SVG: exploded French press, by claude-haiku-5.5
claude-haiku-5.5 · round 4 of 4 · seed 3$0.01SVGPNGpress.svg
press.svg · 101 lines
<svg xmlns="http://www.w3.org/2000/svg" width="800" height="1000" viewBox="0 0 800 1000">
  <defs>
    <pattern id="mesh" width="6" height="6" patternUnits="userSpaceOnUse">
      <path d="M0 0 L6 6 M6 0 L0 6" stroke="#777" stroke-width="0.8"/>
    </pattern>
    <linearGradient id="glass" x1="0" x2="1">
      <stop offset="0" stop-color="#cfe8f5"/>
      <stop offset="0.5" stop-color="#f4fbff"/>
      <stop offset="1" stop-color="#bfdcec"/>
    </linearGradient>
    <linearGradient id="steel" x1="0" x2="1">
      <stop offset="0" stop-color="#9aa3ab"/>
      <stop offset="0.5" stop-color="#e6ebef"/>
      <stop offset="1" stop-color="#8b949c"/>
    </linearGradient>
    <marker id="arr" markerWidth="8" markerHeight="8" refX="4" refY="4" orient="auto">
      <path d="M0 0 L8 4 L0 8 z" fill="#333"/>
    </marker>
  </defs>

  <rect width="800" height="1000" fill="white"/>
  <text x="400" y="36" text-anchor="middle" font-family="Helvetica, Arial, sans-serif" font-size="22" font-weight="bold" fill="#222">French Press — Exploded Assembly (three-piece plunger filter)</text>

  <!-- alignment guide -->
  <line x1="400" y1="70" x2="400" y2="945" stroke="#999" stroke-width="1" stroke-dasharray="6,5"/>

  <!-- A. Lid -->
  <g id="lid">
    <rect x="260" y="84" width="280" height="36" rx="18" fill="url(#steel)" stroke="#444" stroke-width="2"/>
    <rect x="382" y="88" width="36" height="28" fill="white" stroke="#444" stroke-width="1.5"/>
  </g>

  <!-- B. Plunger knob -->
  <rect x="345" y="150" width="110" height="34" rx="16" fill="url(#steel)" stroke="#444" stroke-width="2"/>

  <!-- C. Plunger rod -->
  <rect x="388" y="184" width="24" height="148" fill="url(#steel)" stroke="#444" stroke-width="1.5"/>

  <!-- D. Plunger frame (holder) -->
  <rect x="290" y="330" width="220" height="22" rx="4" fill="url(#steel)" stroke="#444" stroke-width="2"/>
  <g fill="white" stroke="#444" stroke-width="1">
    <circle cx="320" cy="341" r="5"/><circle cx="350" cy="341" r="5"/>
    <circle cx="380" cy="341" r="5"/><circle cx="420" cy="341" r="5"/>
    <circle cx="450" cy="341" r="5"/><circle cx="480" cy="341" r="5"/>
  </g>

  <!-- E. Fine mesh screen (disc) -->
  <rect x="280" y="366" width="240" height="12" rx="3" fill="url(#mesh)" stroke="#444" stroke-width="2"/>

  <!-- H. Retaining cage (lower filter cylinder) -->
  <path d="M300 392 L300 430 Q300 438 308 438 L492 438 Q500 438 500 430 L500 392" fill="url(#mesh)" stroke="#444" stroke-width="2"/>
  <line x1="300" y1="392" x2="500" y2="392" stroke="#444" stroke-width="2"/>

  <!-- F. Carafe -->
  <path d="M250 480 L250 880 Q250 905 275 905 L525 905 Q550 905 550 880 L550 480 Z" fill="url(#glass)" fill-opacity="0.75" stroke="#2c5a73" stroke-width="2.5"/>
  <path d="M250 480 L550 480" stroke="#2c5a73" stroke-width="3"/>
  <path d="M262 500 L262 870" stroke="white" stroke-width="6" opacity="0.7"/>
  <path d="M550 540 Q620 530 620 600 L620 760 Q620 830 550 820" fill="none" stroke="#2c5a73" stroke-width="16" stroke-linecap="round"/>
  <path d="M550 540 Q620 530 620 600 L620 760 Q620 830 550 820" fill="none" stroke="#d9eef8" stroke-width="7" stroke-linecap="round"/>

  <!-- G. Base ring -->
  <rect x="300" y="905" width="200" height="22" rx="6" fill="url(#steel)" stroke="#444" stroke-width="2"/>

  <!-- Labels: right column -->
  <g font-family="Helvetica, Arial, sans-serif" font-size="15" fill="#222">
    <line x1="545" y1="102" x2="585" y2="102" stroke="#555"/>
    <text x="592" y="107">A  Lid</text>

    <line x1="458" y1="167" x2="585" y2="167" stroke="#555"/>
    <text x="592" y="172">B  Plunger knob</text>

    <line x1="412" y1="250" x2="585" y2="250" stroke="#555"/>
    <text x="592" y="255">C  Plunger rod</text>

    <line x1="508" y1="341" x2="585" y2="341" stroke="#555"/>
    <text x="592" y="346">D  Plunger frame (holder)</text>

    <line x1="518" y1="372" x2="585" y2="372" stroke="#555"/>
    <text x="592" y="377">E  Fine mesh screen</text>

    <line x1="508" y1="415" x2="585" y2="415" stroke="#555"/>
    <text x="592" y="420">H  Retaining cage</text>
  </g>

  <!-- Labels: left column -->
  <g font-family="Helvetica, Arial, sans-serif" font-size="15" fill="#222">
    <line x1="252" y1="650" x2="150" y2="650" stroke="#555"/>
    <text x="142" y="655" text-anchor="end">F  Carafe (glass)</text>

    <line x1="300" y1="916" x2="150" y2="916" stroke="#555"/>
    <text x="142" y="921" text-anchor="end">G  Base ring</text>
  </g>

  <!-- Lift direction arrow (left side, clear of labels) -->
  <line x1="190" y1="240" x2="190" y2="70" stroke="#333" stroke-width="2" marker-end="url(#arr)"/>
  <text x="182" y="150" text-anchor="end" font-family="Helvetica, Arial, sans-serif" font-size="13" fill="#333">lift</text>
  <text x="182" y="166" text-anchor="end" font-family="Helvetica, Arial, sans-serif" font-size="13" fill="#333">to separate</text>

  <text x="400" y="965" text-anchor="middle" font-family="Helvetica, Arial, sans-serif" font-size="14" fill="#555">Three-piece plunger filter: holder (D) and fine screen (E) stack on the rod; cage (H) sits beneath. Lid (A) rests on carafe rim.</text>
</svg>
round 1 of 4
Exploded French press, by Claude Haiku 5.5, the render after round 1
1234What the model saw after each round. The picture above is the round that was scored, round 4.
gallery/Exploded French press/Claude Haiku 5.5, run 3

Exploded French press: Claude Haiku 5.5

modelanthropic/claude-haiku-5.5tasksvg-french-press@v2, checks c1, harness h1date2026-10-08rounds4 of 8 allowed, 12 minutes on the clockcost$0.0076thinkingmediumtokens86,590 in, 9,833 out, of which 2,992 reasoningtime1 min 3 sfailedAll seven parts: incomplete, component missing, major, its note said nothing was wrong · Stack order: false, relation transposed, critical, its note said nothing was wrong · Filter fits the glass: false, geometry distorted, major, its note named the fault · Labels match: false, annotation misbound, major, its note said nothing was wrong
All seven partsdecided by looking · Pass if all seven are drawn as separate shapes and each has a label naming it. A part that is only named in a label or a comment, with nothing drawn, fails it.fail
Stack orderdecided by a number, from the filefail
Filter fits the glassdecided by a number, from the filefail
One assembly axisdecided by looking · Pass if one vertical line runs through the middle of every part, and every leader line leaves from the same side. One part pushed off to the side fails it.pass
Labels matchdecided by looking · Pass if following each leader line from its label ends on the part that label names. One label pointing at the wrong part, or at nothing, fails it.fail

There is no post about this one, since only some results need one, so the picture, the source and the scoring are here instead.

its other runs
Exploded French press, by Claude Haiku 5.5, run 1run 1 · 2r · $0.0080Exploded French press, by Claude Haiku 5.5, run 2run 2 · 2r · $0.0040
same prompt, other modelsall 65 runs on Exploded French press →
the prompt it was given
Draw an exploded assembly diagram of a French press, as an SVG. Use the standard three-piece plunger filter rather than a two-piece travel press.
Frozen at v2. This model got this and nothing else.
ground truth

The standard three-piece plunger, from the top down: spiral (spring) plate, mesh screen, cross-plate. The cross-plate is the bottom piece, because its threaded stem is what the rod screws into. The spiral plate above the mesh is what presses the mesh edge out against the glass. Checked against the WebstaurantStore anatomy diagram, which is drawn exploded and labelled, and against each part's y coordinate in the SVG rather than its comment. Two-piece travel presses exist and stack differently, which is why v2 of the prompt names the design. How it is scored, and this run's files on GitHub.