35B小模型，干翻大模型？
大模型做复杂任务时，贵在每一步都要调用一次，成本和时间是叠加的。这篇论文发布了一个 35B 参数的模型 Occamy-1.0，在多个协同工作基准上，成绩和比它大好几倍的模型差不多，但成本低得多，处在性价比的拐点上。它靠的是把训练数据换成真实执行轨迹，专门练状态跟踪、工具调用、代码修改这些干活时真正耗时的环节，而不是一味堆推理能力。模型权重和部分训练数据已开源。它不是你明天就能直接用的产品，但如果你在搭 AI 工作流、或者关心 AI 服务的定价，这个方向意味着：以后跑复杂任务，可能不用再为用不上的“聪明”买单。
📄 原文摘要(英文)
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 cost-efficient 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. Supporting evaluations in tool calling, coding, and instruction following further show that this specialization preserves broad agentic capability. We release the model weights and a subset of the training data to support research on practical co-work agents and agentic post-training.