# Navigation from Dialog History on NDH Unseen (test)

Source: [Navigation from Dialog History on NDH Unseen (test)](<https://www.sota2.com/research/sota/navigation-from-dialog-history-on-ndh-unseen-test>)

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

Data updated: 2026-02-26T05:46:01.012Z

Evaluation of performance for Navigation from Dialog History on the unseen test split of the NDH dataset, measured using Goal Progress variants.

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 | Navigation from Dialog History |
| Dataset (including any stated split) | NDH (Navigation from Dialog History) Unseen (test) |
| Metric | Goal Progress (Oracle) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Goal Progress (Oracle)](<https://www.sota2.com/research/sota/navigation-from-dialog-history-on-ndh-unseen-test.md?metric=Goal%20Progress%20(Oracle)>): Higher is better; unit: SCALAR.

- [Goal Progress (Navigator)](<https://www.sota2.com/research/sota/navigation-from-dialog-history-on-ndh-unseen-test.md?metric=Goal%20Progress%20(Navigator)>): Higher is better; unit: SCALAR.

- [Goal Progress (Mixed)](<https://www.sota2.com/research/sota/navigation-from-dialog-history-on-ndh-unseen-test.md?metric=Goal%20Progress%20(Mixed)>): Higher is better; unit: SCALAR.

- [Goal Progress](<https://www.sota2.com/research/sota/navigation-from-dialog-history-on-ndh-unseen-test.md?metric=Goal%20Progress>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Goal Progress (Oracle) | Result date | Report paper |
| --- | --- | --- | --- |
| HOP (2) | 2.99 | Not recorded | 68fa6c0d1e209131cea31b5d |
| HOP (1) | 2.92 | Not recorded | 68fa6c0d1e209131cea31b5d |
| ORIST | 2.78 | Not recorded | 68fa6c0d1e209131cea31b5d |
| CMN | 2.69 | Not recorded | 68fa6c0d1e209131cea31b5d |
| HOP (0) | 2.05 | Not recorded | 68fa6c0d1e209131cea31b5d |
| PREVALENT | 1.67 | Not recorded | 68fa6c0d1e209131cea31b5d |
| Seq2Seq | 1.25 | Not recorded | 68fa6c0d1e209131cea31b5d |

### HOP (2)

Goal Progress (Oracle): 2.99. Result ID: 698ebddfffc3901de0a04620.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Implementation](<https://github.com/YanyuanQiao/HOP-VLN>)

Recorded evaluation configuration: {"pre-training":"PREVALENT + BnB data","description":"finetuned model pre-trained on data of both PREVALENT and processed data from BnB"}. This record does not assert independent reproduction.

### HOP (1)

Goal Progress (Oracle): 2.92. Result ID: 698ebddfffc3901de0a0461f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Implementation](<https://github.com/YanyuanQiao/HOP-VLN>)

Recorded evaluation configuration: {"pre-training":"PREVALENT data","description":"finetuned model pre-trained on the same data as PREVALENT"}. This record does not assert independent reproduction.

### ORIST

Goal Progress (Oracle): 2.78. Result ID: 698ebddfffc3901de0a0461d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a951e209131cea290dd.md>)

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

### CMN

Goal Progress (Oracle): 2.69. Result ID: 698ebddfffc3901de0a0461b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67341e209131cea14b60.md>)

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

### HOP (0)

Goal Progress (Oracle): 2.05. Result ID: 698ebddfffc3901de0a0461e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Implementation](<https://github.com/YanyuanQiao/HOP-VLN>)

Recorded evaluation configuration: {"pre-training":"none","description":"baseline model without pre-training"}. This record does not assert independent reproduction.

### PREVALENT

Goal Progress (Oracle): 1.67. Result ID: 698ebddfffc3901de0a0461c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67581e209131cea15b3c.md>)

[Implementation](<https://github.com/weituo12321/PREVALENT>)

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

### Seq2Seq

Goal Progress (Oracle): 1.25. Result ID: 698ebddfffc3901de0a0461a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66811e209131cea10bdb.md>)

[Implementation](<https://cvdn.dev/>)

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.