Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Vision-and-Language Navigation research benchmarks – Page 3 · SOTA2 Research

Vision-and-Language Navigation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Real-world scenario Lobby

78Success Rate

12

May 14, 2026

Real-world scenario Gym

83Success Rate

12

May 14, 2026

Office Real-world scenario

67Success Rate

12

May 14, 2026

MapGPT (GPT-4V)

43.7Success Rate (SR)

12

Mar 11, 2026

R2R Discrete (val-unseen)

2.09Navigation Error (NE)

12

Feb 26, 2026

Touchdown Unseen (test)

27nDTW

11

Feb 26, 2026

A2A whole (full)

87Success Rate (SR)

10

Mar 27, 2026

A2A high-complexity portion subtask >= 3

80Success Rate (SR)

10

Mar 27, 2026

REVERIE Unseen Discrete (val)

63.9OSR

10

Feb 26, 2026

52.44TC

10

Feb 26, 2026

0.57TC

10

Feb 26, 2026

SOON unseen house (test)

90.4Success Rate

10

Feb 26, 2026

map2seq Unseen (test)

46.1nDTW

10

Feb 26, 2026

map2seq Seen (test)

67.3nDTW

10

Feb 26, 2026

OpenUAV UM Hard (test)

90.96Navigation Error (NE)

9

May 28, 2026

OpenUAV Easy Unseen Map UM (test)

45Navigation Error (NE)

9

May 28, 2026

OpenUAV Full UM (test Unseen-Map)

203NE

9

May 28, 2026

HA-VLNCE (val seen)

63.09TCR

9

May 14, 2026

IR2R-CE (val-unseen)

11.4TL (Task Length Success Rate)

9

Feb 26, 2026

GSA basic (test)

79.04SR

9

Feb 26, 2026

SOON seen house (val)

7,630SR

9

Feb 26, 2026

Touchdown seen (dev)

ORAR full model

28.3SDTW

9

Feb 26, 2026

RxR (Room-Across-Room) seen (val)

EnvEdit (on HAMT)

67.2SR

9

Feb 26, 2026

Room-to-Room (R2R) Unseen (test)

8.13TL

9

Feb 26, 2026

4.9Navigation Error (NE)

8

Jun 9, 2026

Page 3 of 6

Popular datasets

R2R Room-to-Room SOON REVERIE map2seq

Follow for updates

Join SOTA2 Contact