Claude Haiku 5.5

Anthropic, closed weights, released Oct 2026, run at provider defaults through OpenRouter, served by Anthropic. It built the same five pages as every model on season 0.6.1 of the Rams Index, and Rams graded each one at desktop and phone size.

Rams Index, 0 to 100

70.0

95% interval 64.4–73.7

Rank: 11of 26 models by Index; the paired intervals allow 7 to 13
Cost per page: $0.006Generation only, list price on run day
Earlier judges: 73.8Under the grade sum this board used until 10/28, GPT-5.6 Terra placed it 22th of 26 and the Claude judge 23th.
Grade sum: 25.27Seven 1–5 grades, out of 35
Pages judged: 1010 judge passes, 2 builds per brief
Defects per page: 3.1Tap targets under 24px on the phone (7 of 10)

Rank 11 of 26; the data allows anywhere from 7 to 13. Within noise of GLM 5.3, Claude Sonnet 5.5, Mistral Large 4, GPT-6 Luna, GPT-5.6 Sol and Kimi K3: the gap to each sits inside the noise, so the board can't order them yet. Clearly behind GPT-6.1 Sol, GPT-6 Astra, Grok 4.7, Claude Fable 5.1, GPT-6.1 Terra and Claude Opus 5.5. Clearly ahead of Claude Fable 5, Kimi K3.1 Pro, GLM 5.3 Prime, DeepSeek V4 Pro, Claude Opus 4.8, MiMo V2.6 Pro, Gemini 4 Argon, Gemini 3.8 Flash, MiniMax M3, Qwen 3.8 Max, Qwen 3.8 Max Prime, Muse Spark Open and Muse Wonder.

Checked against one designer · 63% agreementSeason 0.6.1New 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 26 models.

Hierarchy3.3522 of 26
Typography3.2522 of 26
Spacing3.1021 of 26
Color3.3519 of 26
Components3.3025 of 26
Composure3.3520 of 26
Craft3.3022 of 26

Bars start at 2.8 and end at 4.6, 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 26.

Landing30.916 of 26
Dashboard96.81 of 26
Settings70.112 of 26
Pricing29.519 of 26
Article83.95 of 26

Bars run from 0 to 100.

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: 52sMedian over every build, broken ones included
Output tokens: 11.3kMedian per page, reasoning included
Reasoning tokens: 0.7kMedian per page, as the API reports them
Broken pages: 0 of 10Every build came back as a whole page
Criticals: 0%0 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: Dashboard98.4
Index on this page, one judge pass. Brief mean 96.8.
- Right-column stat cards clipped mid-labelSerious
- Excessive dead space below episode tableModerate
- Redundant 'vs prior 30 days' repeated four times in stat cardsModerate
Worst: Landing13.7
Index on this page, one judge pass. Brief mean 30.9.
- Two-color gradient headline splits accent budget across two hues simultaneouslySerious
- Inconsistent time format between active row and completed rows in preview widgetSerious
- Headline span breaks across lines awkwardly, splitting gradient from anchor textSerious