Description

Xiaomi is publicly streaming the real-time reinforcement learning (RL) training process of its upcoming AI model, Mimo v2.6. The dashboard provides a rare glimpse into a frontier lab's training, displaying costs (over $1.6M so far), token counts (nearly 48B), batch sizes, and live benchmark performance improvements across various tasks like coding and general reasoning.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.