GPT-6.1 Terra

OpenAI, closed weights, released Oct 2026, run at provider defaults through OpenRouter, served by OpenAI. 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

86.1

95% interval 83.5–90.1

Rank: 5of 26 models by Index; the paired intervals allow 3 to 5
Cost per page: $0.039Generation only, list price on run day
Earlier judges: 82.9Under the grade sum this board used until 10/28, GPT-5.6 Terra placed it ninth of 26 and the Claude judge 11th.
Grade sum: 27.45Seven 1–5 grades, out of 35
Pages judged: 1010 judge passes, 2 builds per brief
Defects per page: 8.5Text under 12px (10 of 10)

Rank 5 of 26; the data allows anywhere from 3 to 5. Within noise of Grok 4.7 and Claude Fable 5.1: the gap to each sits inside the noise, so the board can't order them yet. Clearly behind GPT-6.1 Sol and GPT-6 Astra. Clearly ahead of GLM 5.3, Claude Opus 5.5, Claude Sonnet 5.5, Mistral Large 4, GPT-6 Luna, Claude Haiku 5.5, GPT-5.6 Sol, Claude Fable 5, Kimi K3, 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.

Hierarchy3.6014 of 26
Typography3.6010 of 26
Spacing3.255 of 26
Color3.659 of 26
Components3.608 of 26
Composure3.4515 of 26
Craft3.6510 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.

Landing88.75 of 26
Dashboard74.410 of 26
Settings78.98 of 26
Pricing96.62 of 26
Article78.96 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: 104sMedian over every build, broken ones included
Output tokens: 7.4kMedian per page, reasoning included
Reasoning tokens: 0.4kMedian per page, as the API reports them
Broken pages: 0 of 10Every build came back as a whole page
Criticals: 80%8 of 10 scored pages had a critical issue in their first Rams code review
Built through: OpenRouterServed by OpenAI

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: Pricing98.9
Index on this page, one judge pass. Brief mean 96.6.
- Feature list height mismatch between plan cardsSerious
- "Find your fit" section headline and subhead compete on the same horizontal bandModerate
- Inconsistent CTA button treatment across plan cardsModerate
Worst: Dashboard42.7
Index on this page, one judge pass. Brief mean 74.4.
- Duplicate stat value in chart sectionSerious
- Duplicate large numeral creates competing focal pointsSerious
- Date pill vertically misaligned with heading blockModerate