NOUMENOpen app
NOUMEN

Qwen · Open weights

Qwen3 30B A3B

Added Feb 27, 2025Open weights

Compare models

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

Loading models…

Use in the app

Qwen 3 30b A3B is a 30b model with 3 billion active parameters per pass. 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.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.30

Reference prices as published by the model provider. API example

Specifications

Context window
41K
Max output
32.8K
Average output (7 days)
228 tokens
Longer than 24% of 465 models

Side by side

Qwen3 30B A3B 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 30B A3BQwenThis modelLlama 4 ScoutMetaRemove
ProviderQwenMeta
Discovery tierOpen weightsOpen weights
AddedFeb 27, 2025Sep 5, 2025
Limits
Context window41K328KBest
Max output32.77K65.54KBest
Average output228 tokens79 tokens
Pricing, USD per 1M tokens
Input$0.10$0.085Best
Output$0.30Best$0.46
Performance
Request success (24h)99.2%Best49.6%
Benchmark indexes
Intelligence Index6.6Best6.5
Coding Index—8.2
Math Index21.7Best14.0
Capabilities
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 30B A3B
  • Llama 4 Scout

Intelligence Index

  • Qwen3 30B A3B6.6
  • Llama 4 Scout6.5

Qwen3 30B A3B: Better than 5% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Qwen3 30B A3B: —
    • Llama 4 Scout: 8.2

  • Math Index

    Composite of the math evaluations

    • Qwen3 30B A3B: 21.7Top
    • Llama 4 Scout: 14.0

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Qwen3 30B A3B: —
    • Llama 4 Scout: 0.2%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Qwen3 30B A3B: —
    • Llama 4 Scout: 0.0%

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Qwen3 30B A3B: —
    • Llama 4 Scout: 0.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen3 30B A3B: 0.0%
    • Llama 4 Scout: 27.7%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen3 30B A3B: 4.6%Top
    • Llama 4 Scout: 3.8%

  • GPQA Diamond

    Graduate-level science questions

    • Qwen3 30B A3B: 51.5%
    • Llama 4 Scout: 58.7%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Qwen3 30B A3B: 71.0%
    • Llama 4 Scout: 75.2%Top

  • IFBench

    Following precise output instructions

    • Qwen3 30B A3B: 31.9%
    • Llama 4 Scout: 39.5%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Qwen3 30B A3B: —
    • Llama 4 Scout: 0.0%

  • SciCode

    Scientific computing in Python

    • Qwen3 30B A3B: —
    • Llama 4 Scout: 21.3%

  • LiveCodeBench

    Recent competitive programming problems

    • Qwen3 30B A3B: 32.2%Top
    • Llama 4 Scout: 29.9%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Qwen3 30B A3B: 21.7%Top
    • Llama 4 Scout: 14.0%

  • AIME

    Competition mathematics

    • Qwen3 30B A3B: 26.0%
    • Llama 4 Scout: 28.3%Top

  • MATH-500

    Competition math problems

    • Qwen3 30B A3B: 86.3%Top
    • Llama 4 Scout: 84.4%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen3 30B A3B: 6.8%Top
    • Llama 4 Scout: 1.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen3 30B A3B: 22.2%Top
    • Llama 4 Scout: 15.5%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen3 30B A3B: 0.0%
    • Llama 4 Scout: 27.7%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.

Request success (24h)
99.2%
Reliable
Hourly request success · last 72 hoursLowest hour 88.8%
  • 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/qwen3-30b-a3b",
    "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/qwen3-30b-a3b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Qwen

Other Qwen models, starting with the same family.