Test results

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

Gemini 4 Argon

Skill version 2.3

Results for 22 components, each generated 3 times.Each acceptance criterion is counted once per component if it fails in any generation.
Measure	Skill off	Skill on
Failed acceptance criteria	22	0
of which WCAG	15	0
of which Best practice	7	0
Total cost (US dollars)	$4.84	$10.85

Checkbox

Results, totals across all generations

Failed acceptance criteria

Each acceptance criterion is counted once per component if it fails in any generation.

Skill off

3 fails

WCAG: 2 fails
Best practice: 1 fail

Skill on

0 fails

WCAG: 0 fails
Best practice: 0 fails

Efficiency, average per generation

Input tokens include cache reads.

Cost in USD

Input tokens

Skill off: 10,475 tokens
Skill on: 94,187 tokens

Output tokens

Skill off: 4,670 tokens
Skill on: 9,396 tokens

Turns

Skill off: 4 turns
Skill on: 7 turns

Time

Skill off: 75 seconds
Skill on: 157 seconds

Cost

Skill off: $0.06
Skill on: $0.16

Generated components

Prompt given to the model

Build a single checkbox in a single self-contained HTML file (inline CSS and JS, no build step, no external libraries). It is a consent checkbox labelled "I agree to the terms and conditions". Ticking it is mandatory. The checkbox is currently unticked, so the field is in error: show the validation message "You must agree to the terms and conditions to continue." for the checkbox. Output the complete code in one HTML code block.

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)

Acceptance criteria

Showing 13 of 13 criteria

Labels and messaging1 criterion

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

Semantic markup5 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
The 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 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 checkbox'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 checkbox 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 checkbox is 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 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
1/3 failed
- Generation 1: Pass
- Generation 2: Fail
- 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
1/3 failed
- Generation 1: Pass
- Generation 2: Fail
- 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 failed
- Generation 1: Pass
- Generation 2: Fail
- Generation 3: Fail
Skill on
3/3 passed
- Generation 1: Pass
- Generation 2: Pass
- Generation 3: Pass