NOUMENOpen app
NOUMEN

Qwen · Open weights

Qwen3 Coder 30B A3B Instruct

Added Aug 5, 2025Open weights

Compare models

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

Loading models…

Use in the app

Qwen3 Coder 30B with 3B active parameters, optimized for code generation and technical tasks

  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.40

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
65.5K

Side by side

Qwen3 Coder 30B A3B Instruct 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 Coder 30B A3B InstructQwenThis modelQwen 3 Coder 480BQwenRemove
ProviderQwenQwen
Discovery tierOpen weightsOpen weights
AddedAug 5, 2025Mar 17, 2026
Limits
Context window128K262KBest
Max output65.54K65.54K
Average output—315 tokens
Pricing, USD per 1M tokens
Input$0.10Best$0.13
Output$0.40Best$0.50
Performance
Throughput—72.7 tok/s
Time to first token—4.8 s
Request success (24h)100.0%Best94.7%
Benchmark indexes
Intelligence Index—11.9
Math Index—39.3
Capabilities
ToolsYesYes
Structured outputYesYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Qwen3 Coder 30B A3B Instruct
  • Qwen 3 Coder 480B

Intelligence Index

  • Qwen3 Coder 30B A3B Instruct—
  • Qwen 3 Coder 480B11.9
3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 39.3

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 45.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 4.5%

  • GPQA Diamond

    Graduate-level science questions

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 61.8%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 78.8%

  • IFBench

    Following precise output instructions

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 40.5%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 58.5%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 39.3%

  • AIME

    Competition mathematics

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 47.7%

  • MATH-500

    Competition math problems

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 94.2%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 18.9%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 43.6%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen3 Coder 30B A3B Instruct: —
    • Qwen 3 Coder 480B: 45.7%

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.

Prompt cache hits
49.1%
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 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-coder-30b-a3b-instruct",
    "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-coder-30b-a3b-instruct",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Qwen

Other Qwen models, starting with the same family.