Qwen4 Max 发布:Artificial Analysis 智能指数得分 43,比 Qwen3.8 Max 高 9 分
Qwen4 Max 把单任务成本砍到 Qwen3.8 Max 的三分之一,分数还反超 9 分,智能指数 43 分只差 Kimi K3.1 Pro 三分。做知识工作智能体的看 AA-Briefcase 上 1686 Elo 领先,写代码的注意它在 Terminal-Bench 4.0 上还输 Kimi 一截。
Alibaba Qwen 团队发布 Qwen4 Max,在 Artificial Analysis Intelligence Index 上以 xhigh 推理档位拿到 43 分,比 Qwen3.8 Max(xhigh,34 分)高出 9 分,仅落后 Kimi K3.1 Pro(46 分)3 分。每个 Index 评测项都有提升,其中 HLE-Diamond 从 24% 涨到 45%(+21 分),AA-Omniscience +18 分,AutomationBench-AA +17 分,Terminal-Bench 4.0 +9 分。
成本方面改善明显:单任务成本 $3.27,约为 Qwen3.8 Max($10.02)的三分之一,比 Kimi K3.1 Pro($3.68)低约 11%。这来自 25% 的每 token 降价($1.50/$4.50 每百万输入/输出 token,缓存命中价 $0.075)、缓存命中便宜 70%,以及每任务输出 token 从约 171k 降到约 105k(少 39%)。模型支持 1M token 上下文和文本+图像输入。
短板也存在:Terminal-Bench 4.0 上得 48%,明显落后 Kimi K3.1 Pro 的 67%;Cognition 私有评测 FrontierCode 2.0 上得 26%,与 Kimi K3.1 Pro 持平但落后 Tencent Hy4(31%)。Tencent Hy4 单任务成本仅 $1.03,但 Index 分数低 8 分,国内旗舰模型在性价比区间形成竞争梯队。
+9 points over Qwen3.8-Max with lower costs. Give it a try! @ArtificialAnlys Artificial Analysis @ArtificialAnlys Alibaba has launched Qwen4 Max, gaining 9 points over Qwen3.8 Max on the Artificial Analysis Intelligence Index and landing 3 points behind Kimi K3.1 Pro at ~11% lower Cost per Task Qwen4 Max, using xhigh reasoning effort, scores 43 on the Intelligence Index, 9 points ahead of Qwen3.8 Max (xhigh) and 3 points behind Kimi K3.1 Pro (max, 46) Key takeaways: ➤ Qwen4 Max improves on every evaluation in the Index vs Qwen3.8 Max (xhigh, 34): HLE-Diamond +21 points (24% to 45%), AA-Omniscience +18 points, AutomationBench-AA +17 points, CritPt v2 +13 points, Terminal-Bench-Science +11 points, Terminal-Bench 4.0 +9 points, GDP.pdf +3 points, FrontierCode 2.0 +3 points and AA-Briefcase +82 Elo. ➤ Qwen4 Max costs $3.27 per Intelligence Index task, ~3x less than Qwen3.8 Max ($10.02) and ~11% less than Kimi K3.1 Pro ($3.68): This is driven by 25% lower per-token pricing than Qwen3.8 Max, 70% cheaper cache hits and lower token usage. Tencent Hy4 costs ~3x less per task ($1.03) than Qwen4 Max but scores 8 points lower on the Index. ➤ Qwen4 Max uses 39% fewer output tokens per task than Qwen3.8 Max: ~105k output tokens per Intelligence Index task vs ~171k for Qwen3.8 Max, ~72k for Kimi K3.1 Pro and ~78k for Tencent Hy4. Qwen4 Max uses fewer tokens, while increasing 9 points on the Intelligence Index ➤ Improvements in AA-Briefcase (knowledge work): On AA-Briefcase, our evaluation of agentic work across real business files, Qwen4 Max reaches 1686 Elo vs 1674 for Kimi K3.1 Pro and 1446 for Tencent Hy4. ➤ Qwen4 Max trails Kimi K3.1 Pro on Terminal-Bench 4.0 and Tencent Hy4 on FrontierCode 2.0: Qwen4 Max scores 48% on Terminal-Bench 4.0 vs 67% for Kimi K3.1 Pro and 37% for Tencent Hy4. On FrontierCode 2.0, @cognition ’s private evaluation of real-world coding tasks, it scores 26%, level with Kimi K3.1 Pro (26%) and behind Tencent Hy4 (31%). Key model details: ➤ Context window: 1M tokens ➤ Multimodal: Text and image input with text output ➤ Pricing: $1.50/$4.50 per 1M input/output tokens on Alibaba's first-party APIs, with a $0.075 cache hit price. This is lower than Qwen3.8 Max across the board ($2.00/$6.00, with a $0.25 cache hit price) ➤ Availability: @Alibaba_Qwen 's first-party APIs 🔗 View Quoted Tweet📊 11 ⚡
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. Key entities and technical topics under continuous tracking include Qwen4 Max, Qwen, Alibaba, Kimi K3.1 Pro.
Source attribution: curated from 阿里通义 Qwen (@Alibaba_Qwen).