Alibaba 表示 Qwen3.8-Max 在商业代理基准测试中领先于开放权重模型
Accio 团队的基于状态的基准测试报告显示，Qwen3.8-Max 通过 Accio 完成了 56 项任务，通过 OpenClaw 完成了 47 项，通过 Pi 完成了 53 项；Alibaba 称其为整体最强的开放权重结果。
By RuntimeWire Staff · Published
Primary source: Qwen / Alibaba
为何重要
代理供应商需要的是检查已完成业务状态的测试，而不是查看被润色过的对话记录。Accio 团队的基准测试推进了这一做法；与此同时，Alibaba（阿里巴巴）自报的 two-pass open-weight margin、harness variance 以及缺乏不可变的公开任务级别 bundles，使得可审计性与排行榜名次同样重要。
Yukun Lian, Sicong Xie and ten colleagues on Alibaba International's Accio team built Commerce Agent Bench to test whether AI agents can finish commercial work inside stateful replicas of business software. Alibaba's Qwen3.8-Max, part of the Qwen3.8 model family, completed 56 of 107 tasks through Accio, 47 through OpenClaw and 53 through Pi.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.