Strengths
- It scores 43 on the independent Artificial Analysis Intelligence Index v5.0.1, against 34 for Qwen3.8-Max.
- A task in the Artificial Analysis test costs $3.27 and takes 31 minutes on average. Qwen3.8-Max needed $10.02 and 48 minutes.
- At $1.5 per million input and $4.5 per million output tokens it is cheaper than its predecessor. Cached input costs only $0.075.
- Vals AI independently confirmed its 48.5% on Terminal-Bench 4.0, a test of agents working in the command line.
- A one-million-token context and text, image and video input. You can switch thinking off or set how deeply the model reasons.
- Alibaba says it writes safer code: on Last Secure Code Bench, the share of code that both works and is secure rose from 22% to 31.8%.
Weaknesses
- You cannot download the weights. Alibaba only promises smaller open Qwen4 models, so far with no date or sizes.
- In Frankfurt it only runs in Global scope, so processing is not tied to the EU.
- With thinking on by default it is slow: in Artificial Analysis measurements it took 148 seconds on average to start answering and writes 56 tokens per second.
- Alibaba published many of the results itself, for example from its own Work360 test. It does not state the knowledge cutoff.
Best for
- coding and long tasks with AI agents
- analysing documents, images and video
- long documents up to one million tokens
- a capable API model at a lower price
Not ideal for
- data that may only be processed in the EU
- companies that want to run the model on their own servers
- fast replies, for example in a customer chatbot
How to use it in Europe
Through the API in Alibaba Cloud Model Studio as qwen4-max. The international Singapore region gives you a free quota of 1 million tokens for 90 days. In Frankfurt your data is stored in Germany, but Max only runs there in Global scope, so processing may happen outside the EU. For consumers it is in the QwenWork app with plans in USD, in QwenStudio and in the Qoder coding tool. If data must stay in house, use the open Qwen3.8-2.4T-A95B on your own server.
What is coming
Confirmed by vendor When it released Qwen4-Max on 16 November 2026, Alibaba promised smaller Qwen4 models with open weights soon. It has not given names, sizes or a date. When: no date yet, Alibaba only says “soon” →
Price compared with similar models
Benchmark results
| Benchmark | Score | Source |
|---|---|---|
| Artificial Analysis Intelligence Index v5.0.1 | 43 | artificialanalysis.ai ↗, November 2026 |
| Vals Index | 63.2% | vals.ai ↗, November 2026 |
| Terminal-Bench 4.0 (Vals AI) | 48.5% | vals.ai ↗, November 2026 |
| Work360 | 52.69 | qwen.ai ↗ (vendor-reported), November 2026 |
| Last Secure Code Bench, functional and secure | 31.8% | qwen.ai ↗ (vendor-reported), November 2026 |
Benchmarks cover only a narrow slice of ability and vendors often report them at their best settings. Treat them as a rough guide.
More models from this vendor
- Qwen3.7-Plus: An affordable mid-range Qwen model for everyday business tasks through the API, with a one-million-token context and image input.
- Qwen3.8-Flash: A very cheap, fast Qwen model for high volumes of tasks. Unlike Max and Plus, it runs in Frankfurt with processing kept in the EU.
- Qwen3.8-2.4T-A95B: The open-weight text base of Qwen3.8-Max with 2.4 trillion parameters, for large companies with their own GPU cluster.
- Qwen3.8-27B: A small open Qwen model under Apache 2.0 that runs on your own computer and understands images and video.
Similar models from other vendors
- Claude Opus 5.5 (Anthropic): Anthropic's main model for demanding work, coding and long documents, and the one Anthropic recommends starting with.
- DeepSeek V4 Pro (DeepSeek): DeepSeek's largest open-weight model for demanding text tasks at a low price. It does not understand images.
- Gemini 4 Carbon (Google): Google's most capable model, available since 10 November 2026 in the paid API, for businesses and in Google AI Ultra. It scores 60 on the independent index.
- Gemini 4 Neon (Google): Google's powerful model between Carbon and Hydrogen, out since 18 November 2026. In the app it comes with Google AI Pro in place of Argon.
- Muse Wonder (Meta): Meta's strongest model for long-running agents and coding, still released as a preview.
- Mistral Large 4 (Mistral AI): Mistral's largest model, now with open weights. Built for demanding tasks, long documents and agents, with data kept in the EU and a cheaper API than in preview.