, with the same budget per page.

Effort: Default (always thinks)The provider’s default. We send no effort or thinking setting
Time per page: 180sMedian over every build, broken ones included
Output tokens: 17.3kMedian per page, reasoning included
Reasoning tokens: n/aIts API doesn’t report them separately
Broken pages: 0 of 10Every build came back as a whole page
Criticals: 30%3 of 10 scored pages had a critical issue in their first Rams code review
Built through: Anthropic APIServed by Anthropic

Best and worst page

Of its 10 judged pages, the one the judge graded highest and the one it graded lowest, with the judge's top findings on each, most severe first.

Best: Article71.4
Index on this page, one judge pass. Brief mean 67.9.
- Pull-quote lacks visual distinction from body text weightModerate
- Kicker and meta line share identical typographic weight/sizeModerate
- Brand lockup weight contrast is subtle to the point of near-invisibilityModerate
Worst: Dashboard50.0
Index on this page, one judge pass. Brief mean 58.0.
- Inconsistent card internal padding rhythmSerious
- Bar chart not drawn in brand geometry: library defaultsModerate
- Four stat cards carry equal visual weight: no primary metricModerate

All 10 of its pages sit beside every other model's in the gallery.

Head to head

Claude Fable 5.1 against every other model: the paired difference in Index points, and whether the 95% interval on it clears zero.

vs GPT-6 Astra-7.5Clearly behind
vs Grok 4.7-7.1Clearly behind
vs GPT-6.1 Sol-6.4Clearly behind
vs Claude Sonnet 5.5-2.9Inside the noise
vs GPT-6 Luna-2.9Clearly behind
vs Gemini 4 Argon-2.7Inside the noise
vs Muse Wonder-1.6Inside the noise
vs Claude Opus 5.5-1.4Inside the noise
vs GPT-5.6 Sol0.0Inside the noise
vs Claude Fable 5+1.3Inside the noise
vs Gemini 3.8 Flash+3.4Inside the noise
vs DeepSeek V4 Pro+4.3Inside the noise
vs Claude Opus 4.8+6.1Clearly better

The other models

Season 0.5 of the Rams Index, in board order, then the unranked.

Rams Index v0.5 · updated 2026-10-17Judged by Rams eyes · Claude Sonnet 4.6