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 Strategic Reasoning research benchmarks · SOTA2 Research

Multi-Agent Strategic Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

ConnectFour OOD

99.93First-mover Normalized Score

18

May 7, 2026

SimpleHanabi OOD

Gemini-2.5-flash

73.1Collective Avg Normalized Score

9

May 7, 2026

LeducHoldem OOD

Gemini-2.5-flash

83.51First-mover Normalized Score

9

May 7, 2026

Tic-Tac-Toe (In-domain)

67.2Success Rate

8

Mar 5, 2026

Kuhn Poker In-domain

65.6Success Rate

8

Mar 5, 2026

Popular datasets

tic-tac-toe Kuhn Poker ConnectFour LeducHoldem SimpleHanabi

Follow for updates

Join SOTA2 Contact