---
title: Blueprint token benchmark
seoTitle: Blueprint token benchmark, measured November 20, 2026
description: How many tokens an agent writes for the same small UI as Brilliant Blueprint rows, as a Figma-style JSON node tree and as Figma plugin JavaScript. 6 public fixtures, measured November 20, 2026, with the script to re-run it.
section: developers
order: 3
featured: false
related: developers/blueprint, agents/limits, agents/overview
---

# Blueprint token benchmark

On 6 small UI fixtures, measured November 20, 2026, a Figma-style JSON node tree took a median of 3.61x the tokens of the same design as Blueprint rows (range 3.42x to 4.06x), and Figma plugin JavaScript a median of 4.43x (range 4.15x to 5.21x). Tokenizer: tiktoken 0.12.0, `o200k_base`. The script and every fixture are on this page, so you can check the numbers.

## What was measured?

The text an agent has to write to create one design, in three forms:

- **Blueprint rows.** The [Blueprint](/docs/developers/blueprint) an agent sends to Brilliant, one element per line.
- **A Figma-style JSON node tree.** Minified, holding only the fields the design needs: id, name, type, layout, size, fills, strokes, radius, effects and text style.
- **Figma plugin JavaScript.** A straight-line script that builds the same tree, one statement per property, with no helpers and no error handling.

Each count is the whole text of that form, in tokens.

## What are the results?

n = 6. tiktoken 0.12.0, `o200k_base`. Measured November 20, 2026.

| Fixture | Elements | Blueprint | Figma-style JSON | vs Blueprint | Plugin JavaScript | vs Blueprint |
|---|---|---|---|---|---|---|
| [Pricing card](/docs/bench/blueprint-tokens/fixtures/pricing_card.bl) | 21 | 426 | 1,567 | 3.68x | 2,008 | 4.71x |
| [Nav bar](/docs/bench/blueprint-tokens/fixtures/nav_bar.bl) | 13 | 245 | 995 | 4.06x | 1,276 | 5.21x |
| [Sign-in form](/docs/bench/blueprint-tokens/fixtures/sign_in_form.bl) | 21 | 505 | 1,728 | 3.42x | 2,191 | 4.34x |
| [Dashboard tile](/docs/bench/blueprint-tokens/fixtures/dashboard_tile.bl) | 17 | 395 | 1,434 | 3.63x | 1,787 | 4.52x |
| [Task list](/docs/bench/blueprint-tokens/fixtures/task_list.bl) | 22 | 564 | 2,024 | 3.59x | 2,427 | 4.30x |
| [Confirm modal](/docs/bench/blueprint-tokens/fixtures/confirm_modal.bl) | 13 | 382 | 1,330 | 3.48x | 1,585 | 4.15x |
| **Median** | | | | **3.61x** | | **4.43x** |

With `cl100k_base` as a cross-check the medians are 3.62x and 4.46x.

## What does one fixture look like?

The nav bar, 13 elements. As Blueprint, 245 tokens:

```blueprint title="nav_bar.bl"
al(h,x(sb),y(c),pad(16,32)) s(1200,hug) f[(#FFFFFF)] st[(#E5E7EB,w(1))] "Nav bar"
  al(h,y(c),g(8)) "Brand"
    c s(24,24) f[(#4F46E5)] "Mark"
    t("Acme",Inter,16,b) f[(#111827)]
  al(h,y(c),g(28)) "Links"
    t("Product",Inter,14,m) f[(#374151)]
    t("Pricing",Inter,14,m) f[(#374151)]
    t("Docs",Inter,14,m) f[(#374151)]
    t("Blog",Inter,14,m) f[(#374151)]
  al(h,y(c),g(12)) "Actions"
    t("Sign in",Inter,14,m) f[(#374151)]
    al(h,x(c),y(c),pad(8,14)) f[(#111827)] rd(8) "Button"
      t("Get started",Inter,14,sb) f[(#FFFFFF)]
```

The same nav bar as plugin JavaScript is 1,276 tokens. Its first 14 lines:

```text title="nav_bar.plugin.js, the first 14 lines"
await figma.loadFontAsync({"family":"Inter","style":"Bold"});
await figma.loadFontAsync({"family":"Inter","style":"Medium"});
await figma.loadFontAsync({"family":"Inter","style":"Semi Bold"});
const n1=figma.createFrame();
n1.name="Nav bar";
n1.layoutMode="HORIZONTAL";
n1.primaryAxisAlignItems="SPACE_BETWEEN";
n1.counterAxisAlignItems="CENTER";
n1.paddingTop=16;
n1.paddingRight=32;
n1.paddingBottom=16;
n1.paddingLeft=32;
n1.fills=[{"type":"SOLID","color":{"r":1,"g":1,"b":1}}];
n1.strokes=[{"type":"SOLID","color":{"r":0.898,"g":0.906,"b":0.922}}];
```

The full files: [nav_bar.figma.json](/docs/bench/blueprint-tokens/fixtures/nav_bar.figma.json) and [nav_bar.plugin.js](/docs/bench/blueprint-tokens/fixtures/nav_bar.plugin.js).

## What are the caveats?

- **We wrote the fixtures and the mapping.** The six designs are generated for this benchmark, and the JSON and JavaScript forms are produced from the Blueprint by the script. Read the mapping before you trust the numbers.
- **Six fixtures is a small sample.** They are a pricing card, a nav bar, a form, a dashboard tile, a list and a modal, each 13 to 22 elements. Larger or different designs can land elsewhere.
- **The Figma forms are minimal.** They hold only what the design needs. A node tree exported from a real Figma file carries more fields per node, and a production plugin script carries helpers and error handling. Neither is measured here.
- **Three fixtures use design tokens and three use literal values.** Both styles are in the table, so you can see each.
- **These are OpenAI tokenizers.** Other models count differently, so the ratios move a little per model.
- **This measures writing a design, nothing else.** It says nothing about HTML, about reading a design back, or about the quality of what an agent makes.

## How do I reproduce it?

Download the script and the `fixtures` folder, keep them side by side, and run it with Python 3 and `tiktoken`:

```text title="Re-run the benchmark"
pip install tiktoken
python3 bench.py
```

- [bench.py](/docs/bench/blueprint-tokens/bench.py): the script, with the mapping from Blueprint to both Figma forms.
- [results.json](/docs/bench/blueprint-tokens/results.json): every number on this page.
- Fixtures: Pricing card ([bl](/docs/bench/blueprint-tokens/fixtures/pricing_card.bl), [json](/docs/bench/blueprint-tokens/fixtures/pricing_card.figma.json), [js](/docs/bench/blueprint-tokens/fixtures/pricing_card.plugin.js)), Nav bar ([bl](/docs/bench/blueprint-tokens/fixtures/nav_bar.bl), [json](/docs/bench/blueprint-tokens/fixtures/nav_bar.figma.json), [js](/docs/bench/blueprint-tokens/fixtures/nav_bar.plugin.js)), Sign-in form ([bl](/docs/bench/blueprint-tokens/fixtures/sign_in_form.bl), [json](/docs/bench/blueprint-tokens/fixtures/sign_in_form.figma.json), [js](/docs/bench/blueprint-tokens/fixtures/sign_in_form.plugin.js)), Dashboard tile ([bl](/docs/bench/blueprint-tokens/fixtures/dashboard_tile.bl), [json](/docs/bench/blueprint-tokens/fixtures/dashboard_tile.figma.json), [js](/docs/bench/blueprint-tokens/fixtures/dashboard_tile.plugin.js)), Task list ([bl](/docs/bench/blueprint-tokens/fixtures/task_list.bl), [json](/docs/bench/blueprint-tokens/fixtures/task_list.figma.json), [js](/docs/bench/blueprint-tokens/fixtures/task_list.plugin.js)), Confirm modal ([bl](/docs/bench/blueprint-tokens/fixtures/confirm_modal.bl), [json](/docs/bench/blueprint-tokens/fixtures/confirm_modal.figma.json), [js](/docs/bench/blueprint-tokens/fixtures/confirm_modal.plugin.js)).

`python3 bench.py --check` fails if a generated fixture or `results.json` differs from what the script produces. Without `tiktoken` the script prints NOT MEASURED and no numbers.
