NOUMENOpen app
NOUMEN

Qwen · Open weights

Qwen 3 32b

Added Jan 1, 2024Open weights

Compare models

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

Loading models…

Use in the app

Qwen 3 32b is a 32b model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.

  • Tools
  • PDF input
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.08
Output
$0.24

Reference prices as published by the model provider. API example

Specifications

Context window
41K
Max output
32.8K
Average output (7 days)
646 tokens
Longer than 58% of 468 models

Side by side

Qwen 3 32b 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 3 32bQwenThis modelHermes 4 LargenousresearchRemove
ProviderQwennousresearch
Discovery tierOpen weightsOpen weights
AddedJan 1, 2024Aug 26, 2025
Limits
Context window41K128KBest
Max output32.77KBest8.19K
Average output646 tokens199 tokens
Pricing, USD per 1M tokens
Input$0.08Best$0.30
Output$0.24Best$1.20
Performance
Throughput26.6 tok/s44.5 tok/sBest
Time to first token2.8 s0.7 sBest
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index7.37.4Best
Math Index19.7Best15.3
Capabilities
ToolsYesNo
Structured outputNoYes
PDF inputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • Qwen 3 32b
  • Hermes 4 Large

Intelligence Index

  • Qwen 3 32b7.3
  • Hermes 4 Large7.4

Qwen 3 32b: Better than 10% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Qwen 3 32b: 19.7Top
    • Hermes 4 Large: 15.3

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen 3 32b: 0.0%
    • Hermes 4 Large: 22.0%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen 3 32b: 4.1%
    • Hermes 4 Large: 4.2%Top

  • GPQA Diamond

    Graduate-level science questions

    • Qwen 3 32b: 53.5%
    • Hermes 4 Large: 53.6%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Qwen 3 32b: 72.7%
    • Hermes 4 Large: 72.9%Top

  • IFBench

    Following precise output instructions

    • Qwen 3 32b: 31.5%
    • Hermes 4 Large: 34.8%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Qwen 3 32b: 28.8%
    • Hermes 4 Large: 54.6%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Qwen 3 32b: 19.7%Top
    • Hermes 4 Large: 15.3%

  • AIME

    Competition mathematics

    • Qwen 3 32b: 30.3%
    • Hermes 4 Large: —

  • MATH-500

    Competition math problems

    • Qwen 3 32b: 86.9%
    • Hermes 4 Large: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen 3 32b: —
    • Hermes 4 Large: 9.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen 3 32b: —
    • Hermes 4 Large: 26.6%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen 3 32b: 0.0%
    • Hermes 4 Large: 22.0%Top

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

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
26.6 tok/s
Faster than 17% of 263 models
Time to first token
2.8 s
Quicker than 62% of 263 models
Prompt cache hits
0.0%
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 92.8%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

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/qwen3-32b",
    "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/qwen3-32b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Qwen

Other Qwen models, starting with the same family.