# Situational Question Answering on SQA3D

Source: [Situational Question Answering on SQA3D](<https://www.sota2.com/research/sota/situational-question-answering-on-sqa3d>)

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

Data updated: 2026-04-21T13:09:44.690Z

Evaluation of model performance on the SQA3D dataset for Situational Question Answering, reporting Exact Match (EM) 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 | Situational Question Answering |
| Dataset (including any stated split) | SQA3D |
| Metric | Exact Match (EM) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Exact Match (EM)](<https://www.sota2.com/research/sota/situational-question-answering-on-sqa3d.md?metric=Exact%20Match%20(EM)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Exact Match (EM) | Result date | Report paper |
| --- | --- | --- | --- |
| Video-3D LLM† | 0.603 | Not recorded | 69e7051c7d0172140ec7f281 |
| Geo3DPruner | 0.596 | Not recorded | 69e7051c7d0172140ec7f281 |
| Video-3D LLM | 0.586 | Not recorded | 69e7051c7d0172140ec7f281 |
| Geo3DPruner | 0.583 | Not recorded | 69e7051c7d0172140ec7f281 |
| Geo3DPruner | 0.558 | Not recorded | 69e7051c7d0172140ec7f281 |
| LLaVA-3D | 0.556 | Not recorded | 69e7051c7d0172140ec7f281 |
| LEO | 0.5 | Not recorded | 69e7051c7d0172140ec7f281 |
| ScanQA | 0.472 | Not recorded | 69e7051c7d0172140ec7f281 |

### Video-3D LLM†

Exact Match (EM): 0.603. Result ID: 69e7770147f34ce924cf486a.

[Reporting paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea7494d.md>)

[Implementation](<https://github.com/LaVi-Lab/Video-3D-LLM>)

Recorded evaluation configuration: {"Video sequence length":"32","3D Encoder":"Additional 3D encoder"}. This record does not assert independent reproduction.

### Geo3DPruner

Exact Match (EM): 0.596. Result ID: 69e7770147f34ce924cf486b.

[Reporting paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

Recorded evaluation configuration: {"Video sequence length":"32","3D Encoder":"Additional 3D encoder","Reduction ratio":"↓60%"}. This record does not assert independent reproduction.

### Video-3D LLM

Exact Match (EM): 0.586. Result ID: 69e7770147f34ce924cf4869.

[Reporting paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea7494d.md>)

[Implementation](<https://github.com/LaVi-Lab/Video-3D-LLM>)

Recorded evaluation configuration: {"Video sequence length":"32"}. This record does not assert independent reproduction.

### Geo3DPruner

Exact Match (EM): 0.583. Result ID: 69e7770147f34ce924cf486c.

[Reporting paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

Recorded evaluation configuration: {"Video sequence length":"32","3D Encoder":"Additional 3D encoder","Reduction ratio":"↓80%"}. This record does not assert independent reproduction.

### Geo3DPruner

Exact Match (EM): 0.558. Result ID: 69e7770147f34ce924cf486d.

[Reporting paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

Recorded evaluation configuration: {"Video sequence length":"32","3D Encoder":"Additional 3D encoder","Reduction ratio":"↓90%"}. This record does not assert independent reproduction.

### LLaVA-3D

Exact Match (EM): 0.556. Result ID: 69e7770147f34ce924cf4868.

[Reporting paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

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

### LEO

Exact Match (EM): 0.5. Result ID: 69e7770147f34ce924cf4867.

[Reporting paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732c1e209131cea5aefe.md>)

[Implementation](<https://embodied-generalist.github.io/>)

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

### ScanQA

Exact Match (EM): 0.472. Result ID: 69e7770147f34ce924cf4866.

[Reporting paper](<https://www.sota2.com/research/paper/69e7051c7d0172140ec7f281.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c781e209131cea341f7.md>)

[Implementation](<https://github.com/ATR-DBI/ScanQA>)

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.