CAD
Models design mechanical parts and assemblies, in CAD software or as CAD code and 3D models. We count 40 benchmarks here, 1 of them arenas. A benchmark belongs here when environment includes SolidWorks, AutoCAD, Autodesk Fusion, Fusion 360, FreeCAD, Onshape, CATIA, Siemens NX, OpenSCAD, CadQuery or Rhinoceros 3D. Or output includes 3D, and subject includes mechanical engineering. Or subject includes mechanical engineering, and output includes code, and environment includes none.
How fast it grows
22 were released since July, more than the 9 in the first half of 2026.
How much is still open
No model has passed 85% on 15 of the 20 benchmarks here that score in percent, 75% of them.
Every benchmark in this view
Newest first. Facets come from each benchmark’s own documents, and our methodology says how we tag them.
| Benchmark | Level | Released | Best score | Status |
|---|---|---|---|---|
| SimReady Text-to-CAD Models convert mechanical part descriptions into CAD programs. OpenCASCADE checks geometry. The hub port uses 111 prompts covering 37 parts from the original 150-prompt evaluation. | University | Nov 2026 | 96.2% | Not in cards |
| SolidWorks Bench Agents model the custom parts of 73 real machines in SolidWorks and assemble them from raster drawing packages, through screenshots and the SolidWorks API. A grader checks the geometry against the reference and reads mates, motion and feature trees from the native files. | Expert | Nov 2026 | 0.57 | Not in cards |
| BenchCAD 2.0 Models reconstruct parts, assemblies, and circuit boards from drawings and images. The Core set contains 100 problems with partial credit. | Expert | Oct 2026 | 59% | Not in cards |
| BenchCAD 2.1 Models reconstruct parts, assemblies, and circuit boards from drawings and images. The Core set contains 100 problems with partial credit. | Expert | Oct 2026 | 83.5% | In use |
| BenchCAD 2.1-beta Models reconstruct parts, assemblies, and circuit boards from drawings and images. The Core set contains 100 problems with partial credit. | Expert | Oct 2026 | Not in cards | |
| FrontierCAD Agents build 39 machined parts from engineering drawings and place parts into 16 assemblies, in their own coding harnesses. A verifier that tolerates rotation and checks hole positions scores the geometry. | Expert | Oct 2026 | 0.67 | Not in cards |
| FrontierCAD Assemblies Agents place supplied CAD parts into 16 assemblies. The score is the published mean assembly geometry score. | Expert | Oct 2026 | 0.71 | Not in cards |
| FrontierCAD Parts Agents build 39 CAD parts from engineering drawings. The score is the published mean geometry score. | Expert | Oct 2026 | 0.63 | Not in cards |
| LMBuild 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. | Expert | Oct 2026 | 66.5% | Not in cards |
| Prompt-to-Bench HO-16 Models design 16 additional laboratory fixtures in OpenSCAD. The grader checks each rendered part against the dimensions and features in its prompt. | University | Oct 2026 | 16.0 | Not in cards |
| Prompt-to-Bench-16 Models write OpenSCAD programs for laboratory fixtures from measured dimensions. They receive feedback after each failed attempt. The grader checks the rendered geometry. | University | Oct 2026 | | Not in cards |
| RWE-bench Agents do mechanical, electrical and aerospace design tasks, such as a crankshaft, dense PCB routing or turbine-vane cooling, with CAD and CAE tools. A deterministic verifier runs physics solvers and passes a design only if it meets every requirement. | Expert | Oct 2026 | 62% | Not in cards |
| SimReadyBench NV100 Agents reconstruct an articulated 3D asset from one image and nominal dimensions. The verifier grades formal, visual, and kinematic fidelity separately across 100 assets. | Expert | Oct 2026 | 100% | Not in cards |
| SnorkelManufacturing Agents make engineering, production, quality, supplier and safety decisions in a simulated discrete-parts plant across 200 tasks, a third of them CAD tasks. | Expert | Oct 2026 | | Not in cards |
| CAD Arena Agents rebuild licensed engineering drawings as editable CAD parts through the scripting APIs of NX, SolidWorks, Onshape, Fusion or Build123d. A verifier scores geometric match. | Expert | Sep 2026 | | Not in cards |
| CADClamp 0.2 Models generate mechanical parts in seven CAD languages. Each part must meet its specification before the grader compares its printability with a reference part. | University | Sep 2026 | 0.93 | Not in cards |
| EngiWorld Agents work through the full industrial engineering design loop on 1,301 expert-curated tasks that need reasoning over geometric and physical constraints across software. | Expert | Sep 2026 | 44.7% | Not in cards |
| Parametric CAD Bench Agents create and edit parametric FreeCAD models from text and engineering drawings. Programmatic checks award continuous task rewards for geometry and specification consistency. | Expert | Sep 2026 | 61.0 | Not in cards |
| cad-spec Models write CadQuery code for mounting plates from dimensioned specifications. The evaluator measures each finished solid against nine requirements. | University | Aug 2026 | | Not in cards |
| CADClamp 0.1 Models write programs for mechanical parts in OpenSCAD and build123d. The grader checks the resulting solids and scores their suitability for 3D printing. | University | Aug 2026 | 0.89 | Not in cards |
| OmniCAD Models choose parts from a component library and predict their assembly positions, orientations, and connections. The evaluator measures pose accuracy and how well connections match. | University | Aug 2026 | | Not in cards |
| AutoCAD Bench Computer-use agents turn a dimensioned reference drawing into a correct, editable DWG in AutoCAD through the screen alone, with mouse and keyboard. 50 tasks span 2D drafting and 3D modeling at four difficulty levels. | Expert | Jul 2026 | 46% | Not in cards |
| BuildArena 2.0 Construction Challenge Agents build and test machines in Besiege for seasonal engineering challenges. The organizers score each entry using simulation results and the rules for its track. | Competition | Jun 2026 | Not in cards | |
| P3D-Bench Models generate parametric 3D objects from text, images, or assembly instructions. The evaluator checks whether outputs run and preserve geometry, topology, and part structure. | University | Jun 2026 | 69.4 | Not in cards |
| BenchCAD Programmatic CAD: 17,900 execution-verified CadQuery programs over 106 industrial part families. Four matched tasks scored on geometry. | University | May 2026 | 95.9% | In use |
| CADGenBench Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness. | University | May 2026 | 45.1% | System cards only |
| CADTestBench Models generate mechanical parts from text. Executable tests check the geometry and topology of each solid. A part passes when it satisfies every test. | University | May 2026 | 81% | Not in cards |
| MUSE (CAD assemblies) Models turn design specifications into CAD assemblies. A program checks the geometry. A vision model grades function, manufacturability, and ease of assembly. | University | May 2026 | 52.4% | Not in cards |
| Parametric CAD Bench V1 Agents write FreeCAD scripts that build editable parametric parts from plain-English descriptions and dimension tables. Each of 100 tasks scores the harmonic mean of geometry similarity and spec consistency. | Expert | May 2026 | In use | |
| neuralCAD-Edit Agents edit existing CAD models from text or recorded instructions. CAD experts rate whether they would accept each edit. Software also compares the resulting geometry. | University | Apr 2026 | 0.25 | Not in cards |
| PartBench Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity. | University | 2026 | 58.5% | System cards only |
| CADExpert Models write CadQuery programs from dimensioned engineering drawings. The graders check whether each program runs and compare its 3D shape with the reference. | University | Dec 2025 | | Not in cards |
| FEM-Bench Models implement finite element functions and write tests for them. The evaluator checks numerical outputs and whether the tests distinguish reference functions from faulty implementations. | University | Aug 2025 | | Not in cards |
| CADmium Fusion 360 Reconstruction Models reconstruct CAD parts from text descriptions of Fusion 360 designs. The authors measure shape distance and count invalid outputs. | University | Jul 2025 | Not in cards | |
| CFDCodeBench Models write Python solvers for partial differential equations. The grader checks execution, agreement with reference solutions, and convergence as the grid gets finer. | University | May 2025 | 14.3% | Not in cards |
| CadEval Models write OpenSCAD code for single mechanical parts from text descriptions. Rendered parts are checked against reference geometry, scored by pass rate. | University | Apr 2025 | 74% | Not in cards |
| CADPrompt Models write CadQuery programs from text descriptions of mechanical parts. The authors align each generated shape with its reference and measure point cloud distance. | University | Oct 2024 | Not in cards | |
| Text2CAD Models generate parametric CAD designs from text prompts at different levels of detail. The authors compare generated geometry with the reference and count invalid designs. | University | Sep 2024 | Not in cards | |
| SimBench (PyChrono) Models write and revise PyChrono simulation programs over three turns. A model grades each program using the reference solution and API documentation. | University | Aug 2024 | 49.0 | Not in cards |
| SCADBench Models write OpenSCAD code from the same short prompt. Voters rotate two rendered objects and choose which one better fits the prompt. | University | | Not in cards |