# Spatial Visual Question Answering on CVBench

Source: [Spatial Visual Question Answering on CVBench](<https://www.sota2.com/research/sota/spatial-visual-question-answering-on-cvbench>)

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

Data updated: 2026-05-29T11:43:41.857Z

Evaluation of Spatial Visual Question Answering performance on the CVBench dataset, reporting metrics including Relative (Rel.), Dependency (Dep.), Distance (Dis.), and Average (Avg.) scores.

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 Visual Question Answering |
| Dataset (including any stated split) | CVBench |
| Metric | Relative Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Relative Score](<https://www.sota2.com/research/sota/spatial-visual-question-answering-on-cvbench.md?metric=Relative%20Score>): Higher is better; unit: PERCENT.

- [Dependency Score](<https://www.sota2.com/research/sota/spatial-visual-question-answering-on-cvbench.md?metric=Dependency%20Score>): Higher is better; unit: PERCENT.

- [Distance Score](<https://www.sota2.com/research/sota/spatial-visual-question-answering-on-cvbench.md?metric=Distance%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/spatial-visual-question-answering-on-cvbench.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Relative Score | Result date | Report paper |
| --- | --- | --- | --- |
| GR3D-8B | 96.92 | Not recorded | 6a191dbfdbd7150506f82a2a |
| GR3D-8B | 96.46 | Not recorded | 6a191dbfdbd7150506f82a2a |
| NVILA-Lite-8B | 93.38 | Not recorded | 6a191dbfdbd7150506f82a2a |

### GR3D-8B

Relative Score: 96.92. Result ID: 6a197be3fbc373592c14d8d7.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dbfdbd7150506f82a2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191dbfdbd7150506f82a2a.md>)

Recorded evaluation configuration: {"Training Stage":"Stage 1"}. This record does not assert independent reproduction.

### GR3D-8B

Relative Score: 96.46. Result ID: 6a197be3fbc373592c14d8d8.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dbfdbd7150506f82a2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191dbfdbd7150506f82a2a.md>)

Recorded evaluation configuration: {"Training Stage":"Stage 2"}. This record does not assert independent reproduction.

### NVILA-Lite-8B

Relative Score: 93.38. Result ID: 6a197be3fbc373592c14d8d6.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dbfdbd7150506f82a2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77481e209131cea723b2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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