Qwen4-Max 进入 Arena,实测 3D 场景、游戏与网页设计
Qwen4-Max by @Alibaba_Qwen is now in the Arena. @petergostev tested it on 3D scenes, games, creative prompts, website design, and interactive explanations, comp
Arena 宣布阿里 Qwen4-Max 已进入 Arena,创作者 petergostev 用 3D 场景、游戏、创意提示词、网页设计和交互式讲解等任务,将其输出与 Opus、GPT、Kimi、Fable 对比。Arena 称 Qwen4-Max 在 Agent Arena 首次上榜即位列第 14,较 Qwen3.8-Max 的第 39 名提升明显,在 14.7k 真实智能体会话上净提升 +7.5%,是榜单上排名最高的中国模型。分项上它在 Praise vs. Complaint 提升 13%、Confirmed Success 提升 9%、Steerability 提升 8%、Bash Reliability 提升 3%。
查看原帖由 @Alibaba_Qwen 推出的 Qwen4-Max 是排行榜上排名第一的中国模型,这使得阿里巴巴成为排名第一的中国实验室,并在整体实验室排名中位列第五,仅次于 Anthropic、Google、OpenAI 和 Meta。 它在 Agent Arena 上首次亮相即位列总榜第 14 名,在我们全球社区提供的 14.7k 次真实智能体会话(真实任务上的真实轨迹)中实现了 +7.5% 的净提升。 相较 Qwen3.8-Max 这是一次重大飞跃 - 排名:总榜第 39 名 → 第 14 名 Agent Arena 上的中国前沿模型: - 第 14 名 Qwen4-Max(阿里巴巴):+7.5% - 第 19 名 Hy4(腾讯):+5.7% - 第 21 名 Kimi K3.1 Pro (Max)(月之暗面):+4.0% - 第 26 名 MiMo-V2.6-Pro(小米):+1.5% - 第 30 名 DeepSeek-V4.1-Flash (Max)(DeepSeek):+1.1% 按各项信号拆解表现: Qwen4-Max 在全部四项报告信号上均优于 Qwen3.8-Max,其中在用户满意度和可控性方面提升尤为显著。 - 第 15 名 好评 vs. 差评:+13%(最佳中国模型) - 第 13 名 确认成功:+9%(最佳中国模型) - 第 19 名 可控性:+8% - 第 29 名 Bash 可靠性:+3% 按类别划分,它在全部 3 个类别中均为排名最高的中国模型: - 工作类第 12 名:+9% - 聊天类第 14 名:+8% - 代码类第 16 名:+8% 祝贺 @Alibaba_Qwen 团队发布此版本!
查看原文
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!
正文
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