SVG: exploded French press, by nemotron-3.5-super-vl
nemotron-3.5-super-vl · round 4 of 4 · seed 2$0.02SVGPNGpress.svg
press.svg · 85 lines
<svg width="900" height="700" xmlns="http://www.w3.org/2000/svg">
  <defs>
    <style>
      .title { font-family: sans-serif; font-size: 20; font-weight: bold; fill: #1a1a1a; text-anchor: middle; }
      .label { font-family: sans-serif; font-size: 14; font-weight: bold; fill: #1a1a1a; text-anchor: middle; }
      .label-small { font-family: sans-serif; font-size: 12; fill: #1a1a1a; }
      .glass { fill: #cce6ff; stroke: #0d47a1; stroke-width: 2; opacity: 0.85; }
      .glass-edge { fill: none; stroke: #0d47a1; stroke-width: 2; }
      .metal { fill: #d7ccc8; stroke: #5d4037; stroke-width: 2; }
      .metal-dark { fill: #b0a090; stroke: #5d4037; stroke-width: 2; }
      .plastic { fill: #efebe9; stroke: #4e342e; stroke-width: 2; }
      .rod { fill: none; stroke: #5d4037; stroke-width: 3; stroke-linecap: round; }
      .mesh { fill: none; stroke: #777; stroke-width: 1; opacity: 0.7; }
      .leader { stroke: #666; stroke-width: 1; stroke-dasharray: 5,4; }
      .box { fill: #fafafa; stroke: #999; stroke-width: 1; }
    </style>
  </defs>

  <text x="450" y="28" class="title">French Press — Exploded Assembly</text>

  <!-- ============ CARAFE (left, assembled) ============ -->
  <g id="carafe" transform="translate(140, 150)">
    <ellipse cx="0" cy="300" rx="82" ry="11" class="glass"/>
    <ellipse cx="0" cy="300" rx="82" ry="11" class="glass-edge"/>
    <path d="M -82 10 L -82 290 L 82 290 L 82 10 Z" class="glass"/>
    <path d="M -82 10 L -82 290" class="glass-edge"/>
    <path d="M 82 10 L 82 290" class="glass-edge"/>
    <ellipse cx="0" cy="10" rx="84" ry="14" fill="none" stroke="#5d4037" stroke-width="3"/>
    <ellipse cx="0" cy="10" rx="84" ry="14" fill="none" stroke="#8d6e63" stroke-width="1"/>
    <path d="M 82 90 Q 140 90 140 180 L 112 180 Q 82 180 82 90 Z" class="glass"/>
    <path d="M 82 90 Q 140 90 140 180 L 112 180 Q 82 180 82 90 Z" class="glass-edge"/>
  </g>

  <text x="140" y="470" class="label">1. Carafe (glass beaker)</text>
  <text x="140" y="488" class="label-small" text-anchor="middle">(shown assembled, for reference)</text>

  <!-- ============ EXPLODED PLUNGER (right) ============ -->
  <line x1="640" y1="130" x2="640" y2="620" stroke="#ccc" stroke-width="1" stroke-dasharray="2,3"/>

  <circle cx="640" cy="100" r="13" class="plastic"/>
  <circle cx="640" cy="100" r="13" fill="none" stroke="#4e342e" stroke-width="2"/>
  <text x="742" y="104" class="label-small">Knob</text>
  <line x1="658" y1="100" x2="732" y2="104" class="leader"/>

  <ellipse cx="640" cy="180" rx="72" ry="17" class="plastic"/>
  <ellipse cx="640" cy="180" rx="72" ry="17" fill="none" stroke="#4e342e" stroke-width="2"/>
  <ellipse cx="640" cy="180" rx="50" ry="7" class="metal"/>
  <circle cx="640" cy="180" r="7" fill="#fff" stroke="#4e342e" stroke-width="2"/>
  <text x="742" y="184" class="label-small">Lid</text>
  <line x1="718" y1="180" x2="732" y2="184" class="leader"/>

  <line x1="640" y1="220" x2="640" y2="390" class="rod"/>
  <circle cx="640" cy="405" r="10" class="plastic"/>
  <circle cx="640" cy="405" r="10" fill="none" stroke="#4e342e" stroke-width="2"/>
  <text x="742" y="305" class="label-small">Plunger rod</text>
  <line x1="658" y1="305" x2="732" y2="305" class="leader"/>

  <ellipse cx="640" cy="450" rx="62" ry="9" class="metal"/>
  <ellipse cx="640" cy="450" rx="62" ry="9" fill="none" stroke="#5d4037" stroke-width="2"/>
  <circle cx="640" cy="450" r="6" fill="#fff" stroke="#5d4037" stroke-width="2"/>
  <text x="742" y="454" class="label-small">3a. Top cross plate</text>
  <line x1="708" y1="450" x2="732" y2="454" class="leader"/>

  <ellipse cx="640" cy="530" rx="64" ry="7" class="metal-dark"/>
  <ellipse cx="640" cy="530" rx="64" ry="7" fill="none" stroke="#5d4037" stroke-width="2"/>
  <ellipse cx="640" cy="530" rx="56" ry="3" class="mesh"/>
  <ellipse cx="640" cy="530" rx="56" ry="3" class="mesh" transform="rotate(90 640 530)"/>
  <text x="742" y="534" class="label-small">3b. Mesh filter</text>
  <line x1="708" y1="530" x2="732" y2="534" class="leader"/>

  <ellipse cx="640" cy="610" rx="66" ry="9" class="metal"/>
  <ellipse cx="640" cy="610" rx="66" ry="9" fill="none" stroke="#5d4037" stroke-width="2"/>
  <circle cx="640" cy="610" r="6" fill="#fff" stroke="#5d4037" stroke-width="2"/>
  <path d="M 620 625 Q 628 630 636 625 Q 644 620 652 625 Q 660 630 668 625" fill="none" stroke="#5d4037" stroke-width="2"/>
  <text x="742" y="614" class="label-small">3c. Support plate + spring</text>
  <line x1="708" y1="610" x2="732" y2="614" class="leader"/>

  <text x="640" y="75" class="label-small" text-anchor="middle">Plunger assembly — exploded</text>

  <!-- ============ PARTS LIST (bottom right, fits in frame) ============ -->
  <rect x="600" y="642" width="295" height="52" class="box"/>
  <text x="615" y="658" class="label-small" font-weight="bold">Parts list</text>
  <text x="615" y="672" class="label-small">1. Carafe · 2. Lid with plunger rod &amp; knob</text>
  <text x="615" y="686" class="label-small">3. Filter: 3a top · 3b mesh · 3c support plate + spring</text>
</svg>
round 1 of 4
Exploded French press, by Nemotron 3.5 Super VL, 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/Nemotron 3.5 Super VL, run 2

Exploded French press: Nemotron 3.5 Super VL

modelnvidia/nemotron-3.5-super-vltasksvg-french-press@v2, checks c1, harness h1date2026-10-16rounds4 of 8 allowed, 12 minutes on the clockcost$0.0238thinkingmediumtokens151,059 in, 18,378 out, of which 7,754 reasoningtime1 min 10 sfailedAll seven parts: incomplete, component missing, major · Stack order: false, relation transposed, critical · Filter fits the glass: false, geometry distorted, major · One assembly axis: unreadable, geometry inconsistent, minor
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.fail
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
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.