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

Multi-agent coordination research benchmarks – Page 5 · SOTA2 Research

Multi-agent coordination

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Manufacturing size (evaluation)

100Success Rate

2

Feb 26, 2026

Overcooked unseen tasks, hard difficulty

43.7Completion Rate

2

Feb 26, 2026

Overcooked unseen tasks, medium difficulty

1Completion Rate

2

Feb 26, 2026

Hanabi 5-player JaxMARL

23.73SP Score

1

Feb 26, 2026

Hanabi 4-player JaxMARL

24.55SP

1

Feb 26, 2026

XOR game n=k=3 (train eval)

—

—Primary metric

0

May 11, 2026

Page 5 of 5

Popular datasets

Overcooked Overcooked-AI SMAC VirtualHome-Social Warehouse

Follow for updates

Join SOTA2 Contact