# Spatial Reasoning on CVBench (Single Score Metric)

Source: [Spatial Reasoning on CVBench (Single Score Metric)](<https://www.sota2.com/research/sota/spatial-reasoning-on-cvbench-single-score-metric>)

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

Data updated: 2026-04-07T07:45:53.739Z

Evaluation of model performance on the CVBench dataset for Spatial Reasoning, reporting a single aggregated 'Score'.

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 reasoning |
| Dataset (including any stated split) | CVBench |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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-reasoning-on-cvbench-single-score-metric.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| LLaVA-1.5-7B | 57.3 | Not recorded | 69d48f997d0172140ec7434b |
| LSG | 7.3 | Not recorded | 69d48f997d0172140ec7434b |
| LSG | 2.1 | Not recorded | 69d48f997d0172140ec7434b |
| LSG | 0.5 | Not recorded | 69d48f997d0172140ec7434b |

### LLaVA-1.5-7B

Score: 57.3. Result ID: 69d4b5a847f34ce924bc3a86.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f997d0172140ec7434b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Gating layer configuration":"None (Baseline)"}. This record does not assert independent reproduction.

### LSG

Score: 7.3. Result ID: 69d4b5a847f34ce924bc3a87.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f997d0172140ec7434b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d48f997d0172140ec7434b.md>)

Recorded evaluation configuration: {"Gating layer configuration":"L2","Base model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction.

### LSG

Score: 2.1. Result ID: 69d4b5a847f34ce924bc3a88.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f997d0172140ec7434b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d48f997d0172140ec7434b.md>)

Recorded evaluation configuration: {"Gating layer configuration":"L10","Base model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction.

### LSG

Score: 0.5. Result ID: 69d4b5a847f34ce924bc3a89.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f997d0172140ec7434b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d48f997d0172140ec7434b.md>)

Recorded evaluation configuration: {"Gating layer configuration":"L19","Base model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction.

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