AI News

阿里 Qwen4-Max 基准成绩公布,Artificial Analysis Index 得 43 分

Testing Catalog更新于 11月16日 21:09

ALIBABA 🔥: Qwen4-Max benchmarks are out, and it scored 43 points on the Artificial Analysis Index, one point below Muse Wonder.

AI 导读

TestingCatalog 汇总了阿里 Qwen4-Max 的基准成绩,该模型在 Artificial Analysis Index 上得 43 分,比 Muse Wonder 低 1 分。Qwen4-Max 采用新的 MoE 架构,原生支持视觉并具备 1M-token 上下文窗口;在 xhigh 推理强度下比 Qwen3.8 Max 高 9 分,比 Kimi K3.1 Pro(max,46 分)低 3 分。它还在 Agent Arena 总榜首次上榜位列第 14,在 14.7k 真实智能体会话上取得 +7.5% 的净提升。

推荐理由

AI 评分 70

原文给出了 Qwen4-Max 在第三方指数与 Agent Arena 上的位置,读者可据此判断它与前代及竞品的差距。

主题

标签

引用

Qwen

@Alibaba_Qwen

📢 认识 Qwen4-Max,你全新的 AI 队友,助力工作、创意与探索! Qwen4-Max 基于全新的 MoE 架构构建,原生支持视觉,并具备 1M-token 上下文窗口。 亮点: - 在我们的内部评测中,其表现超越 Qwen3.8-Max,最多可减少约 50% 的 token 用量,同时每项任务的平均成本下降超过 60%。 - 凭借对专业工具的更强熟练度、更强的长程执行能力和更高质量的交付成果,提升现实世界的生产力。 - 可处理真实任务,涵盖 3D 建模、游戏开发、制造业、金融、法律、医疗健康以及前沿科学发现。 - 输入 $1.5/百万 tokens,输出 $4.5/百万 tokens,隐式缓存 $0.075/百万 tokens——全部低于 Qwen3.8-Max,其中隐式缓存费用下降 70%。 API 已在 QwenCloud 上线。你也可以在 Qwen Studio、QwenWork 和 Qoder 上试用 Qwen4-Max。 今天就开始构建吧!🚀 - 博客:https://t.co/AuiWxugjE6 - API:https://t.co/aS1QEkS8nu - Token 方案:https://t.co/YRvcGdB9Bv 更多内容即将到来!更小规模的 Qwen4 模型将开放权重。敬请期待。👀

查看原文

📢 Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery! Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window. Highlights: - Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation. - Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables. - Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery. - $1.5/M tokens for input, $4.5/M tokens for output, and $0.075/M tokens for implicit caching — all lower than Qwen3.8-Max, with implicit caching down by 70%. The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder. Start building today! 🚀 - Blog: https://t.co/AuiWxugjE6 - API: https://t.co/aS1QEkS8nu - Token Plan: https://t.co/YRvcGdB9Bv More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. 👀

查看原帖

正文

ALIBABA 🔥: Qwen4-Max benchmarks are out, and it scored 43 points on the Artificial Analysis Index, one point below Muse Wonder.

Qwen4-Max is a new MoE architecture model with native vision and a 1M-token context window.

> Qwen4 Max, using xhigh reasoning effort, scores 9 points ahead of Qwen3.8 Max (xhigh) and 3 points behind Kimi K3.1 Pro (max, 46).

> It also debuted at #14 overall on Agent Arena with a +7.5% net improvement across 14.7k real-world agentic sessions.

来源

Testing Catalog