# Vision-and-Language Navigation on GSA-R2R N-Scene (test)

Source: [Vision-and-Language Navigation on GSA-R2R N-Scene (test)](<https://www.sota2.com/research/sota/vision-and-language-navigation-on-gsa-r2r-n-scene-test>)

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

Data updated: 2026-05-13T10:25:12.632Z

Evaluation of Vision-and-Language Navigation performance on the 'test' split of the GSA-R2R N-Scene dataset, reporting metrics including TL, NE, SR, SPL, and nDTW.

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 | Vision-and-Language Navigation |
| Dataset (including any stated split) | GSA-R2R N-Scene (test) |
| Metric | SR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 37 of 37 |
| 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

- [SR](<https://www.sota2.com/research/sota/vision-and-language-navigation-on-gsa-r2r-n-scene-test.md?metric=SR>): Higher is better; unit: PERCENT.

- [TL](<https://www.sota2.com/research/sota/vision-and-language-navigation-on-gsa-r2r-n-scene-test.md?metric=TL>): Lower is better; unit: SCALAR.

- [NE](<https://www.sota2.com/research/sota/vision-and-language-navigation-on-gsa-r2r-n-scene-test.md?metric=NE>): Lower is better; unit: SCALAR.

- [SPL](<https://www.sota2.com/research/sota/vision-and-language-navigation-on-gsa-r2r-n-scene-test.md?metric=SPL>): Higher is better; unit: PERCENT.

- [nDTW](<https://www.sota2.com/research/sota/vision-and-language-navigation-on-gsa-r2r-n-scene-test.md?metric=nDTW>): Higher is better; unit: PERCENT.

## Recorded results

| Method | SR | Result date | Report paper |
| --- | --- | --- | --- |
| NavGPT-2 (FlanT5-5B) | 57 | Not recorded | 68fa7bc01e209131cea8a306 |
| SkillNav (ScaleVLN-Aug) | 57 | Not recorded | 68fa7bc01e209131cea8a306 |
| NavGPT-2 | 56.67 | Not recorded | 69687494e25ad2fa9d1ec56b |
| slow4fast-VLN | 55.1 | Not recorded | 69687494e25ad2fa9d1ec56b |
| ScaleVLN | 55 | Not recorded | 68fa7bc01e209131cea8a306 |
| SkillNav (SRDF-Aug) | 54 | Not recorded | 68fa7bc01e209131cea8a306 |
| SRDF | 52 | Not recorded | 68fa7bc01e209131cea8a306 |
| slow4fast-VLN | 50.7 | Not recorded | 69687494e25ad2fa9d1ec56b |
| Memoir (Ours) | 50.2 | Not recorded | 68fa7bfb1e209131cea8b980 |
| GR-DUET | 48.1 | Not recorded | 69687494e25ad2fa9d1ec56b |
| GR-DUET | 48.1 | Not recorded | 68fa7bfb1e209131cea8b980 |
| GR-DUET | 48 | Not recorded | 68fa7bc01e209131cea8a306 |
| GR-DUET\* | 47.1 | Not recorded | 68fa7bfb1e209131cea8b980 |
| Memoir (w/o retrieval) | 43.3 | Not recorded | 68fa7bfb1e209131cea8b980 |
| +SAR | 41.4 | Not recorded | 69687494e25ad2fa9d1ec56b |
| DUET + SAR | 41.4 | Not recorded | 68fa7bfb1e209131cea8b980 |
| +BT | 41.2 | Not recorded | 69687494e25ad2fa9d1ec56b |
| DUET + BT | 41.2 | Not recorded | 68fa7bfb1e209131cea8b980 |
| +TENT | 40.6 | Not recorded | 69687494e25ad2fa9d1ec56b |
| DUET + TENT | 40.6 | Not recorded | 68fa7bfb1e209131cea8b980 |
| DUET | 40 | Not recorded | 68fa7bc01e209131cea8a306 |
| +MLM | 39.8 | Not recorded | 69687494e25ad2fa9d1ec56b |
| DUET + MLM | 39.8 | Not recorded | 68fa7bfb1e209131cea8b980 |
| +MRC | 39.7 | Not recorded | 69687494e25ad2fa9d1ec56b |
| DUET + MRC | 39.7 | Not recorded | 68fa7bfb1e209131cea8b980 |
| DUET | 39.6 | Not recorded | 69687494e25ad2fa9d1ec56b |
| DUET | 39.6 | Not recorded | 68fa7bfb1e209131cea8b980 |
| BEVBERT | 39 | Not recorded | 68fa7bc01e209131cea8a306 |
| HAMT | 34 | Not recorded | 68fa7bc01e209131cea8a306 |
| NavCoT | 29 | Not recorded | 69687494e25ad2fa9d1ec56b |
| NavCoT (LLaMA2) | 29 | Not recorded | 68fa7bc01e209131cea8a306 |
| MapGPT (GPT4v) | 25 | Not recorded | 68fa7bc01e209131cea8a306 |
| MapGPT | 24.67 | Not recorded | 69687494e25ad2fa9d1ec56b |
| OVER-NAV | 16.7 | Not recorded | 69687494e25ad2fa9d1ec56b |
| OVER-NAV | 16.7 | Not recorded | 68fa7bfb1e209131cea8b980 |
| TourHAMT | 9.7 | Not recorded | 69687494e25ad2fa9d1ec56b |
| TourHAMT | 9.7 | Not recorded | 68fa7bfb1e209131cea8b980 |

### NavGPT-2 (FlanT5-5B)

SR: 57. Result ID: 6a04517047f34ce924ead5d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74dc1e209131cea643f0.md>)

Recorded evaluation configuration: {"Backbone":"FlanT5-5B"}. This record does not assert independent reproduction.

### SkillNav (ScaleVLN-Aug)

SR: 57. Result ID: 6a04517047f34ce924ead5d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

Recorded evaluation configuration: {"large-scale data augmentation":"true","visual encoder":"CLIP-B/16","language backbone":"BERT-base-uncased","action router":"GPT-4o"}. This record does not assert independent reproduction.

### NavGPT-2

SR: 56.67. Result ID: 6997c1d55698665ec418a8bf.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74dc1e209131cea643f0.md>)

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

### slow4fast-VLN

SR: 55.1. Result ID: 6997c1d55698665ec418a8c0.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

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

### ScaleVLN

SR: 55. Result ID: 6a04517047f34ce924ead5d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70491e209131cea4a363.md>)

Recorded evaluation configuration: {"large-scale data augmentation":"true"}. This record does not assert independent reproduction.

### SkillNav (SRDF-Aug)

SR: 54. Result ID: 6a04517047f34ce924ead5d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

Recorded evaluation configuration: {"large-scale data augmentation":"true","visual encoder":"InternViT-6B","action router":"GPT-4o"}. This record does not assert independent reproduction.

### SRDF

SR: 52. Result ID: 6a04517047f34ce924ead5d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77261e209131cea7167c.md>)

Recorded evaluation configuration: {"large-scale data augmentation":"true"}. This record does not assert independent reproduction.

### slow4fast-VLN

SR: 50.7. Result ID: 6997c1d55698665ec418a8a4.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

Recorded evaluation configuration: {"adaptation\_category":"Memory-Based"}. This record does not assert independent reproduction.

### Memoir (Ours)

SR: 50.2. Result ID: 69cb927947f34ce924b42a6a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

Recorded evaluation configuration: {"Pre-training":"Full navigation graph","Retrieval":"Enabled"}. This record does not assert independent reproduction.

### GR-DUET

SR: 48.1. Result ID: 6997c1d55698665ec418a8a3.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ca1e209131cea6f19e.md>)

Recorded evaluation configuration: {"adaptation\_category":"Memory-Based"}. This record does not assert independent reproduction.

### GR-DUET

SR: 48.1. Result ID: 69cb927947f34ce924b42a67.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ca1e209131cea6f19e.md>)

Recorded evaluation configuration: {"Pre-training":"Full navigation graph"}. This record does not assert independent reproduction.

### GR-DUET

SR: 48. Result ID: 6a04517047f34ce924ead5d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ca1e209131cea6f19e.md>)

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

### GR-DUET\*

SR: 47.1. Result ID: 69cb927947f34ce924b42a68.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ca1e209131cea6f19e.md>)

Recorded evaluation configuration: {"Pre-training":"Full navigation graph","Experimental conditions":"Aligned"}. This record does not assert independent reproduction.

### Memoir (w/o retrieval)

SR: 43.3. Result ID: 69cb927947f34ce924b42a69.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

Recorded evaluation configuration: {"Pre-training":"Full navigation graph","Retrieval":"Disabled"}. This record does not assert independent reproduction.

### +SAR

SR: 41.4. Result ID: 6997c1d55698665ec418a8a0.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e961e209131cea40e77.md>)

Recorded evaluation configuration: {"adaptation\_category":"Optimization-Based"}. This record does not assert independent reproduction.

### DUET + SAR

SR: 41.4. Result ID: 69cb927947f34ce924b42a66.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e961e209131cea40e77.md>)

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

### +BT

SR: 41.2. Result ID: 6997c1d55698665ec418a89e.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682b1e209131cea1a779.md>)

Recorded evaluation configuration: {"adaptation\_category":"Optimization-Based"}. This record does not assert independent reproduction.

### DUET + BT

SR: 41.2. Result ID: 69cb927947f34ce924b42a64.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682b1e209131cea1a779.md>)

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

### +TENT

SR: 40.6. Result ID: 6997c1d55698665ec418a89f.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.md>)

Recorded evaluation configuration: {"adaptation\_category":"Optimization-Based"}. This record does not assert independent reproduction.

### DUET + TENT

SR: 40.6. Result ID: 69cb927947f34ce924b42a65.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.md>)

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

### DUET

SR: 40. Result ID: 6a04517047f34ce924ead5d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6be11e209131cea30d3f.md>)

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

### +MLM

SR: 39.8. Result ID: 6997c1d55698665ec418a89c.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"adaptation\_category":"Optimization-Based"}. This record does not assert independent reproduction.

### DUET + MLM

SR: 39.8. Result ID: 69cb927947f34ce924b42a62.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.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.

### +MRC

SR: 39.7. Result ID: 6997c1d55698665ec418a89d.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa661c1e209131cea0e5d5.md>)

Recorded evaluation configuration: {"adaptation\_category":"Optimization-Based"}. This record does not assert independent reproduction.

### DUET + MRC

SR: 39.7. Result ID: 69cb927947f34ce924b42a63.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.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.

### DUET

SR: 39.6. Result ID: 6997c1d55698665ec418a89b.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6be11e209131cea30d3f.md>)

Recorded evaluation configuration: {"type":"Baseline"}. This record does not assert independent reproduction.

### DUET

SR: 39.6. Result ID: 69cb927947f34ce924b42a61.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6be11e209131cea30d3f.md>)

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

### BEVBERT

SR: 39. Result ID: 6a04517047f34ce924ead5d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703e1e209131cea49eaf.md>)

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

### HAMT

SR: 34. Result ID: 6a04517047f34ce924ead5d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70531e209131cea4a418.md>)

[Implementation](<https://cshizhe.github.io/projects/vln_hamt.html>)

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

### NavCoT

SR: 29. Result ID: 6997c1d55698665ec418a8be.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77971e209131cea7434e.md>)

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

### NavCoT (LLaMA2)

SR: 29. Result ID: 6a04517047f34ce924ead5cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77971e209131cea7434e.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA2"}. This record does not assert independent reproduction.

### MapGPT (GPT4v)

SR: 25. Result ID: 6a04517047f34ce924ead5ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a306.md>)

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

Recorded evaluation configuration: {"Backbone":"GPT4v"}. This record does not assert independent reproduction.

### MapGPT

SR: 24.67. Result ID: 6997c1d55698665ec418a8bd.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

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

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

### OVER-NAV

SR: 16.7. Result ID: 6997c1d55698665ec418a8a2.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b31e209131cea57ff4.md>)

Recorded evaluation configuration: {"adaptation\_category":"Memory-Based"}. This record does not assert independent reproduction.

### OVER-NAV

SR: 16.7. Result ID: 69cb927947f34ce924b42a60.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b31e209131cea57ff4.md>)

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

### TourHAMT

SR: 9.7. Result ID: 6997c1d55698665ec418a8a1.

[Reporting paper](<https://www.sota2.com/research/paper/69687494e25ad2fa9d1ec56b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a91e209131cea5267d.md>)

Recorded evaluation configuration: {"adaptation\_category":"Memory-Based"}. This record does not assert independent reproduction.

### TourHAMT

SR: 9.7. Result ID: 69cb927947f34ce924b42a5f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b980.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a91e209131cea5267d.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.
