All research
BenchmarkPreliminary

HappyCAD on BenchCAD 2.0 Public

HappyCAD scored 0.856 / 1 on the 91 CAD cases of the BenchCAD 2.0 Public set.

Portrait of Kimi Kong

Reviewed by

Kimi Kong

Co-founder, HappyCAD

Stanford University; ex-Google DeepMind, AWS, Microsoft

Results

TaskHappyCAD (Public)GPT-6 AstraOpus 5.5Sonnet 5.5Fable 5.1Haiku 5.5
1. Drawing to CAD: part0.940 (21)0.8070.8370.7930.5210.561
2. Drawing to CAD: assembly, parts supplied0.971 (14)0.7210.6670.3420.3980.091
3. 3D reverse engineering: part0.955 (23)0.5760.5920.5910.3100.316
4. 3D reverse engineering: assembly0.626 (27)0.5010.4400.4380.2460.154
5. Drawing to CAD: parts and assembly0.947 (6)0.6900.6610.2230.3720.010
All five tasks0.856 (91)0.6120.5890.4550.3300.196
  • Scores: from 0 to 1, where 1.0 is a perfect answer. Each score is the mean over the task's cases.
  • Scoring: BenchCAD's own scorer compares each answer with a reference model: the shape of each part, and the position of each part in an assembly.
  • Cases: HappyCAD ran on the Public set (91 cases; the count for each task is in brackets). The five models in the table ran on the held-out Core set (88 cases: 6, 11, 28, 25 and 18 for tasks 1–5). The two sets have no cases in common.
  • Model columns: BenchCAD's own results for BenchCAD 2.0, from its 25 published runs, each model at max effort.
  • Other models: newer models, such as Claude Fable 5.2 and GPT-6.2 Astra, have only an overall BenchCAD 2.1 score (leaderboard), with no score for each task, so the table does not include them.
  • Official score: only Core gives an official BenchCAD score. Our request for access to Core is in review with the BenchCAD team. When they approve it, we will run HappyCAD on Core.

Score for each HappyCAD case →