partforge

Mesh rebuild freecad knob

hard tier · create

The request

Attached is an STL of a knob exported from a CAD application: a round body with a chamfered top edge and a hexagonal socket in the underside. Rebuild it as a parametric part named exactly `knob`, standing where the mesh stands (Z up, same origin, base on the same plane), with controls `diameter` (±10 mm around the mesh) and `height` (±5 mm), and a hex socket that fits a 8 mm key. Keep the mesh imported in the part while you work. Measure the mesh first.
A render of the mesh the model was given
Mesh · made with FreeCAD 1.1.0 (Part workbench, MeshPart tessellation at 0.008 mm linear deflection) · CC0-1.0

What the AI judge checks

  • The overall form matches the reference: the same kind of object, the same silhouette from the matching angle
  • Proportions match: the relative sizes of the major dimensions agree with the reference within what the eye can judge
  • Every major feature visible in the reference (holes, slots, bosses, tabs, lips) is present in the result
  • Those features sit where the reference has them
  • Nothing is present that the reference does not show — no decorative or unexplained geometry
  • The top edge is chamfered, not sharp
  • A hexagonal socket is visible in the bottom view

Measured checks

  • one sub-part named knob (gate)
  • volume within 3 % of the mesh (gate)
  • bounding box within 0.5 mm of the mesh (gate)
  • symmetric difference under the measured floor
  • the socket clears a 8 mm key across the flats
  • the socket is hexagonal, not round
  • the socket is 6 mm deep
  • the imported knob is still declared as an import
  • asked the oracle at most once

Ranked by hand

One reviewer put one attempt from each model in order, best first, ties left tied.

  1. #1
    Gemini 3.8 Flash
    Gemini 3.8 Flash's ranked attempt
  2. #2
    Fable 5.1
    Fable 5.1's ranked attempt
  3. #3
    Opus 5
    Opus 5's ranked attempt
  4. #4
    GPT-5.6 Sol
    GPT-5.6 Sol's ranked attempt
  5. #5
    GPT-6 Astra
    GPT-6 Astra's ranked attempt

Ordering by hand decides Human rank and Human rate on the leaderboard; it never affects Overall or Strict.

Every model's attempts

Run baseline-2026-092026-09-10commit 41aec7daspend $339.70 + $48.02 AI judging, 7 unpricedOther runs: 2026-09-04T20-02-10-stage2-hard-cases, 2026-09-04T19-48-31-screen-14-fixed