Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Co-work agents execute complex workflows that combine information gathering, tool use, coding, and file manipulation across many model invocations. Because cost and latency accumulate over the full episode, their practical value depends not only on peak capability but also on how efficiently that capability is delivered. Yet many steps in everyday work emphasize state tracking, coordination, recovery, and follow-through rather than frontier-scale reasoning. We present Occamy-1.0, a costefficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint. We construct execution-grounded data and environments, capture replayable long-horizon trajectories across multiple harnesses, and use staged post-training to develop and consolidate complementary execution capabilities. Across a broad suite of co-work benchmarks, Occamy-1.0 is consistently among the strongest comparably sized models and remains competitive with substantially larger frontier systems on several tasks. Under our stated evaluation and pricing protocol, its aggregate performance across four representative benchmarks places it at the low-cost knee of the observed cost–performance Pareto frontier.

Introduction. Co-work is an end-to-end workload. Digital agents are increasingly asked to carry out real work rather than answer isolated questions: update CRM records, complete finance workflows, operate an e-commerce business, or handle the everyday tasks involved in running a company. These settings combine dense context—customer histories, documents, policies, transactions, and prior decisions—with specialized tools and evolving external state. An agent may need to gather information, write and run code, edit files, invoke structured tools, inspect intermediate results, and recover from failed actions. We use co-work to describe this user-directed, multi-step work in a persistent digital environment. It may draw on coding, information gathering, and tool use, but is defined by sustained coordination across the complete task rather than by any fixed collection of skills. Why efficiency matters. Co-work changes the economics of model inference. A long task can invoke the model dozens or hundreds of times, so small differences in per-call cost and latency accumulate across the episode.

Discussion / Conclusion. Occamy-1.0 is a compact model built for co-work. It is designed for long, stateful tasks that require an agent to coordinate tools, files, structured APIs, and productivity software over many steps. Rather than rebuilding general capability from a base model, we continue post-training from Qwen3.6-35B-A3B and concentrate learning on the coordination, recovery, and follow-through that real work demands. The model is the product of an execution-centered post-training system. Our data and environments connect task construction to runnable state transitions and task-level outcomes. The training infrastructure supports multiple harnesses while preserving token-exact trajectories, environment-state replay, and segment boundaries created by history rewrites.