GPT-5.6 在 DeepSWE 编程智能体基准测试中达到约 72%-73% 的解决率，每任务成本约 $8.4；而 Claude/Fable-5 最高约 70%，每任务成本高达 $13-$22。DeepSWE 要求模型在真实开源仓库中完成长周期软件工程任务，涵盖仓库导航、错误诊断、代码编辑、工具使用、测试运行及多步修复，共涉及 91 个仓库和 5 种语言的 113 个任务。该基准通过程序验证器检查最终补丁是否有效，最佳模型需在最低平均任务成本下解决最多任务。
GPT 5.6 Beats Fable 5 by on DeepSWE at a cheaper price.
GPT-5.6 Sol reaches roughly 72% to 73% DeepSWE at about $8.4 per task, while Claude/Fable-5 tops out around 70% at a much higher cost, around $13 to $22 per task.
DeepSWE is a coding-agent benchmark, not a normal code-generation test, because the model must work inside real open-source repositories and finish long software engineering tasks.
Each task gives the agent a repo and a requested change, then checks whether the final patch actually works using program-based verifiers, so the score means “what % of the 113 tasks were solved.”
The benchmark tests repo navigation, bug diagnosis, code editing, tool use, test running, and multi-step repair across 91 repositories and 5 languages, not just writing a neat function from a prompt.
On this benchmark, the best model is the one that solves the most tasks for the least average task cost.
来源：Rohan Paul · x.com