Mesh rebuild blender handle
hard tier · create
The request
Attached is an STL of a D-shaped pull handle exported from Blender. Rebuild it parametrically as one sub-part named `handle`, standing where the mesh stands (Z up, same origin, feet on the same plane): a round section swept along a D-shaped path standing off the mounting face, with two flat feet each carrying a 5 mm through-hole, holes 114 mm apart. Controls: `span` (±20 mm) and `sectionDiameter` (4–12 mm). Keep the mesh imported in the part while you work. Measure the mesh first.

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
- A D-shaped loop standing off two flat feet, as in the reference
- The grip has a round cross-section
Measured checks
- one sub-part named handle (gate)
- volume within 5 % of the mesh (gate)
- bounding box within 0.5 mm of the mesh (gate)
- symmetric difference under the measured floor
- mounting holes are 114 mm apart
- the imported handle 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 tieGemini 3.8 Flash

- #1 tieDeepSeek V4.1 Flash

- #1 tieGPT-6 Luna

- #1 tieGPT-6 Sol

- #1 tieOpus 5.5

- #6Kimi K3 Fast

- #7Kimi K3 (Moonshot)
not acceptable
Parts marked not acceptable fall below the reviewer's acceptable line whatever their order. Ordering by hand decides Human rank and Human rate on the leaderboard; it never affects Overall or Strict.
Every model's attempts
This is an older run. See the current results.
Run hard-baseline-2026-09-232026-09-23commit 6edf19e0spend $212.67 + $43.09 AI judging, 15 unpricedstopped early (interrupted)Other runs: 2026-10-16T18-49-10-hard-compact-2026-10-16, 2026-09-10T19-44-23-baseline-2026-09, 2026-09-04T20-02-10-stage2-hard-cases, 2026-09-04T19-48-31-screen-14-fixed