| Benchmark | Model | Rank | Results |
|---|---|---|---|
| vision-and-language-navigation-on-touchdown | VLN Transformer +M-50 +style | #4 | Task Completion (TC): 16.2 |
| vision-and-language-navigation-on-touchdown | VLN Transformer | #5 | Task Completion (TC): 14.9 |
| vision-and-language-navigation-on-touchdown | Gated Attention (GA) | #7 | Task Completion (TC): 11.9 |
| vision-and-language-navigation-on-touchdown | RConcat | #8 | Task Completion (TC): 11.8 |