Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
MindAgentmindagent.github.io · Low evidenceMindAgent is an infrastructure for emergent gaming interaction that enables multi-NPC and human-NPC collaboration. It leverages large language models to evaluate planning and coordination capabilities in multi-agent systems, including a new gaming benchmark called CUISINEWORLD.
Parse Score