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. The authors note that many steps in everyday work emphasize state tracking, coordination, recovery, and follow-through rather than frontier-scale reasoning.

Occamy-1.0 is presented as a cost-efficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint. The training approach constructs execution-grounded data and environments, captures replayable long-horizon trajectories across multiple harnesses, and uses 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 the 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. Supporting evaluations in tool calling, coding, and instruction following further show that this specialization preserves broad agentic capability.

The model weights and a subset of the training data are released to support research on practical co-work agents and agentic post-training.