Test results

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

Grok 4.7

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	90	9
of which WCAG	60	8
of which Best practice	30	1
Total cost (US dollars)	$7.93	$51.79
Input tokens	2.6 million	35.3 million
Output tokens	805,511	3.1 million

Radio

Results, totals across all generations

Cost in USD

Failed acceptance criteria

Skill off

0 fails

WCAG: 0 fails
Best practice: 0 fails

Skill on

0 fails

WCAG: 0 fails
Best practice: 0 fails

Total cost

Skill off: $0.27
Skill on: $1.77

Efficiency, average per generation

Input tokens include cache reads.

Input tokens

Skill off: 23,094 tokens
Skill on: 279,985 tokens

Output tokens

Skill off: 9,815 tokens
Skill on: 41,082 tokens

Turns

Skill off: 4 turns
Skill on: 9 turns

Time

Skill off: 115 seconds
Skill on: 554 seconds

Cost

Skill off: $0.09
Skill on: $0.59

Prompt given to the model

Build a set of radio buttons in a single self-contained HTML file (inline CSS and JS, no build step, no external libraries). Present a "Delivery speed" question where the user picks exactly one option from: Standard (3 to 5 days), Express (next day), and Same day. No option is selected yet. Choosing a delivery speed is mandatory, and because nothing is selected the field is currently in error: show the validation message "Please select a delivery speed." for the delivery speed 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 17 of 17 criteria

Labels and messaging2 criteria

The radio button 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 radio 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 radio button'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 radio button 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 radio buttons 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 radio 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 radio button'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 radio group's required state 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 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

Keyboard5 criteria

The radio buttons 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
The radio buttons can be checked using a keyboard, and checking one automatically deselects the others in the group.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 Up/Down or Left/Right arrow keys move focus between radio buttons in the group and automatically select the focused button.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
The radio button 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 radio button 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: Not applicable
- Generation 2: Pass
- Generation 3: Pass
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass