Holo4 is a new series of agentic models (27B dense and 35B-A3B MoE) that can interact with software through GUIs, code, APIs, and MCP tools across desktop, web, and mobile platforms. Trained via supervised learning and reinforcement learning on 10,000 tasks from an internal Agentic Task Factory, Holo4 27B scores 61.7% on OSWorld 2.0 at $0.08 per task, competing with frontier models at significantly lower cost.
Holo4 is a new series of agentic models (27B dense and 35B-A3B MoE) designed for computer-use tasks that interact with software through GUIs, code, APIs, and MCP. Trained via supervised and reinforcement learning on diverse environments, it scores competitively with frontier models on academic benchmarks like OSWorld 2.0 while operating at significantly lower cost and parameter count.