跳到正文

Qwen4-Max 在 Agent Arena 上超越 Qwen3.8-Max

Qwen · X转述· @Alibaba_Qwen·· 21 小时前精选

2万 次浏览 · 361 赞 · 26 转发 (收录时)

原文
谁
Alibaba_Qwen
引文
Qwen4-Max outperforms Qwen3.8-Max by +7.5% net on Agent Arena, making Alibaba #5 lab overall.

发生了什么

Qwen 称,Qwen4-Max 在 Agent Arena 上的净表现比 Qwen3.8-Max 高出 7.5%,使阿里巴巴位列整体实验室第 5 名。引述的 Agent Arena 帖子称,Qwen4-Max 首次亮相便位列整体第 14 名,高于 Qwen3.8-Max 的第 39 名;结果基于 1.47 万次真实世界智能体会话。

推荐理由

Qwen4-Max 在 Agent Arena 上排名高于 Qwen3.8-Max,四项信号和三类指标均报告了提升;结果基于 1.47 万次真实世界智能体会话。

接下来读什么

查看这件事的完整进展Qwen4-Max Ranks Above Qwen3.8-Max on Agent Arena
正文 · 中文版本尚未就绪(原文)

Qwen4-Max outperforms Qwen3.8-Max by +7.5% net on Agent Arena, making Alibaba #5 lab overall.

引用Arena.ai@arena

Qwen4-Max by @Alibaba_Qwen is the #1 Chinese model on the leaderboard making Alibaba now the #1 Chinese lab and #5 lab overall, just behind Anthropic, Google, OpenAI and Meta.

It debuts overall at #14 on Agent Arena with +7.5% net improvement across 14.7k real-world agentic sessions from our global community, real traces on real tasks.

This is a major leap over Qwen3.8-Max
- Rank: #39 → #14 overall

The Chinese frontier on Agent Arena:

  • #14 Qwen4-Max (Alibaba): +7.5%
  • #19 Hy4 (Tencent): +5.7%
  • #21 Kimi K3.1 Pro (Max) (Moonshot): +4.0%
  • #26 MiMo-V2.6-Pro (Xiaomi): +1.5%
  • #30 DeepSeek-V4.1-Flash (Max) (DeepSeek): +1.1%

Breaking down performance across signals:
Qwen4-Max improves over Qwen3.8-Max across all four reported signals, with particularly large gains in user satisfaction and steerability.

  • #15 Praise vs. Complaint: +13% (best Chinese model)
  • #13 Confirmed Success: +9% (best Chinese model)
  • #19 Steerability: +8%
  • #29 Bash Reliability: +3%

By category, it is a top-ranked Chinese model across all 3:

  • #12 in Work: +9%
  • #14 in Chat: +8%
  • #16 in Code: +8%

Congrats to the @Alibaba_Qwen team on this release!

在 X 查看被引用的帖子

这件事到目前为止

Qwen says Qwen4-Max outperformed Qwen3.8-Max by 7.5% net on Agent Arena; the quoted leaderboard post placed Qwen4-Max at No. 14 overall and Qwen3.8-Max at No. 39, based on 14,700 real-world agent sessions. Qwen also said Alibaba ranked No. 5 among labs.

这条收录于 11月17日 AI 日报看这一期日报的全部内容