# Spatial & 3D Understanding on STRIDE-QA

Source: [Spatial & 3D Understanding on STRIDE-QA](<https://www.sota2.com/research/sota/spatial-and-3d-understanding-on-stride-qa>)

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

Data updated: 2026-04-21T13:36:38.119Z

Evaluation of Spatial & 3D Understanding capabilities using the STRIDE-QA dataset.

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 | Spatial & 3D Understanding |
| Dataset (including any stated split) | STRIDE-QA |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Score](<https://www.sota2.com/research/sota/spatial-and-3d-understanding-on-stride-qa.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| XEmbodied (Best) | 27.76 | Not recorded | 69e7052e7d0172140ec7f361 |
| GPT-4o | 14.7 | Not recorded | 69e7052e7d0172140ec7f361 |
| Qwen3-VL-A3B-30B | 8.69 | Not recorded | 69e7052e7d0172140ec7f361 |
| PR1-OCR-2B | 8.18 | Not recorded | 69e7052e7d0172140ec7f361 |
| Mimo-Embodied | 7.9 | Not recorded | 69e7052e7d0172140ec7f361 |
| PR1-Grounding-2B | 7.15 | Not recorded | 69e7052e7d0172140ec7f361 |
| Qwen2.5-VL-32B | 6.58 | Not recorded | 69e7052e7d0172140ec7f361 |
| Qwen3-VL-32B | 6 | Not recorded | 69e7052e7d0172140ec7f361 |
| UniVG-R1-7B | 4.61 | Not recorded | 69e7052e7d0172140ec7f361 |
| PR1-Detection-3B | 4.35 | Not recorded | 69e7052e7d0172140ec7f361 |
| PR1-Counting-2B | 1.94 | Not recorded | 69e7052e7d0172140ec7f361 |
| Qwen2.5-VL-7B | 1.41 | Not recorded | 69e7052e7d0172140ec7f361 |
| DriveMM | 1.12 | Not recorded | 69e7052e7d0172140ec7f361 |
| Cosmos-R1 | 1.03 | Not recorded | 69e7052e7d0172140ec7f361 |

### XEmbodied (Best)

Score: 27.76. Result ID: 69e77cea47f34ce924cf7129.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

Recorded evaluation configuration: {"Model Category":"Our Model"}. This record does not assert independent reproduction.

### GPT-4o

Score: 14.7. Result ID: 69e77cea47f34ce924cf711c.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary Models"}. This record does not assert independent reproduction.

### Qwen3-VL-A3B-30B

Score: 8.69. Result ID: 69e77cea47f34ce924cf711f.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Model Category":"Open-Source Models"}. This record does not assert independent reproduction.

### PR1-OCR-2B

Score: 8.18. Result ID: 69e77cea47f34ce924cf7122.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77f11e209131cea7628e.md>)

Recorded evaluation configuration: {"Model Category":"Spatial Models"}. This record does not assert independent reproduction.

### Mimo-Embodied

Score: 7.9. Result ID: 69e77cea47f34ce924cf7128.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

[Implementation](<https://github.com/XiaomiMiMo/MiMo-Embodied>)

Recorded evaluation configuration: {"Model Category":"Embodied Models"}. This record does not assert independent reproduction.

### PR1-Grounding-2B

Score: 7.15. Result ID: 69e77cea47f34ce924cf7125.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77f11e209131cea7628e.md>)

Recorded evaluation configuration: {"Model Category":"Spatial Models"}. This record does not assert independent reproduction.

### Qwen2.5-VL-32B

Score: 6.58. Result ID: 69e77cea47f34ce924cf711e.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Model Category":"Open-Source Models"}. This record does not assert independent reproduction.

### Qwen3-VL-32B

Score: 6. Result ID: 69e77cea47f34ce924cf7120.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Model Category":"Open-Source Models"}. This record does not assert independent reproduction.

### UniVG-R1-7B

Score: 4.61. Result ID: 69e77cea47f34ce924cf7121.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78ac1e209131cea79c7c.md>)

Recorded evaluation configuration: {"Model Category":"Spatial Models"}. This record does not assert independent reproduction.

### PR1-Detection-3B

Score: 4.35. Result ID: 69e77cea47f34ce924cf7123.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77f11e209131cea7628e.md>)

Recorded evaluation configuration: {"Model Category":"Spatial Models"}. This record does not assert independent reproduction.

### PR1-Counting-2B

Score: 1.94. Result ID: 69e77cea47f34ce924cf7124.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77f11e209131cea7628e.md>)

Recorded evaluation configuration: {"Model Category":"Spatial Models"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Score: 1.41. Result ID: 69e77cea47f34ce924cf711d.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Model Category":"Open-Source Models"}. This record does not assert independent reproduction.

### DriveMM

Score: 1.12. Result ID: 69e77cea47f34ce924cf7126.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a741e209131cea835a8.md>)

Recorded evaluation configuration: {"Model Category":"Embodied Models"}. This record does not assert independent reproduction.

### Cosmos-R1

Score: 1.03. Result ID: 69e77cea47f34ce924cf7127.

[Reporting paper](<https://www.sota2.com/research/paper/69e7052e7d0172140ec7f361.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78961e209131cea791df.md>)

Recorded evaluation configuration: {"Model Category":"Embodied Models"}. This record does not assert independent reproduction.

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