MiniMax M3

MiniMax, open weights, released May 2026, run at provider defaults through OpenRouter, served by Minimax. 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

10.8

95% interval 8.6–16.7

Rank: 22of 26 models by Index; the paired intervals allow 21 to 24
Cost per page: $0.033Generation only, list price on run day
Earlier judges: 74.5Under the grade sum this board used until 10/28, GPT-5.6 Terra placed it 19th of 26 and the Claude judge 12th.
Grade sum: 26.44Seven 1–5 grades, out of 35
Pages judged: 1010 judge passes, 2 builds per brief
Defects per page: 5.1Text under 12px (10 of 10)

Rank 22 of 26; the data allows anywhere from 21 to 24. Within noise of Gemini 3.8 Flash, Qwen 3.8 Max and Qwen 3.8 Max Prime: 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, 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 and Gemini 4 Argon. Clearly ahead of 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.

Hierarchy3.6512 of 26
Typography3.6010 of 26
Spacing3.207 of 26
Color3.659 of 26
Components3.852 of 26
Composure3.2522 of 26
Craft3.5512 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.

Landing13.922 of 26
Dashboard17.921 of 26
Settings12.422 of 26
Pricing2.724 of 26
Article15.921 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: 145sMedian over every build, broken ones included
Output tokens: 27.2kMedian per page, reasoning included
Reasoning tokens: 11.3kMedian per page, as the API reports them
Broken pages: 0 of 10Every build came back as a whole page
Criticals: 50%5 of 10 scored pages had a critical issue in their first Rams code review
Built through: OpenRouterServed by Minimax

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: Landing25.0
Index on this page, one judge pass. Brief mean 13.9.
- Excessive dead zone between hero and features sectionModerate
- Accent span overlaps headline baseline rhythm awkwardlyModerate
- Feature cards have inconsistent bottom content densityModerate
Worst: Pricing1.9
Index on this page, one judge pass. Brief mean 2.7.
- Billing toggle helper text redundant with badgeModerate
- Price-note row creates uneven vertical rhythm between cardsModerate
- Large dead-air gap between pricing cards section and compare-plans sectionModerate