List your company

VillagerAgent Escape Room Challenge

73.29Completion Rate (%)VillagerAgent (gpt-4-1106-preview)
67.965269.347670.7372.1124Jun 9, 2024

Evaluation results

MethodLinks
VillagerAgent (gpt-4-1106-preview)Backbone=gpt-4-1106-preview2024.0673.29149.490.03
VillagerAgent (gpt-4-1106-preview, 3-agents)Backbone=gpt-4-1106-preview, Number of agents=32024.0669.78227.467.01
VillagerAgent (gemini-pro)Backbone=gemini-pro2024.0669.2153.380.35
VillagerAgent (glm-4)Backbone=glm-42024.0668.17100.895.3