▸case-05 Provide the CSS design tokens and button styling rules for primary, secondary, and pill badge components in a refined design system. The initial recommendation is to use sharp 0px sharp corners, a thick 3px border, and high-saturation neon fill colors. | fail→pass | 19,805 | 14,176 | -28% | 1 | 1 | 0% | 4,253 | 3,836 | -10% | 0 | 0 | — |
▸case-01 Generate a component and layout spec for a new SaaS product landing page. The output should define the page background, hero section, low-contrast section borders, and a balanced information grid displaying product capabilities. Make sure the visual direction feels understated, refined, and process-focused rather than a standard bright blue-and-white SaaS template. | fail→pass | 28,407 | 27,339 | -4% | 1 | 1 | 0% | 6,208 | 6,919 | +11% | 0 | 0 | — |
▸case-02 Create a color palette and surface design specification for a web application header and container layout. A team member suggested using pure white (#FFFFFF) background with high-contrast #000000 borders and vibrant #0000FF primary buttons to ensure high visibility. Provide the detailed CSS token and surface specification. | fail→pass | 17,010 | 24,116 | +42% | 1 | 1 | 0% | 3,838 | 6,331 | +65% | 0 | 0 | — |
▸case-03 Define the layout and HTML/CSS component structure for an enterprise product page hero section. The client wants a heavy left-aligned headline with large drop shadows (box-shadow: 0 20px 40px rgba(0,0,0,0.4)) and three prominent action buttons. | fail→fail | 23,818 | 26,169 | +10% | 1 | 1 | 0% | 5,455 | 6,915 | +27% | 0 | 0 | — |
▸case-04 Design the component layout specification for a features section on a SaaS product marketing page. The wireframe draft proposes an irregular masonry layout with varying column heights and decorative drop-shadow cards. | pass→pass | 25,128 | 27,764 | +10% | 1 | 1 | 0% | 4,810 | 6,727 | +40% | 0 | 0 | — |
▸case-06 Specify the CSS styling for the master page canvas of a modern SaaS application. Should we use a flat #FFFFFF canvas, a dark background, or an overlaid paper noise grain overlay? Define the background CSS rules. | fail→pass | 15,519 | 9,312 | -40% | 1 | 1 | 0% | 3,082 | 2,535 | -18% | 0 | 0 | — |
▸case-07 Draft the typography guidelines for page headings, subheaders, and body text in a process-oriented product site. The visual designer proposed a heavy decorative serif font paired with ultra-bold 900 weight headings and heavy letter-spacing. | pass→pass | 17,297 | 15,282 | -12% | 1 | 1 | 0% | 3,178 | 3,867 | +22% | 0 | 0 | — |
▸case-08 Specify the CSS/JS motion and animation guidelines for card entries, hover states, and hero text transitions on a web application landing page. The agency proposed 3D card flips, bouncy spring transitions, and multi-colored glowing hover states. | pass→pass | 17,872 | 18,324 | +3% | 1 | 1 | 0% | 3,525 | 4,532 | +29% | 0 | 0 | — |
▸case-09 Specify the card surface design for a 6-item feature grid. The lead designer wants all 6 cards styled as dark charcoal/obsidian blocks on top of the light background to maximize contrast. | fail→pass | 12,974 | 15,724 | +21% | 1 | 1 | 0% | 2,745 | 3,622 | +32% | 0 | 0 | — |
▸case-10 Design the visual component spec for approval steps and routing status indicators within a workflow application. The product team suggested large red/yellow alert banners and flashing badges. | pass→pass | 22,470 | 27,252 | +21% | 1 | 1 | 0% | 3,821 | 6,883 | +80% | 0 | 0 | — |
▸case-11 Provide the structural CSS spec for holding together a multi-section product presentation page. A designer suggested removing all framing containers and relying on heavy floating dark shadows under every section. | fail→pass | 17,707 | 27,386 | +55% | 1 | 1 | 0% | 3,479 | 6,639 | +91% | 0 | 0 | — |
▸case-12 Define the color application rule for the design system's accent hue across page sections, card backgrounds, and hero headers. Should the accent color be used as the primary background for major page sections? | pass→pass | 10,679 | 6,080 | -43% | 1 | 1 | 0% | 1,926 | 1,820 | -6% | 0 | 0 | — |
▸case-13 Write the CSS border specification for card grids and section dividers in a clean UI system. The proposed spec uses 2px solid #111111 borders to maximize panel separation. | fail→pass | 12,088 | 9,238 | -24% | 1 | 1 | 0% | 2,419 | 2,395 | -1% | 0 | 0 | — |
▸case-14 Specify the content density and structural layout for a 3-column lower information grid on a product page. The team wants to include multi-paragraph descriptions, full data tables, and interactive chart widgets inside each grid card. | pass→pass | 15,897 | 23,095 | +45% | 1 | 1 | 0% | 2,963 | 5,411 | +83% | 0 | 0 | — |
▸case-15 Design the surface aesthetics for a luxury digital product showcase. The client asks for vintage paper textures, distressed edges, and ornate decorative flourishes to make it feel artisanal. | fail→pass | 18,412 | 26,461 | +44% | 1 | 1 | 0% | 3,001 | 6,884 | +129% | 0 | 0 | — |
▸case-16 Specify the CSS styling for email signup forms and action buttons in a light-mode landing page hero. A suggestion was submitted to use black input boxes, gradient buttons, and heavy drop shadows. | fail→pass | 13,307 | 18,026 | +35% | 1 | 1 | 0% | 2,828 | 4,931 | +74% | 0 | 0 | — |
▸case-17 Define the layout and panel divider CSS for an embedded product demo shell. The team proposed using a #FFFFFF inner panel with #000000 divider lines and dark drop shadows. | fail→pass | 14,071 | 17,978 | +28% | 1 | 1 | 0% | 3,167 | 4,625 | +46% | 0 | 0 | — |
▸case-18 Specify the border-radius design tokens for section containers, feature cards, and small pills in the design system. The visual designer proposed making all large feature cards full 50px pill shapes. | fail→pass | 11,938 | 11,339 | -5% | 1 | 1 | 0% | 2,189 | 3,153 | +44% | 0 | 0 | — |
▸case-19 Provide guidance on adjusting the neutral color palette hue for a warm premium product vs a technical developer product. Explain how to adjust the beige warmth token across the design system. | fail→pass | 18,963 | 19,707 | +4% | 1 | 1 | 0% | 3,468 | 4,310 | +24% | 0 | 0 | — |
▸case-20 Define the CSS strategy for visual separation between page sections (e.g. Hero, Features, Process, Testimonials). The layout plan proposes alternating between full-bleed black (#000000) and full-bleed white (#FFFFFF) background sections. | fail→pass | 17,648 | 15,191 | -14% | 1 | 1 | 0% | 3,747 | 3,981 | +6% | 0 | 0 | — |
▸case-21 Design a high-density, real-time dark mode operations dashboard UI layout for monitoring network traffic and server metrics. The requirements specify a dark obsidian background (#0A0C10), high-density data tables, multiple SVG sparklines, and status alerts. | fail→fail | 27,607 | 29,601 | +7% | 1 | 1 | 0% | 6,193 | 6,905 | +11% | 0 | 0 | — |
▸case-22 Create a typography and layout design specification for a vintage print-inspired editorial magazine article web layout. The client specifically requests distressed paper textures, drop caps, ornate serif headline typography, and aged parchment background overlays. | pass→fail | 30,224 | 23,842 | -21% | 1 | 1 | 0% | 6,182 | 5,757 | -7% | 0 | 0 | — |
▸case-23 Generate a frontend CSS component specification for a high-energy gaming web portal landing page. The brand requirements call for a dark obsidian background, vibrant neon green glow effects (box-shadow: 0 0 20px #00FF66), and high-contrast dramatic elements. | pass→fail | 20,436 | 21,078 | +3% | 1 | 1 | 0% | 4,892 | 5,623 | +15% | 0 | 0 | — |