PartBench
Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity.
Only source found is the Grok 4.6 card reference to normalfactory.com.
- Made by
- Normal Factory
- Released
- 2026
- Kind
- CAD models
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Strongest model tested
- Grok 4.6 #28 on the capability index
- Last in a system card
- August 2026
- Last model added
- August 2026
Grok 4.6 leads with 58.5%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Grok 4.6 58.5%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4.6 | 58.5% | Aug 2026 | Lab model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Aug 12, 2026 | Grok 4.6 model card | 58.5 | PartBench, reward, xhigh, run by Normal Factory (4.3) | Capabilities |
More in Engineering and CAD
- EEBench In use 13 electrical-engineering circuit and PCB design tasks graded by deterministic build checks, simulation and BOM constraints. No LLM judge.
Gemini 4 Carbon 83.9% - Parametric CAD Bench In use Agents author editable parametric FreeCAD part designs, graded against held-back references for geometry and spec consistency. Claude Opus 5.5 61%
- 3DCodeBench In use Agentic procedural 3D modeling via code: author engine-ready 3D assets through software APIs. Graded for executability and shape fidelity.
LongCat-2.5 55.4% - CADGenBench Only in system cards Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness. Claude Fable 5 45.1%
- LMBuild Not in model cards Language model agents design 3D structures as parts, joints, materials and assembly steps. Scoring checks that the structures can be built and work as intended. GPT-6 Astra 66.5%
- Physical-Engineering's Last Exam Not in model cards Agents produce billable engineering deliverables such as calculation packages, drawings and design reviews in 85 tasks across electrical, civil, structural and mechanical engineering. Automatic graders check constraints, safety limits and the design objective. Claude Opus 5.5 0.49