# Agent Navigation on Masa 10 x 10 grid (test)

Source: [Agent Navigation on Masa 10 x 10 grid (test)](<https://www.sota2.com/research/sota/agent-navigation-on-masa-10-x-10-grid-test>)

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

Data updated: 2026-02-26T05:42:22.077Z

Evaluation of agent navigation performance within the Masa 10x10 grid environment, specifically on the test split.

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 | Agent Navigation |
| Dataset (including any stated split) | Masa 10 x 10 grid (test) |
| Metric | Error Rate (C=12) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Error Rate (C=12)](<https://www.sota2.com/research/sota/agent-navigation-on-masa-10-x-10-grid-test.md?metric=Error%20Rate%20(C%3D12)>): Lower is better; unit: SCALAR.

- [Error Rate (C=13)](<https://www.sota2.com/research/sota/agent-navigation-on-masa-10-x-10-grid-test.md?metric=Error%20Rate%20(C%3D13)>): Lower is better; unit: SCALAR.

- [Error Rate (C=14)](<https://www.sota2.com/research/sota/agent-navigation-on-masa-10-x-10-grid-test.md?metric=Error%20Rate%20(C%3D14)>): Lower is better; unit: SCALAR.

- [Error Rate (C=15)](<https://www.sota2.com/research/sota/agent-navigation-on-masa-10-x-10-grid-test.md?metric=Error%20Rate%20(C%3D15)>): Lower is better; unit: SCALAR.

- [Error Rate (C=16)](<https://www.sota2.com/research/sota/agent-navigation-on-masa-10-x-10-grid-test.md?metric=Error%20Rate%20(C%3D16)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Error Rate (C=12) | Result date | Report paper |
| --- | --- | --- | --- |
| Random | 0.0314 | Not recorded | 68fa73791e209131cea5cc4b |
| DiT | 0.0923 | Not recorded | 68fa73791e209131cea5cc4b |
| GOMAA-Geo | 0.2427 | Not recorded | 68fa73791e209131cea5cc4b |

### Random

Error Rate (C=12): 0.0314. Result ID: 6992e3673a6c314849122df9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73791e209131cea5cc4b.md>)

Recorded evaluation configuration: {"Step Budget (B)":"20","Grid Setting":"10 x 10","Training Configuration":"5 x 5 grid","Generalization Mode":"Zero-shot"}. This record does not assert independent reproduction.

### DiT

Error Rate (C=12): 0.0923. Result ID: 6992e3673a6c314849122dfa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73791e209131cea5cc4b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b46.md>)

Recorded evaluation configuration: {"Step Budget (B)":"20","Grid Setting":"10 x 10","Training Configuration":"5 x 5 grid","Generalization Mode":"Zero-shot"}. This record does not assert independent reproduction.

### GOMAA-Geo

Error Rate (C=12): 0.2427. Result ID: 6992e3673a6c314849122dfb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73791e209131cea5cc4b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73791e209131cea5cc4b.md>)

Recorded evaluation configuration: {"Step Budget (B)":"20","Grid Setting":"10 x 10","Training Configuration":"5 x 5 grid","Generalization Mode":"Zero-shot"}. This record does not assert independent reproduction.

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