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 modelCeleris 1celerisRemove
ProviderQwenceleris
Discovery tierBalancedBalanced
AddedOct 1, 2024Jul 25, 2026
Limits
Context window32KBest8.19K
Max output8.19K8.19K
Pricing, USD per 1M tokens
Input$1.60Best$2.00
Output$6.39$6.00Best
Benchmark indexes
Intelligence Index—6.3
Coding Index—14.4
Capabilities
Reasoning effort——

Public evaluations

Benchmarks

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

  • Qwen 2.5 Max
  • Celeris 1

Intelligence Index

  • Qwen 2.5 Max—
  • Celeris 16.3
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Qwen 2.5 Max: —
    • Celeris 1: 14.4

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Qwen 2.5 Max: —
    • Celeris 1: 0.4%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Qwen 2.5 Max: —
    • Celeris 1: 0.2%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Qwen 2.5 Max: —
    • Celeris 1: 151 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Qwen 2.5 Max: —
    • Celeris 1: 301 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Qwen 2.5 Max: —
    • Celeris 1: 1.2%

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen 2.5 Max: —
    • Celeris 1: 38.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen 2.5 Max: —
    • Celeris 1: 6.8%

  • GPQA Diamond

    Graduate-level science questions

    • Qwen 2.5 Max: —
    • Celeris 1: 63.1%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Qwen 2.5 Max: —
    • Celeris 1: 78.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Qwen 2.5 Max: —
    • Celeris 1: 0.0%

  • SciCode

    Scientific computing in Python

    • Qwen 2.5 Max: —
    • Celeris 1: 21.6%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen 2.5 Max: —
    • Celeris 1: 38.0%

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.