What is the context window of Qwen3 Max, and how long can its output be?

The context window of Qwen3 Max is 262K tokens (262,144), and its maximum output is 66K tokens (65,536).

Can Qwen3 Max read images, audio, video or PDFs?

No. Qwen3 Max accepts text input only, not images, audio, video or PDFs.

Does Qwen3 Max support tool calling?

Yes, Qwen3 Max supports tool calling (function calling).

Does Qwen3 Max have a reasoning or thinking mode?

No, Qwen3 Max does not have a reasoning or thinking mode.

What is the knowledge cutoff of Qwen3 Max?

The knowledge cutoff of Qwen3 Max is 2025-04.

Where does Qwen3 Max rank on Arena?

Qwen3 Max holds rank 128 on Arena Text with a score of 1423.

What are the closest alternatives to Qwen3 Max?

The closest alternatives, matched on model kind and release date with no comparable price, are ERNIE X1.1 by Baidu, x-AI/Grok-Code-Fast 1 by xAI and Seed 1.6 by ByteDance.

What is the best open-weight alternative to Qwen3 Max?

Kimi K3, the highest-ranked open-weight model on Arena Text at rank 19. Qwen3 Max itself is closed.

What is the difference between Qwen3 Max and Qwen3 235B-A22B?

Qwen3 Max has a 262K token (262,144) context and was released September 23, 2025, while Qwen3 235B-A22B has a 131K token (131,072) context and was released April 28, 2025.

Is Qwen3 Max open source or open weights?

No, Qwen3 Max is closed, so it is neither open source nor open weights.

Who made Qwen3 Max and when was it released?

Qwen made Qwen3 Max, which was released on September 23, 2025.

Qwen3 Max

Alibaba

Announcement

Qwen3 Max

Developer	Alibaba
Release date	September 23, 2025
Family	Qwen
Generation	Qwen 3
Level
Context window	262K tokens
Max output	66K tokens
Input	Text
Output	Text
Knowledge cutoff	2025-04
Weights	Closed
Successor	Qwen3.7 Max
Website	alibabagroup.com

Part of a series on

Qwen

Context: 262Ktokens
Released: 1y ago

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

How it compares

Level

FlagshipThe lab's most capable generally available line, priced for hard tasks.

Vs. your stack

Add the models you use to see how this one compares.

Vs. what you use

Better Same Worse

No verdicts yet

Discussion

No comments yet

Be the first to share your thoughts.

Additional source evidence

Source model: alibaba/qwen3-max
Source family: qwen
Last updated: 2025-09-23
Knowledge cutoff: 2025-04
Model context: 262K
Model output limit: 66K
Open weights: No
File attachments: No
Reasoning: No
Tool calling: Yes
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
Artificial Analysis Coding Index	26.4 · index	2026-05-30	Source
SciCode	38.3 · percent correct	2026-05-30	Source
Terminal-Bench Hard	20.5 · success rate	2026-05-30	Source

Complete source record (JSON)

{
  "id": "alibaba/qwen3-max",
  "name": "Qwen3 Max",
  "description": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use",
  "family": "qwen",
  "last_updated": "2025-09-23",
  "knowledge": "2025-04",
  "attachment": false,
  "reasoning": false,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 262144,
    "output": 65536
  },
  "benchmarks": [
    {
      "name": "Artificial Analysis Coding Index",
      "score": 26.4,
      "source": "https://openrouter.ai/qwen/qwen3-max/benchmarks",
      "metric": "index",
      "date": "2026-05-30"
    },
    {
      "name": "SciCode",
      "score": 38.3,
      "source": "https://openrouter.ai/qwen/qwen3-max/benchmarks",
      "metric": "percent correct",
      "date": "2026-05-30"
    },
    {
      "name": "Terminal-Bench Hard",
      "score": 20.5,
      "source": "https://openrouter.ai/qwen/qwen3-max/benchmarks",
      "metric": "success rate",
      "date": "2026-05-30"
    }
  ],
  "release_date": "2025-09-23",
  "open_weights": false
}