BLXBenchBLXBench UI
blxbench

Benchmark

Misc

DocsOur TestsPassSponsor / Partnership
DocsOur TestsPassSponsor / Partnership
BLXBenchBLXBench UI
blxbench

Benchmark

Suite

Misc

DocsOur TestsPassSponsor / Partnership
DocsOur TestsPassSponsor / Partnership
  1. Home
  2. Our Tests
  3. Ui-Easy-Login-Card
blxbench

Test fixture

Ui-Easy-Login-Card

Uiv2 — Resilienceeasyscorer: singlefile_html_visual_judged

Single-file HTML visual/UI artifacts with render and preview workflows.

How it is scored

The model receives the prompt (and optional system message). The run uses scorer singlefile_html_visual_judged with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.

User prompt
Create a complete single-file HTML document for a responsive login card. Return only the HTML document, without Markdown fences or explanations. The UI must include a small logo placeholder, a clear title, an email field, a password field, a primary login button, and a forgot password link. The card should be centered on the page, visually polished, accessible, and usable on desktop and mobile. Use semantic HTML, labels for inputs, good spacing, readable typography, and a modern but simple visual style.
Scorer config
{
  "min_chars": 2000,
  "requires_style": true,
  "requires_script": false,
  "forbidden_contains": [
    "```",
    "TODO",
    "lorem ipsum",
    "placeholder text"
  ],
  "allowed_cdn_hosts": [
    "cdn.jsdelivr.net",
    "cdnjs.cloudflare.com",
    "unpkg.com"
  ],
  "playwright_enabled": true,
  "judge_enabled": true,
  "render_wait_ms": 500,
  "viewports": [
    {
      "name": "desktop",
      "width": 1440,
      "height": 900
    },
    {
      "name": "mobile",
      "width": 390,
      "height": 844
    }
  ],
  "required_selectors": [
    "input[type='email']",
    "input[type='password']",
    "button"
  ],
  "required_text_groups": [
    [
      "Login",
      "Sign in",
      "Einloggen",
      "Anmelden"
    ],
    [
      "Forgot password",
      "Passwort vergessen"
    ],
    [
      "Logo",
      "BLX",
      "App"
    ]
  ],
  "ui_requirements": [
    {
      "id": "email_input",
      "label": "Has an email input",
      "type": "selector",
      "selector": "input[type='email']",
      "points": 10
    },
    {
      "id": "password_input",
      "label": "Has a password input",
      "type": "selector",
      "selector": "input[type='password']",
      "points": 10
    },
    {
      "id": "login_action",
      "label": "Has a visible login action",
      "type": "text",
      "text": [
        "Login",
        "Sign in",
        "Einloggen",
        "Anmelden"
      ],
      "points": 10
    },
    {
      "id": "forgot_password",
      "label": "Has a forgot password link",
      "type": "text",
      "text": [
        "Forgot password",
        "Passwort vergessen"
      ],
      "points": 5
    },
    {
      "id": "logo_placeholder",
      "label": "Has a logo placeholder or app mark",
      "type": "text",
      "text": [
        "Logo",
        "BLX",
        "App"
      ],
      "points": 5
    }
  ],
  "interaction_checks": [],
  "score_weights": {
    "static": 0.2,
    "render": 0.25,
    "requirements": 0.3,
    "interaction": 0,
    "accessibility": 0.1,
    "animation": 0,
    "judge": 0.15
  },
  "pass_threshold": 0.65
}
Run parameters

temperature

0

max_tokens

6000

timeout (s)

120

type

scored

file

ui-easy-login-card.json

← PreviousSpeed-User-Story-Set
|
Next →Ui-Hard-Game-Lobby

BLXBench

Community driven leaderboardPublic benchmark runner — run in your environment, share results with the community.

© 2026 BLXBench by bitslix.com

ProvenanceAggregated from user runs
Scope40 / 11 / 490
Latestrun_f78b01 / 459 / $18.57
TermsPrivacy