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

SMAC dataset and benchmarks – Page 2 · SOTA2 Research

Research Datasets

SMAC

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Multi-Agent Reinforcement Learning

SMAC 3s5z v1 (test)

92.7Win Rate

13

SMAC

93.7Win Rate

13

Adversarial Attack

SMAC 27m_vs_30m

19.24Reward

12

Adversarial Attack

SMAC bane_vs_bane

20Reward

12

Adversarial Attack

SMAC 8m

20Reward

12

Adversarial Attack

SMAC 1c3s5z

20Reward

12

Multi-agent reinforcement learning on Unseen Tasks

SMAC Stalker-Zealot Medium quality

70.61s3z Performance

12

Multi-Agent Reinforcement Learning

SMAC 2m1z

0.038State Entropy

12

SMAC

96.5Win Rate

12

SMAC

99.8Win Rate

12

SMAC

100Win Rate

12

Multi-Agent Cooperative Control

SMAC 3m v1 (train)

100Win Rate

12

Multi-Agent Reinforcement Learning

SMAC corridor (test)

20Average Score

12

Multi-Agent Reinforcement Learning

SMAC 6h_vs_8z (test)

19.4Average Score

12

Cooperative Multi-Agent Reinforcement Learning

SMAC 3s5z map

18.7Return

11

Cooperative Multi-Agent Reinforcement Learning

SMAC 5m_vs_6m map

19.1Return

11

Cooperative Multi-Agent Reinforcement Learning

SMAC 8m map

17.8Return

11

Cooperative Multi-Agent Reinforcement Learning

SMAC 3m map

19.8Return

11

Decision Inference

SMAC

76.4Accuracy

11

Multi-agent reinforcement learning

SMAC 5v5 v2

17.4Protoss Reward

10

Multi-agent Coordination

SMAC Zerg 5v5 v2

39Median Win Rate

10

Multi-agent Coordination

SMAC Terran 5v5 v2

39Median Win Rate

10

Multi-Agent Reinforcement Learning

SMAC 1c3s5z (test)

100Test Win Rate

10

Multi-Agent Reinforcement Learning

SMAC v2

19.9Protoss Score

9

Multi-Agent Reinforcement Learning

SMAC 8m

87Disparity (Dis-1)

9

Page 2 of 12

Popular tasks

Multi-Agent Reinforcement Learning Multi-Agent Cooperative Control Multi-agent Micromanagement Cooperative Multi-Agent Reinforcement Learning Offline Multi-Agent Reinforcement Learning

Follow for updates

Join SOTA2 Contact