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 8 · SOTA2 Research

Research Datasets

SMAC

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Multi-agent Reinforcement Learning

SMAC zerg_5v5 v2 (test)

14.9Reward

5

Multi-agent Reinforcement Learning

SMAC terran_5v5 v2 (test)

17.9Reward

5

Multi-agent Reinforcement Learning

SMAC protoss_5v5 v2 (test)

17.8Reward

5

Attack Detection

SMAC 27m_vs_30m

91F1 Score

5

Attack Detection

SMAC bane_vs_bane

90F1 Score

5

Attack Detection

SMAC 8m

86F1 Score

5

Attack Detection

SMAC 1c3s5z

82F1 Score

5

Offline Multi-Agent Reinforcement Learning

SMAC

973s5z Win Rate

5

Multi-Agent Reinforcement Learning

SMAC 3s5z (medium replay)

80.625Median Win Rate

5

Multi-Agent Reinforcement Learning

SMAC 3s5z (medium)

86.719Median Win Rate

5

Multi-Agent Reinforcement Learning

SMAC 5m_vs_6m (medium replay)

71.484Median Win Rate

5

Multi-Agent Reinforcement Learning

SMAC 5m_vs_6m (medium)

69.531Median Win Rate

5

Multi-Agent Reinforcement Learning

SMAC 6h_vs_8z medium

60.078Median Win Rate

5

Multi-Agent Reinforcement Learning

SMAC 6h_vs_8z (medium replay)

71.25Median Win Rate

5

Multi-agent Reinforcement Learning

SMAC MMM (Heterog.)

85.7Win Rate

5

Multi-agent Reinforcement Learning

SMAC 1c3s5z Heterog.

87.6Win Rate

5

Multi-agent Reinforcement Learning

SMAC 2s3z (Heterog.)

84.6Win Rate

5

Multi-agent Reinforcement Learning

SMAC corridor Homog.

76.8Win Rate

5

Multi-agent Reinforcement Learning

SMAC baneling (Homog.)

92.7Win Rate

5

Multi-agent Reinforcement Learning

SMAC 2c_vs_64zg Homog.

29.8Win Rate

5

Multi-agent Reinforcement Learning

SMAC 3s_vs_5z Homog

80.4Win Rate

5

Multi-agent Reinforcement Learning

SMAC 3s_vs_4z (Homog.)

77.3Win Rate

5

Multi-agent Reinforcement Learning

SMAC 3s_vs_3z Homog.

97.3Win Rate

5

Multi-agent Reinforcement Learning

SMAC 8m (Homog.)

89.1Win Rate

5

Multi-agent Reinforcement Learning

SMAC 3m (Homog.)

96.2Win Rate

5

Page 8 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