ModelBeat
Models/Qwen3-Max
All models
A
qwen/qwen3-max

Qwen3-Max is Alibaba’s proprietary AI model, released Sep 5, 2025. It costs $0.78/M input and $3.90/M output tokens, and handles a 262K-token context window.

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version.

Context
262K
Input
$0.78 / 1M
Output
$3.90 / 1M
Released
Sep 5, 2025
Modalities
texttext

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Qwen3-Max lands among all models tracked on Model Beat.

34.0
Intelligence Index
Epoch AI
34th percentile of tracked models
35.0
Coding Index
Epoch AI
35th percentile of tracked models
28.0
Agentic Index
Epoch AI
28th percentile of tracked models

Reasoning

4 evals
GPQA Diamond72.6%

Graduate-level scientific reasoning

Humanity's Last Exam11.1%

Frontier of human expert knowledge

MMLU-Pro84.1%

Broad expert knowledge

SimpleQA Verified67.5%

Factual accuracy & hallucination

Coding

2 evals
LiveCodeBench76.7%

Contamination-free coding

SciCode38.3%

Scientific research coding

Math

2 evals
AIME 2024/202573.3%

Olympiad-qualifier math

MATH Level 597.1%

Hardest competition math

Agentic & Tools

1 evals
τ²-bench74.3%

Tool-agent-user reliability

In the news

3

Compare Qwen3-Max with

Frequently asked questions

What is Qwen3-Max?

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version.

Who created Qwen3-Max?

Qwen3-Max is an AI model developed by Alibaba, part of the Qwen family, released Sep 5, 2025.

How much does Qwen3-Max cost?

Qwen3-Max's list price from Alibaba is $0.78 per million input tokens and $3.90 per million output tokens.

What is Qwen3-Max's context window?

Qwen3-Max supports a context window of up to 262K tokens.

How does Qwen3-Max perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Qwen3-Max scores 67.5% on SimpleQA Verified, 84.1% on MMLU-Pro, 76.7% on LiveCodeBench.

Is Qwen3-Max open source?

Qwen3-Max is a proprietary model (API access), available through its provider's API rather than as a downloadable open-weight model.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Jul 30, 2026.