News
Meta introduces Ember model for agent tasks
Small reasoning model optimized for tool calling, coding, and document parsing, matching Claude Haiku 5.5’s top reasoning score at about one‑third the cost and outperforming GPT‑6 Luna.
News
Small reasoning model optimized for tool calling, coding, and document parsing, matching Claude Haiku 5.5’s top reasoning score at about one‑third the cost and outperforming GPT‑6 Luna.