ModelsMulti-source77°

Qwen4-Max 上线 Arena,超越 Qwen3.8-Max 升至总榜第 14

Why we picked it

阿里新旗舰进 Arena 直接冲到总榜第14,把腾讯、Moonshot、DeepSeek 都甩在后面。Peter Gostev 那段实测很值得看:3D 场景、游戏、网站设计全和 Opus、GPT 正面对比,提示词也贴出来了,想选模型做智能体的开发者别错过。

阿里 Qwen 团队发布的 Qwen4-Max 已进入 Arena 排行榜,成为排名最高的中国模型,使 Alibaba 成为全球第 5 的实验室,排在 Anthropic、Google、OpenAI 和 Meta 之后。在 Agent Arena 上,它基于 14.7k 条真实智能体任务会话以 +7.5% 净提升首次亮相,总排名从 Qwen3.8-Max 的 #39 跃升至 #14。

Image · lmarena.ai
Body

在四项信号维度上,Qwen4-Max 较 Qwen3.8-Max 全面提升:Praise vs. Complaint +13%(#15,中国模型最佳)、Confirmed Success +9%(#13)、Steerability +8%(#19)、Bash Reliability +3%(#29)。按场景分类,它在 Work (#12)、Chat (#14)、Code (#16) 三个类别均为排名最高的中国模型。Arena.ai 的 Peter Gostev 还用金门大桥 3D 场景、Voxel Rome、游戏生成、网站设计、交互式讲解(闪电与 Enigma)等测试对比了它与 Opus、GPT、Kimi、Fable 的输出。

中国前沿模型在 Agent Arena 的梯队中,Qwen4-Max (#14, +7.5%) 领先 Tencent 的 Hy4 (#19, +5.7%)、Moonshot 的 Kimi K3.1 Pro (#21, +4.0%)、Xiaomi 的 MiMo-V2.6-Pro (#26, +1.5%) 和 DeepSeek-V4.1-Flash (#30, +1.1%)。视频最后提到该模型的定价尚未公布。

Original · lmarena.ai

Qwen4-Max by @Alibaba_Qwen is now in the Arena. @petergostev tested it on 3D scenes, games, creative prompts, website design, and interactive explanations, comparing its outputs with those from Opus, GPT, Kimi, and Fable. Watch Peter’s first impressions, and find his prompts at the link in thread. 00:00 How close is Qwen4-Max to the frontier? 00:29 Golden Gate Bridge: the first 3D test 01:59 Voxel Rome and more 3D comparisons 05:35 Turning paintings into 3D worlds 09:09 Games: Qwen vs. Opus and Fable 10:18 Creative scenes and camera work 12:32 The crochet mushroom test 13:36 Website design: a smaller gap 15:47 Qwen vs. GPT: web design and usability 18:26 More tests: aircraft, hiking and typography 19:33 Interactive explanations: lightning and Enigma 21:27 Phi Phi Islands: Qwen vs. Fable 22:08 Pricing unknowns and final thoughts

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Qwen4-Max, Alibaba, Agent Arena, reasoning models.

Source attribution: curated from lmarena.ai (@lmarena_ai). Cross-source corroboration: 11 independent sources have covered this development (including 阿里通义 Qwen, 掘金本周最热, shao__meng), confirming industry-wide signal strength.