NOUMENOpen app
NOUMEN

Qwen · Balanced

Qwen 2.5 Max

Added Oct 1, 2024

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Qwen 2.5 Max is the upgraded version of Qwen Max, beating GPT-4o, Deepseek V3 and Claude 3.5 Sonnet in benchmarks.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$1.60
Output
$6.39

Reference prices as published by the model provider. API example

Specifications

Context window
32K
Max output
8.2K

Side by side

Qwen 2.5 Max compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Qwen 2.5 MaxQwenThis modelGemini 2.0 Pro ReasonerGoogleRemove
ProviderQwenGoogle
Discovery tierBalancedBalanced
AddedOct 1, 2024Jan 1, 2024
Limits
Context window32K128KBest
Max output8.19K65.54KBest
Pricing, USD per 1M tokens
Input$1.60$1.29Best
Output$6.39$5.00Best
Cache read—$0.32
Benchmark indexes
Intelligence Index—16.1
Coding Index—33.3
Math Index—87.7
Capabilities
Audio inputNoYes
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Qwen 2.5 Max
  • Gemini 2.0 Pro Reasoner

Intelligence Index

  • Qwen 2.5 Max—
  • Gemini 2.0 Pro Reasoner16.1
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 33.3

  • Math Index

    Composite of the math evaluations

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 87.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 2.2%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 302 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 455 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 10.2%

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 69.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 12.2%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 22.5%

  • GPQA Diamond

    Graduate-level science questions

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 84.4%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 86.2%

  • IFBench

    Following precise output instructions

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 48.7%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 0.0%

  • SciCode

    Scientific computing in Python

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 46.3%

  • LiveCodeBench

    Recent competitive programming problems

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 80.1%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 87.7%

  • AIME

    Competition mathematics

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 88.7%

  • MATH-500

    Competition math problems

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 96.7%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 26.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 54.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen 2.5 Max: —
    • Gemini 2.0 Pro Reasoner: 69.0%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen-max",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="qwen/qwen-max",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Qwen

Other Qwen models, starting with the same family.