GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation
Organizations: Department of Automation, Tsinghua University, 30 Shuangqing Road, Haidian District, Beijing 100084, China · Department of Industrial Engineering, Tsinghua University, 30 Shuangqing Road, Haidian District, Beijing 100084, China
Abstract
Generating accurate CAD models requires substantial engineering expertise and careful control of geometry, topology, and mechanical constraints. Text-to-CAD aims to simplify this process, but current LLM-based methods often generate CAD programs directly. Language models remain unreliable when producing long code while coordinating coupled geometric, topological, and dimensional constraints. Consequently, executable programs may still produce structurally incorrect models, which execution rate and rendered appearance may fail to reveal. To address these limitations, we propose GOPR-CAD, an agentic Text-to-CAD pipeline based on Graph-of-Operations Progressive Reasoning. A language model acts as a decision agent over encapsulated CAD operations and progressively constructs an executable operation graph, which a deterministic compiler converts into the final CAD model. This separation requires no additional training and supports different language models. To evaluate structural fidelity, we construct MHCAD, a benchmark of 300 standard mechanical part requirements derived from Machinery's Handbook. Their explicit structures enable reference-free STEP/B-rep evaluation. GOPR-CAD achieves 82.7% Structural Yield on MHCAD, and 87.2% Structural Yield on an external CADPrompt subset.
Figures & tables
| Method | STEP | SF | SY |
|---|---|---|---|
| GOPR-CAD (Ours) | 90.0 | 89.8 | 82.7 |
| Text2CAD | 94.0 | 40.8 | 37.4 |
| Text-to-CadQuery | 79.0 | 39.4 | 32.7 |
| CADFusion | 53.0 | 64.0 | 30.7 |
| NURBGen | 97.3 | 21.8 | 20.8 |
| Qwen3-Coder Direct | 43.7 | 66.9 | 28.4 |
| Method | Bore | Body | Coax. Axis | Mount Holes | Circ. Pattern | Rolling Count |
|---|---|---|---|---|---|---|
| GOPR-CAD (Ours) | 99.0 | 75.0 | 82.5 | 100.0 | 96.4 | 94.7 |
| Text2CAD | 57.4 | 0.0 | 39.1 | 25.0 | 15.4 | 11.8 |
| Text-to-CadQuery | 59.8 | 25.0 | 25.2 | 60.0 | 44.0 | 40.0 |
| CADFusion | 100.0 | 25.0 | 48.4 | 100.0 | 55.6 | 50.0 |
| NURBGen | 26.5 | 0.0 | 25.1 | 20.0 | 3.6 | 0.0 |
| Qwen3-Coder Direct | 88.6 | 100.0 | 58.3 | 100.0 | 50.0 | 45.5 |
Appendix figures & tables10 assets
Supplementary material from the paper’s appendix.
Appendix
| Category or mechanical family | Prompts | Percentage |
|---|---|---|
| Bearings, bushings, and rolling elements | 79 | 26.3% |
| Fasteners and washers | 73 | 24.3% |
| Power transmission | 44 | 14.7% |
| Shafts, keys, retainers, and seals | 35 | 11.7% |
| Structural sections and stock | 23 | 7.7% |
| Springs and formed wire | 21 | 7.0% |
| Gate | Definition and scoring consequence |
|---|---|
| STEP found | A method produces a STEP file; a missing file remains in the SY denominator with zero structural passes. |
| STEP reimport | The file loads in the CAD kernel. SF includes successful reimports; SY retains failures with zero structural passes. |
| B-rep valid | The imported shape passes the CAD validity test. SF includes valid B-reps; SY assigns zero structural delivery to invalid cases. |
| Structural checks | Applicable checks run on valid reimported B-reps; passes contribute to SF and SY according to their denominators. |
| Method | STEP/ reimport | B-rep valid | SF | SY |
|---|---|---|---|---|
| GOPR-CAD (Ours) | 270/270 | 270/300 | 283/315 | 283/342 |
| Text2CAD | 282/282 | 281/300 | 128/314 | 128/342 |
| Text-to-CadQuery | 237/237 | 228/300 | 112/284 | 112/342 |
| CADFusion | 159/159 | 159/300 | 105/164 | 105/342 |
| NURBGen | 292/292 | 287/300 | 71/326 | 71/342 |
| Qwen3-Coder Direct | 131/131 | 128/300 | 97/145 | 97/342 |
| Method | SF | SF 95% CI | SY | SY 95% CI |
|---|---|---|---|---|
| GOPR-CAD | 89.8 | [86.2, 93.1] | 82.7 | [78.0, 87.1] |
| Text2CAD | 40.8 | [34.4, 47.2] | 37.4 | [31.4, 43.7] |
| Text-to-CQ | 39.4 | [32.3, 46.7] | 32.7 | [26.3, 39.2] |
| CADFusion | 64.0 | [57.0, 70.7] | 30.7 | [24.7, 36.9] |
| NURBGen | 21.8 | [15.9, 28.3] | 20.8 | [15.1, 26.9] |
| Qwen Direct | 66.9 | [58.4, 75.4] | 28.4 | [22.1, 34.9] |
| Method | Bore | Body | Coaxial Axis |
|---|---|---|---|
| GOPR-CAD (Ours) | 98/99 (99.0) | 3/4 (75.0) | 132/160 (82.5) |
| Text2CAD | 58/101 (57.4) | 0/5 (0.0) | 63/161 (39.1) |
| Text-to-CQ | 55/92 (59.8) | 1/4 (25.0) | 36/143 (25.2) |
| CADFusion | 49/49 (100.0) | 1/4 (25.0) | 45/93 (48.4) |
| NURBGen | 27/102 (26.5) | 0/5 (0.0) | 42/167 (25.1) |
| Qwen Direct | 39/44 (88.6) | 3/3 (100.0) | 42/72 (58.3) |
| Variant | STEP | SF [95% CI] | SY [95% CI] |
|---|---|---|---|
| Full GOPR-CAD | 270/300 | 89.8 [86.2, 93.1] | 82.7 [78.0, 87.1] |
| Operation-Internal Defaults | 205/300 | 96.1 [93.0, 98.5] | 78.4 [72.7, 83.6] |
| Feature-Level Operation Reference | 283/300 | 78.8 [73.3, 83.9] | 76.0 [70.4, 81.3] |
| Part-Family Template Recall | 209/300 | 77.4 [71.8, 83.0] | 64.0 [58.2, 69.7] |
| Soft-Constraint Recall | 173/300 | 94.7 [91.4, 97.4] | 62.9 [55.5, 69.5] |
| Free-Text Stages | 10/300 | 37.5 (3/8) | 0.9 (3/342) |
| Group | Item | Count |
|---|---|---|
| Overall | Total CADPrompt cases | 200 |
| Overall | Kept single mechanical structural cases | 30 |
| Overall | Removed | 170 |
| Kept family | Bored cylindrical part | 8 |
| Kept family | Fastener like single part | 1 |
| Kept family | Pipe or flange like single part | 5 |
| Method | STEP found/ reimp./cases | B-rep valid | SF | SY |
|---|---|---|---|---|
| GOPR-CAD (Ours) | 30/30/30 | 30/30 | 41/47 | 41/47 |
| Text2CAD | 30/30/30 | 30/30 | 17/47 | 17/47 |
| Text-to-CQ | 5/5/30 | 5/30 | 3/8 | 3/47 |
| CADFusion | 26/26/30 | 26/30 | 32/40 | 32/47 |
| Qwen Direct | 25/25/30 | 25/30 | 24/41 | 24/47 |
| Method | Bore | Coaxial Axis | Mount Holes | Circular Pattern |
|---|---|---|---|---|
| GOPR-CAD (Ours) | 22/23 | 17/18 | 1/3 | 1/3 |
| Text2CAD | 10/23 | 7/18 | 0/3 | 0/3 |
| Text-to-CQ | 2/3 | 1/3 | 0/1 | 0/1 |
| CADFusion | 17/19 | 11/15 | 2/3 | 2/3 |
Text-to-CAD Generation
Text-to-CAD generation turns natural-language design intent into executable, editable parametric 3D models and assemblies.
See all 54 papers