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
64.2
95% interval 55.5–71.8
Rank
13of 26 models by Index; the paired intervals allow 7 to 16
Cost per page
$0.006Generation only, list price on run day
Tier
MiddleClearly behind at least one model
Pages judged
1010 judge passes, 2 builds per brief
Defects per page
3.1Tap targets under 24px on the phone (7 of 10)

Rank 13 of 26; the data allows anywhere from 7 to 16. Within noise of Mistral Large 4, GLM 5.3, Claude Sonnet 5.5, GPT-5.6 Sol, GPT-6 Luna, Kimi K3, Kimi K3.1 Pro, GLM 5.3 Prime and Claude Fable 5: the gap to each sits inside the noise, so the board can't order them yet. Clearly behind 6 models. Clearly ahead of 10 models.

Checked against one designer · 63% agreementSeason 0.6.1New this season

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.

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.

  • Dashboard page built by Claude Haiku 5.5, desktop, top of the page

    Best: Dashboard96.6

    Index on this page, one judge pass. Brief mean 96.1.

    • Right-column stat cards clipped mid-labelSerious
    • Excessive dead space below episode tableModerate
    • Redundant 'vs prior 30 days' repeated four times in stat cardsModerate
  • Landing page built by Claude Haiku 5.5, desktop, top of the page

    Worst: Landing5.8

    Index on this page, one judge pass. Brief mean 20.7.

    • 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

Head to head

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

The other models

Season 0.6.1 of the Rams Index, in board order.

Rams Index v0.6.1 · updated 2026-10-29Judged by Claude Opus 5.5, GPT-6.1 Sol and Gemini 4 Argon