# CadQuery code generation on Recap-OmniCAD+-2K

Source: [CadQuery code generation on Recap-OmniCAD+-2K](<https://www.sota2.com/research/sota/cadquery-code-generation-on-recap-omnicad-plus-2k>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-05T09:46:55.694Z

Evaluation of models generating CadQuery code on the Recap-OmniCAD+-2K dataset, reporting Intersection Ratio (IR) and Chamfer Distance (CD) statistics (mean and median).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | CadQuery code generation |
| Dataset (including any stated split) | Recap-OmniCAD+-2K |
| Metric | IR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [IR](<https://www.sota2.com/research/sota/cadquery-code-generation-on-recap-omnicad-plus-2k.md?metric=IR>): Higher is better; unit: SCALAR.

- [CD Mean](<https://www.sota2.com/research/sota/cadquery-code-generation-on-recap-omnicad-plus-2k.md?metric=CD%20Mean>): Lower is better; unit: SCALAR.

- [CD Median](<https://www.sota2.com/research/sota/cadquery-code-generation-on-recap-omnicad-plus-2k.md?metric=CD%20Median>): Lower is better; unit: SCALAR.

## Recorded results

| Method | IR | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen2.5 | 49.7 | Not recorded | 69a90e062d603e6de3e407e9 |
| Claude | 41.75 | Not recorded | 69a90e062d603e6de3e407e9 |
| Gemini | 39.25 | Not recorded | 69a90e062d603e6de3e407e9 |
| GPT | 33.55 | Not recorded | 69a90e062d603e6de3e407e9 |
| Pointer-CAD | 26.02 | Not recorded | 69a90e062d603e6de3e407e9 |
| Pointer-CAD | 19.11 | Not recorded | 69a90e062d603e6de3e407e9 |

### Qwen2.5

IR: 49.7. Result ID: 69a950f76dbb7075b9532f7a.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407e9.md>)

Recorded evaluation configuration: {"version":"72B"}. This record does not assert independent reproduction.

### Claude

IR: 41.75. Result ID: 69a950f76dbb7075b9532f77.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407e9.md>)

Recorded evaluation configuration: {"version":"Opus"}. This record does not assert independent reproduction.

### Gemini

IR: 39.25. Result ID: 69a950f76dbb7075b9532f78.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407e9.md>)

Recorded evaluation configuration: {"version":"1.5 Pro"}. This record does not assert independent reproduction.

### GPT

IR: 33.55. Result ID: 69a950f76dbb7075b9532f79.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407e9.md>)

Recorded evaluation configuration: {"version":"4o"}. This record does not assert independent reproduction.

### Pointer-CAD

IR: 26.02. Result ID: 69a950f76dbb7075b9532f7b.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407e9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407e9.md>)

Recorded evaluation configuration: {"version":"0.5B"}. This record does not assert independent reproduction.

### Pointer-CAD

IR: 19.11. Result ID: 69a950f76dbb7075b9532f7c.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407e9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e062d603e6de3e407e9.md>)

Recorded evaluation configuration: {"version":"1.5B"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.