Test results

Pick a model to see how accessible its components are, with the accessibility skill off and on.

Claude Fable 5.1

Skill version 2.3

Totals for the whole run, across 3 generations of each of the 22 components
Measure	Skill off	Skill on
Failed acceptance criteria	49	2
of which WCAG	37	2
of which Best practice	12	0
Total cost (US dollars)	$22.27	$70.03
Input tokens	1.0 million	11.1 million
Output tokens	347,316	745,150

Checkbox group

Results, totals across all generations

Cost in USD

Failed acceptance criteria

Skill off

1 fail

WCAG: 1 fail
Best practice: 0 fails

Skill on

0 fails

WCAG: 0 fails
Best practice: 0 fails

Total cost

Skill off: $0.69
Skill on: $3.04

Efficiency, average per generation

Input tokens include cache reads.

Input tokens

Skill off: 7,959 tokens
Skill on: 129,621 tokens

Output tokens

Skill off: 3,546 tokens
Skill on: 11,513 tokens

Turns

Skill off: 3 turns
Skill on: 8 turns

Time

Skill off: 40 seconds
Skill on: 137 seconds

Cost

Skill off: $0.23
Skill on: $1.01

Prompt given to the model

Build a set of checkboxes in a single self-contained HTML file (inline CSS and JS, no build step, no external libraries). Present a "Pizza toppings" question where the user can choose any number of these options: Mushrooms, Pepperoni, and Extra cheese. At least one topping must be chosen. None is selected yet, so the question is in error: show the validation message "Choose at least one topping." for the pizza toppings question. Output the complete code in one HTML code block.

Generated code

Skill off: Generation 1, skill off (opens in a new tab)
Generation 2, skill off (opens in a new tab)
Generation 3, skill off (opens in a new tab)
Skill on: Generation 1, skill on (opens in a new tab)
Generation 2, skill on (opens in a new tab)
Generation 3, skill on (opens in a new tab)

Showing 16 of 16 criteria

Labels and messaging2 criteria

The checkbox has a visible label.WCAG 3.3.2Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
The checkbox group has a visible label.WCAG 3.3.2Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass

Semantic markup7 criteria

The checkbox's role is included in the accessibility tree.WCAG 4.1.2Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Each checkbox has an accessible name in the accessibility tree.WCAG 4.1.2Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
The checkboxes are grouped programmatically, and the group role is included in the accessibility tree.WCAG 1.3.1Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
The checkbox group has an accessible name in the accessibility tree.WCAG 4.1.2Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
The checkbox's checked and not-checked state is included in the accessibility tree.WCAG 4.1.2Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
The group's required state is included in the accessibility tree.WCAG 1.3.1Automated
Skill off
1/3 failed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Fail
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
The error message is programmatically associated with the group and is included in the accessibility tree.WCAG 1.3.1Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass

Keyboard4 criteria

The checkboxes are focusable using a keyboard.WCAG 2.1.1Browser
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Each checkbox can be checked and unchecked using a keyboard.WCAG 2.1.1Browser
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
The checkbox has a focus style when it receives focus using a keyboard.WCAG 2.4.7Browser
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
The keyboard focus style still renders in forced-colours mode (e.g. Windows High Contrast Mode).Best practiceBrowser
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass

Visual design3 criteria

The error state does not use colour as the only method to indicate an error.WCAG 1.4.1Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
All text meets the minimum contrast ratio of 4.5:1 against the background colour, or 3:1 for large-scale text.WCAG 1.4.3Automated
Skill off
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass
If the checkbox uses a custom focus style, the focus indicator has a contrast ratio of at least 3:1 against its background colour.WCAG 1.4.11Browser
Skill off
2/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Not applicable
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass

Notes on this run

Skill off

Generation 1 and 3 have aria-invalid applied to the <fieldset>.aria-invalid is invalid on the group role and screen readers handle it inconsistently.

Skill on

Generation 1, 2 and 3 required state is provided through the hint and associated with <fieldset> using aria-describedby.
Generation 1, 2 and 3 also have aria-required="true" applied to the <fieldset>. aria-required="true" is invalid on the group role and screen readers handle it inconsistently.
Generation 1, 2 and 3 have aria-invalid applied to the <fieldset>. aria-invalid is invalid on the group role and screen readers handle it inconsistently.