SVG: exploded AeroPress, by claude-haiku-5.5
claude-haiku-5.5 · round 2 of 2 · seed 3$0.01SVGPNGaeropress.svg
aeropress.svg · 109 lines
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 1000" width="800" height="1000" font-family="Helvetica, Arial, sans-serif">
  <defs>
    <linearGradient id="tube" x1="0" x2="1" y1="0" y2="0">
      <stop offset="0" stop-color="#9fb8c4"/>
      <stop offset="0.35" stop-color="#eaf5fa"/>
      <stop offset="0.6" stop-color="#cfe3ec"/>
      <stop offset="1" stop-color="#7f9aa7"/>
    </linearGradient>
    <linearGradient id="plastic" x1="0" x2="1" y1="0" y2="0">
      <stop offset="0" stop-color="#2a4f8a"/>
      <stop offset="0.4" stop-color="#4f7fc4"/>
      <stop offset="1" stop-color="#1e3a68"/>
    </linearGradient>
    <linearGradient id="rubber" x1="0" x2="1" y1="0" y2="0">
      <stop offset="0" stop-color="#1d1d1d"/>
      <stop offset="0.4" stop-color="#4a4a4a"/>
      <stop offset="1" stop-color="#161616"/>
    </linearGradient>
    <linearGradient id="capg" x1="0" x2="1" y1="0" y2="0">
      <stop offset="0" stop-color="#8f8f8f"/>
      <stop offset="0.4" stop-color="#d9d9d9"/>
      <stop offset="1" stop-color="#6c6c6c"/>
    </linearGradient>
    <marker id="arr" markerWidth="10" markerHeight="10" refX="8" refY="5" orient="auto">
      <path d="M0,0 L10,5 L0,10 z" fill="#555"/>
    </marker>
  </defs>

  <rect width="800" height="1000" fill="white"/>

  <!-- title -->
  <text x="400" y="38" text-anchor="middle" font-size="24" font-weight="bold" fill="#222">AeroPress (original model) — exploded assembly</text>

  <!-- central assembly axis -->
  <line x1="400" y1="75" x2="400" y2="935" stroke="#999" stroke-width="1.5" stroke-dasharray="10,6"/>

  <!-- ===== 1. PLUNGER (top) ===== -->
  <g id="plunger">
    <!-- grip / handle -->
    <rect x="300" y="72" width="200" height="34" rx="16" fill="url(#plastic)" stroke="#1b3561" stroke-width="2"/>
    <!-- rod -->
    <rect x="382" y="104" width="36" height="236" fill="url(#plastic)" stroke="#1b3561" stroke-width="2"/>
    <!-- rubber seal / plunger cap -->
    <rect x="338" y="340" width="124" height="34" rx="6" fill="url(#rubber)" stroke="#000" stroke-width="2"/>
    <ellipse cx="400" cy="340" rx="62" ry="8" fill="#333" stroke="#000" stroke-width="1.5"/>
  </g>

  <!-- ===== 2. CHAMBER (middle) ===== -->
  <g id="chamber">
    <!-- body -->
    <rect x="325" y="440" width="150" height="262" fill="url(#tube)" stroke="#4d6a78" stroke-width="2"/>
    <!-- bottom ellipse -->
    <ellipse cx="400" cy="702" rx="75" ry="12" fill="#c8dde7" stroke="#4d6a78" stroke-width="2"/>
    <!-- bottom ridge / lip -->
    <rect x="317" y="696" width="166" height="12" rx="4" fill="#dbeaf1" stroke="#4d6a78" stroke-width="2"/>
    <!-- top flared rim -->
    <rect x="312" y="422" width="176" height="18" rx="6" fill="#f4fbfd" stroke="#4d6a78" stroke-width="2"/>
    <ellipse cx="400" cy="422" rx="88" ry="10" fill="#f4fbfd" stroke="#4d6a78" stroke-width="2"/>
    <!-- opening inside -->
    <ellipse cx="400" cy="422" rx="66" ry="7" fill="#7f9aa7"/>
  </g>

  <!-- ===== 3. FILTER CAP (bottom of chamber) ===== -->
  <g id="filtercap">
    <rect x="335" y="752" width="130" height="50" fill="url(#capg)" stroke="#555" stroke-width="2"/>
    <ellipse cx="400" cy="752" rx="65" ry="10" fill="#e6e6e6" stroke="#555" stroke-width="2"/>
    <ellipse cx="400" cy="802" rx="65" ry="10" fill="#bdbdbd" stroke="#555" stroke-width="2"/>
    <!-- drip holes on cap face -->
    <g fill="#444">
      <circle cx="380" cy="802" r="2.5"/><circle cx="392" cy="800" r="2.5"/><circle cx="404" cy="800" r="2.5"/>
      <circle cx="416" cy="802" r="2.5"/><circle cx="386" cy="806" r="2.5"/><circle cx="398" cy="806" r="2.5"/>
      <circle cx="410" cy="806" r="2.5"/><circle cx="422" cy="806" r="2.5"/><circle cx="374" cy="802" r="2.5"/>
      <circle cx="428" cy="802" r="2.5"/>
    </g>
  </g>

  <!-- ===== 4. ROUND PAPER FILTER (below cap) ===== -->
  <g id="paperfilter">
    <rect x="345" y="850" width="110" height="6" fill="#e9dcc0" stroke="#a48f63" stroke-width="1.5"/>
    <ellipse cx="400" cy="850" rx="55" ry="7" fill="#f6ecd2" stroke="#a48f63" stroke-width="1.5"/>
    <ellipse cx="400" cy="856" rx="55" ry="7" fill="#e9dcc0" stroke="#a48f63" stroke-width="1.5"/>
  </g>

  <!-- ===== Exploded guide lines ===== -->

  <!-- ===== Labels with leader lines ===== -->
  <g stroke="#555" stroke-width="1.2" fill="none">
    <polyline points="500,89 560,89 580,70"/>
    <polyline points="420,222 560,222"/>
    <polyline points="462,357 560,357"/>
    <polyline points="487,529 560,529"/>
    <polyline points="487,777 560,777"/>
    <polyline points="462,853 560,853"/>
  </g>
  <g font-size="17" fill="#222">
    <text x="585" y="75">1. Plunger handle (grip)</text>
    <text x="565" y="227">2. Plunger rod</text>
    <text x="565" y="362">3. Rubber seal (plunger cap)</text>
    <text x="565" y="534">4. Chamber (brew tube)</text>
    <text x="565" y="782">5. Filter cap (with drip holes)</text>
    <text x="565" y="858">6. Round paper filter</text>
  </g>

  <!-- exploded-direction arrows -->
  <!-- footer -->
  <text x="400" y="955" text-anchor="middle" font-size="14" fill="#555">Parts separated along the brewing axis. Original AeroPress model (not Go/XL); round paper filter.</text>
  <text x="400" y="976" text-anchor="middle" font-size="14" fill="#555">Assembly: paper filter → filter cap → chamber (inverted over mug), then plunger inserted from top.</text>
</svg>
round 1 of 2
Exploded AeroPress, by Claude Haiku 5.5, the render after round 1
12What the model saw after each round. The picture above is the round that was scored, round 2.
gallery/Exploded AeroPress/Claude Haiku 5.5, run 3

Exploded AeroPress: Claude Haiku 5.5

modelanthropic/claude-haiku-5.5taskexploded-aeropress@v1, checks c1, harness h1date2026-10-08rounds2 of 8 allowed, 12 minutes on the clockcost$0.0056thinkingmediumtokens52,928 in, 8,071 out, of which 3,564 reasoningtime51 sfailedAll five parts: incomplete, component missing, major, its note said nothing was wrong · Stack order: false, relation transposed, critical, near miss: 1 pair out of order, its note said nothing was wrong
All five partsdecided by looking · Pass if every listed part is drawn as a separate shape and each has a label naming it. A part only named in a label or a comment, with nothing drawn, fails it. The label must say what the part is, in any words: a name that only says where it sits ("top plate") or what it is made of, or a mention in another part's caption, does not count.fail
Stack orderdecided by a number, from the filefail
Parts fitdecided by a number, from the filepass
One assembly axisdecided by looking · Pass if one line runs through the middle of every part on each listed axis, and every leader line leaves from the same side. One part pushed off its axis 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.pass

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 AeroPress, by Claude Haiku 5.5, run 1run 1 · 3r · $0.0085Exploded AeroPress, by Claude Haiku 5.5, run 2run 2 · 2r · $0.0063
same prompt, other modelsall 15 runs on Exploded AeroPress →
the prompt it was given
Draw an exploded assembly diagram of an AeroPress coffee maker, as an SVG. Use the original model with a round paper filter rather than the Go or the XL.
Frozen at v1. This model got this and nothing else.
ground truth

Top to bottom: plunger, rubber seal, chamber, paper filter, filter cap. The seal sits on the plunger's lower end, and the paper filter sits in the cap below the chamber. Checked against AeroPress's replacement-parts pages, which sell the plunger with its seal, the chamber and the cap as the parts of the Original, and Wikipedia's description of the cap holding the filter at the chamber's bottom end. The stirrer and scoop are not part of the assembly. How it is scored, and this run's files on GitHub.