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

Embodied decision-making research benchmarks · SOTA2 Research

Embodied decision-making

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

100Success Rate

51

Jun 15, 2026

ALFWorld held-out (test)

95.5Score

49

May 25, 2026

ALFWorld (test)

89.4Task Success Rate

24

Jun 19, 2026

ALFWorld (ID and OOD)

92.86Success Rate

16

Mar 10, 2026

Game for Peace 1.0 (test)

71.4Parachuting Score

6

Feb 26, 2026

Popular datasets

AlfWorld Game for Peace

Follow for updates

Join SOTA2 Contact