# Zero-Shot Aerial Navigation on AerialVLN (test)

Source: [Zero-Shot Aerial Navigation on AerialVLN (test)](<https://www.sota2.com/research/sota/zero-shot-aerial-navigation-on-aerialvln-test>)

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

Data updated: 2026-02-26T06:05:40.884Z

Evaluation of Zero-Shot Aerial Navigation performance on the test split of the AerialVLN dataset, reporting metrics like Success Rate (SR), Navigation Error (NE), and Time.

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 | Zero-Shot Aerial Navigation |
| Dataset (including any stated split) | AerialVLN (test) |
| Metric | Success Rate (SR) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [Success Rate (SR)](<https://www.sota2.com/research/sota/zero-shot-aerial-navigation-on-aerialvln-test.md?metric=Success%20Rate%20(SR)>): Higher is better; unit: PERCENT.

- [Navigation Error (NE)](<https://www.sota2.com/research/sota/zero-shot-aerial-navigation-on-aerialvln-test.md?metric=Navigation%20Error%20(NE)>): Lower is better; unit: SCALAR.

- [Time](<https://www.sota2.com/research/sota/zero-shot-aerial-navigation-on-aerialvln-test.md?metric=Time>): Lower is better; unit: TIME.

## Recorded results

| Method | Success Rate (SR) | Result date | Report paper |
| --- | --- | --- | --- |
| Fly0 | 70.43 | Not recorded | 6996992809c33900fcd71f51 |
| Fly0 | 62.86 | Not recorded | 6996992809c33900fcd71f51 |
| SPF | 46.72 | Not recorded | 6996992809c33900fcd71f51 |
| OpenFly | 37.72 | Not recorded | 6996992809c33900fcd71f51 |
| UAV-Flow | 36.47 | Not recorded | 6996992809c33900fcd71f51 |
| SPF | 35.07 | Not recorded | 6996992809c33900fcd71f51 |
| NAVGPT | 34.04 | Not recorded | 6996992809c33900fcd71f51 |
| STMR | 30.15 | Not recorded | 6996992809c33900fcd71f51 |
| OpenFly | 29.08 | Not recorded | 6996992809c33900fcd71f51 |
| CityNavAgent | 28.97 | Not recorded | 6996992809c33900fcd71f51 |
| UAV-Flow | 27.46 | Not recorded | 6996992809c33900fcd71f51 |
| NAVGPT | 26.31 | Not recorded | 6996992809c33900fcd71f51 |
| STMR | 22.61 | Not recorded | 6996992809c33900fcd71f51 |
| CityNavAgent | 22.17 | Not recorded | 6996992809c33900fcd71f51 |
| OpenUAV | 20.41 | Not recorded | 6996992809c33900fcd71f51 |
| OpenUAV | 13.19 | Not recorded | 6996992809c33900fcd71f51 |
| AerialVLN | 7.28 | Not recorded | 6996992809c33900fcd71f51 |
| AerialVLN | 3.95 | Not recorded | 6996992809c33900fcd71f51 |

### Fly0

Success Rate (SR): 70.43. Result ID: 699ae8935698665ec4790618.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot","Backbone MLLM":"Qwen2.5VL-32B"}. This record does not assert independent reproduction.

### Fly0

Success Rate (SR): 62.86. Result ID: 699ae8935698665ec479062a.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot","Backbone MLLM":"Qwen2.5VL-32B"}. This record does not assert independent reproduction.

### SPF

Success Rate (SR): 46.72. Result ID: 699ae8935698665ec4790617.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c251e209131cea8cb15.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot"}. This record does not assert independent reproduction.

### OpenFly

Success Rate (SR): 37.72. Result ID: 699ae8935698665ec4790613.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea822dc.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"End to End"}. This record does not assert independent reproduction.

### UAV-Flow

Success Rate (SR): 36.47. Result ID: 699ae8935698665ec4790611.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a770.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"End to End"}. This record does not assert independent reproduction.

### SPF

Success Rate (SR): 35.07. Result ID: 699ae8935698665ec4790629.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c251e209131cea8cb15.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot"}. This record does not assert independent reproduction.

### NAVGPT

Success Rate (SR): 34.04. Result ID: 699ae8935698665ec4790614.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e61e209131cea4dd16.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot"}. This record does not assert independent reproduction.

### STMR

Success Rate (SR): 30.15. Result ID: 699ae8935698665ec4790615.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8b1e209131cea83cd6.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot"}. This record does not assert independent reproduction.

### OpenFly

Success Rate (SR): 29.08. Result ID: 699ae8935698665ec4790625.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea822dc.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"End to End"}. This record does not assert independent reproduction.

### CityNavAgent

Success Rate (SR): 28.97. Result ID: 699ae8935698665ec4790616.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75ac1e209131cea69341.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot"}. This record does not assert independent reproduction.

### UAV-Flow

Success Rate (SR): 27.46. Result ID: 699ae8935698665ec4790623.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a770.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"End to End"}. This record does not assert independent reproduction.

### NAVGPT

Success Rate (SR): 26.31. Result ID: 699ae8935698665ec4790626.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e61e209131cea4dd16.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot"}. This record does not assert independent reproduction.

### STMR

Success Rate (SR): 22.61. Result ID: 699ae8935698665ec4790627.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8b1e209131cea83cd6.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot"}. This record does not assert independent reproduction.

### CityNavAgent

Success Rate (SR): 22.17. Result ID: 699ae8935698665ec4790628.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75ac1e209131cea69341.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"Zero Shot"}. This record does not assert independent reproduction.

### OpenUAV

Success Rate (SR): 20.41. Result ID: 699ae8935698665ec4790610.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa751e1e209131cea65e52.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"End to End"}. This record does not assert independent reproduction.

### OpenUAV

Success Rate (SR): 13.19. Result ID: 699ae8935698665ec4790622.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa751e1e209131cea65e52.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"End to End"}. This record does not assert independent reproduction.

### AerialVLN

Success Rate (SR): 7.28. Result ID: 699ae8935698665ec4790612.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70591e209131cea4a79c.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"End to End"}. This record does not assert independent reproduction.

### AerialVLN

Success Rate (SR): 3.95. Result ID: 699ae8935698665ec4790624.

[Reporting paper](<https://www.sota2.com/research/paper/6996992809c33900fcd71f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70591e209131cea4a79c.md>)

Recorded evaluation configuration: {"Evaluation Paradigm":"End to End"}. This record does not assert independent reproduction.

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