Skip to content

Qwen Proprietary Released Dec 15, 2025 Updated

Qwen3 Max

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #152 / 419

    310 / 1,000

    ToolsGuide Score· votes 344, tests 282

  • Price per 1M tokens

    In $1.20· Out $6.00

    $1.20

    Input · median text model $0.44

Summary

Qwen3 Max is Qwen's model, released Dec 15, 2025. It's ranked in 1 category and does best at text: #152 of 419, with a ToolsGuide Score of 310 against a median of 252.

It costs $1.20 per million input tokens and $6.00 per million output tokens, about 2.7× the median text model ($0.44).

It has published results on 6 tests.

Specifications

Creator
Qwen
Licence
Proprietary
Released
Dec 15, 2025
Context window
256K tokens
Input price
$1.20 / 1M
Output price
$6.00 / 1M
Tests reported
6
Settings ranked
Qwen3-Max (2025-09-23)

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where Qwen3 Max sits among the top 20 in each category.

Text

#152 of 419 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Score against price

Text · the 10 priced models ranked closest · up and to the left is better value

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

Qwen3-Max (2025-09-23) · hover a bar for its rank

Test results

Every test Qwen3 Max has a published result on, out of 100%, with its rank among the models that took it.

  • GPQA

    #186 / 265

    Graduate-level science questions written to be hard to look up.

    62.0%

    Self-reported

  • AIME 2025

    #71 / 124

    Competition maths problems from the 2025 American Invitational Mathematics Exam.

    81.6%

    Self-reported

  • SWE-Bench Verified

    #74 / 123

    Fixing real bugs in real GitHub projects, checked by the projects' own tests.

    69.6%

    Self-reported

  • LiveCodeBench v6

    #44 / 68

    LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.

    69.0%

    Self-reported

  • SuperGPQA

    #11 / 37

    SuperGPQA is a comprehensive benchmark that evaluates large language models across 285 graduate-level academic disciplines. The benchmark contains 25,957 questions covering 13 broad disciplinary areas including Engineering, Medicine, Science, and Law, with specialized fields in light industry, agriculture, and service-oriented domains. It employs a Human-LLM collaborative filtering mechanism with over 80 expert annotators to create challenging questions that assess graduate-level knowledge and reasoning capabilities.

    65.1%

    Self-reported

  • t2-bench

    #16 / 23

    t2-bench is a benchmark for evaluating agentic tool use capabilities, measuring how well models can select, sequence, and utilize tools to solve complex tasks. It tests autonomous planning and execution in multi-step scenarios.

    74.8%

    Self-reported