# Active embodied question answering on Habitat HM3D (val)

Source: [Active embodied question answering on Habitat HM3D (val)](<https://www.sota2.com/research/sota/active-embodied-question-answering-on-habitat-hm3d-val>)

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

Data updated: 2026-05-19T13:53:17.603Z

Evaluation of model performance on the validation split of the Habitat HM3D dataset for the Active Embodied Question Answering task, reporting metrics such as Score, Mean Trajectory length, and SPL.

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 | Active embodied question answering |
| Dataset (including any stated split) | Habitat HM3D (val) |
| Metric | Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/active-embodied-question-answering-on-habitat-hm3d-val.md?metric=Score>): Higher is better; unit: PERCENT.

- [Mean Trajectory Length](<https://www.sota2.com/research/sota/active-embodied-question-answering-on-habitat-hm3d-val.md?metric=Mean%20Trajectory%20Length>): Lower is better; unit: SCALAR.

- [SPL](<https://www.sota2.com/research/sota/active-embodied-question-answering-on-habitat-hm3d-val.md?metric=SPL>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| Robo-Cortex++ | 30.59 | Not recorded | 6a0beefbdbc836b87d82c961 |
| Robo-Cortex | 29.78 | Not recorded | 6a0beefbdbc836b87d82c961 |
| World-In-World | 27.19 | Not recorded | 6a0beefbdbc836b87d82c961 |
| MapGPT | 25.5 | Not recorded | 6a0beefbdbc836b87d82c961 |
| WMNav | 19.5 | Not recorded | 6a0beefbdbc836b87d82c961 |

### Robo-Cortex++

Score: 30.59. Result ID: 6a0c6ac3fbc373592c044e6e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beefbdbc836b87d82c961.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0beefbdbc836b87d82c961.md>)

Recorded evaluation configuration: {"Setting":"Adaptive"}. This record does not assert independent reproduction.

### Robo-Cortex

Score: 29.78. Result ID: 6a0c6ac3fbc373592c044e6d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beefbdbc836b87d82c961.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0beefbdbc836b87d82c961.md>)

Recorded evaluation configuration: {"Setting":"Static"}. This record does not assert independent reproduction.

### World-In-World

Score: 27.19. Result ID: 6a0c6ac3fbc373592c044e6c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beefbdbc836b87d82c961.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c511e209131cea8d831.md>)

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

### MapGPT

Score: 25.5. Result ID: 6a0c6ac3fbc373592c044e6a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beefbdbc836b87d82c961.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e4.md>)

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

### WMNav

Score: 19.5. Result ID: 6a0c6ac3fbc373592c044e6b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beefbdbc836b87d82c961.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a1b1e209131cea81387.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.