test_an

Reported on 5 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots5 results

Vision and Language NavigationonVLN Challenge
error
7.47
best: 1.61 (human)
Vision and Language NavigationonVLN Challenge
length
10.92
best: 1257.38 (Speaker-Follower)
Vision and Language NavigationonVLN Challenge
oracle success
0.34
best: 1 (FOAM-Beam Search)
Vision and Language NavigationonVLN Challenge
spl
0.21
best: 0.76 (human)
Vision and Language NavigationonVLN Challenge
success
0.26
best: 0.86 (human)