智能体
x.com ·
@Arena.ai (@arena)
Qwen3.8-Flash-Next 进入 Agent Arena,开放模型中排名第 7
Qwen3.8-Flash-Next 在 Agent Arena 中排名开放模型第 7(总第 24),净提升 +2.4%,确认成功信号 +12.3%。表现优于 Qwen3.8-27B,但落后于 DeepSeek V4 Flash 和 GLM-5.3。
AI推荐理由 Arena.ai 发布 Qwen3.8-Flash-Next 在 Agent Arena 的排名数据,包含具体净提升百分比和对比,信息详实且来源可信。对评估开放模型 Agent 能力有直接参考价值。
80
浏览 52,478
点赞 314
评论 19
转发 26
正文
Qwen3.8-Flash-Next 由 @Alibaba_Qwen 发布,已登陆 Agent Arena,在开放模型中排名第 7(总体排名第 24),在 8.7K+ 真实世界智能体会话中净提升 +2.4%!
在开放模型中,它紧随 DeepSeek V4 Flash (High) 之后,排名第 6(净提升 +3%),并落后 GLM-5.3 (Max) 两个名次,后者排名第 5(净提升 +3.8%)。
按信号来看,Qwen3.8-Flash-Next 在社区任务完成明确响应方面表现突出(确认成功 +12.3%),在开放模型中排名第 5(总体排名第 7)。以下按信号提供更多性能详情。
Qwen3.8-Flash-Next 在总体净提升(+2.4% 对比 +1.5%)和确认成功(+12.3% 对比 +7.2%)方面均优于 Qwen3.8-27B。Qwen3.8 Max 在总体上仍领先,为 +6%,确认成功率为 +10.8%。
祝贺 @Alibaba_Qwen 团队为开放生态系统做出这一贡献!
查看原文(中文正文为 AI 翻译)
Qwen3.8-Flash-Next by @Alibaba_Qwen has landed in Agent Arena, ranking #7 among open models (#24 overall) with +2.4% net improvement across 8.7K+ real-world agentic sessions!
Among open models, it sits just behind DeepSeek V4 Flash (High) at #6 (+3% net improvement) and two spots behind GLM-5.3 (Max) at #5 (+3.8%).
By signal, Qwen3.8-Flash-Next stands out in delivering an explicit response from the community on task completion (Confirmed Success at +12.3%), ranking #5 among open models (#7 overall). More detail on its performance by signal below.
Qwen3.8-Flash-Next outperforms Qwen3.8-27B in overall net improvement (+2.4% vs. +1.5%) and Confirmed Success (+12.3% vs. +7.2%). Qwen3.8 Max remains ahead overall at +6%, with +10.8% Confirmed Success.
Congrats to the @Alibaba_Qwen team on this contribution to the open ecosystem!