List your company

Multi-agent Game Playing on Avalon Homogeneous Teams (test)

95Win Rate (vs. Rand)GRAIL
-3.821.8547.573.15Jun 21, 2025

Evaluation results

MethodLinks
GRAILTeam Type=Homogeneous, Underlying LLM=GPT-4.12025.069545709075
DeepSeek-R1Team Type=Homogeneous2025.069035709071
ReConTeam Type=Homogeneous, Underlying LLM=GPT-4.12025.068015502543
GPT-o4-miniTeam Type=Homogeneous2025.06705255040
RandTeam Type=Homogeneous2025.0600000