Claude Sonnet 5.5

Anthropic, closed weights, released Sep 2026, run at provider defaults through OpenRouter, served by Anthropic. 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

61.8

95% interval 56.1–70.0

Rank: 4of 14 models by Index; the paired intervals allow 1 to 11
Cost per page: $0.14Generation only, list price on run day
Second judge: 74.5GPT-5.6 Terra places it ninth of 14. The Claude judge: fourth.
Grade sum: 24.30Seven 1–5 grades, out of 35
Pages judged: 1010 judge passes, 2 builds per brief
Defects per page: 2.6Content wider than the phone (8 of 10)

Rank 4 of 14; the data allows anywhere from 1 to 11. Within noise of GPT-6 Astra, Grok 4.7, GPT-6.1 Sol, GPT-6 Luna, Gemini 4 Argon, Muse Wonder, Claude Opus 5.5, GPT-5.6 Sol, Claude Fable 5.1 and Gemini 3.8 Flash: the gap to each sits inside the noise, so the board can't order them yet. Not clearly behind any model. Clearly ahead of Claude Fable 5, DeepSeek V4 Pro and Claude Opus 4.8.

Designer check pending · read Nov 6Season 0.5New this seasonProvisional: 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.

Hierarchy3.753 of 14
Typography3.405 of 14
Spacing3.204 of 14
Color3.358 of 14
Components3.555 of 14
Composure3.752 of 14
Craft3.3011 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.

Landing61.611 of 14
Dashboard57.18 of 14
Settings56.21 of 14
Pricing56.24 of 14
Article77.73 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: DefaultThe provider’s default. We send no effort or thinking setting
Time per page: 95sMedian over every build, broken ones included
Output tokens: 13.6kMedian per page, reasoning included
Reasoning tokens: 2.7kMedian per page, as the API reports them
Broken pages: 0 of 10Every build came back as a whole page
Criticals: 10%1 of 10 scored pages had a critical issue in their first Rams code review
Built through: OpenRouterServed 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: Article78.6
Index on this page, one judge pass. Brief mean 77.7.
- Excessive vertical gap before pullquote sectionModerate
- Pullquote attribution all-caps label slightly redundant with source contentModerate
- Kicker tag stacking with orphaned dotModerate
Worst: Dashboard53.6
Index on this page, one judge pass. Brief mean 57.1.
- Legend dot competes weakly as sole color signalModerate
- Stat-card labels use the same weight/size as body copy: no tonal differentiationModerate
- Large dead zone below the Recent Episodes tableModerate

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

Head to head

Claude Sonnet 5.5 against every other model: the paired difference in Index points, and whether the 95% interval on it clears zero.

vs GPT-6 Astra-4.6Inside the noise
vs Grok 4.7-4.3Inside the noise
vs GPT-6.1 Sol-3.6Inside the noise
vs GPT-6 Luna0.0Inside the noise
vs Gemini 4 Argon+0.2Inside the noise
vs Muse Wonder+1.2Inside the noise
vs Claude Opus 5.5+1.4Inside the noise
vs GPT-5.6 Sol+2.9Inside the noise
vs Claude Fable 5.1+2.9Inside the noise
vs Claude Fable 5+4.2Clearly better
vs Gemini 3.8 Flash+6.2Inside the noise
vs DeepSeek V4 Pro+7.1Clearly better
vs Claude Opus 4.8+8.9Clearly 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