Kimi K2.5: Open-Source Multimodal AI Model with Visual Agentic Intelligence and Agent Swarm Capabilities

Summary

Kimi K2.5 is introduced as the most powerful open-source model to date, building on Kimi K2 with continued pretraining on approximately 15 trillion mixed visual and text tokens. As a native multimodal model, it delivers state-of-the-art coding and vision capabilities along with a self-directed agent swarm paradigm. For complex tasks, Kimi K2.5 can self-direct an agent swarm with up to 100 sub-agents, executing parallel workflows across up to 1,500 tool calls, reducing execution time by up to 4.5x compared to single-agent setups. The model defines Visual Agentic Intelligence and represents a significant advancement in AI capabilities.