NOUMENOpen app
NOUMEN

Qwen · Balanced

Qwen3 Max 2026-01-23

Added Jan 26, 2026

Compare models

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

Loading models…

Use in the app

Qwen3 Max is Alibaba's flagship Qwen 3 reasoning model with native tool use (web search, web extractor, code interpreter) and a 256K context window.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$1.20
Output
$6.00

Reference prices as published by the model provider. API example

Specifications

Context window
256K
Max output
32.8K

Side by side

Qwen3 Max 2026-01-23 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…

Qwen3 Max 2026-01-23QwenThis modelGrok 4.3xAIRemove
ProviderQwenxAI
Discovery tierBalancedBalanced
AddedJan 26, 2026Apr 30, 2026
Limits
Context window256K1MBest
Max output32.77K—
Average output—466 tokens
Pricing, USD per 1M tokens
Input$1.20Best$1.25
Output$6.00$2.50Best
Cache read—$0.20
Performance
Throughput—341.6 tok/s
Time to first token—3.3 s
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index—14.0
Coding Index—35.2
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Qwen3 Max 2026-01-23
  • Grok 4.3

Intelligence Index

  • Qwen3 Max 2026-01-23—
  • Grok 4.314.0
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 35.2

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 0.9%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 0.2%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 724 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 941 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 2.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 32.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 5.6%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 6.8%

  • GPQA Diamond

    Graduate-level science questions

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 65.8%

  • IFBench

    Following precise output instructions

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 47.6%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 0.0%

  • SciCode

    Scientific computing in Python

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 39.4%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 18.9%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 65.8%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen3 Max 2026-01-23: —
    • Grok 4.3: 32.3%

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/qwen3-max-2026-01-23",
    "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/qwen3-max-2026-01-23",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Qwen

Other Qwen models, starting with the same family.