NOUMENOpen app
NOUMEN

Qwen · Open weights

Qwen3 Next 80B A3B (Instruct)

Added Sep 11, 2025Open weights

Compare models

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

Loading models…

Use in the app

Based on the new Qwen3‑Next architecture (hybrid attention, highly sparse MoE, training‑stability optimizations, and multi‑token prediction), the Qwen3‑Next‑80B‑A3B‑Instruct model delivers extreme efficiency with only 3B active parameters per pass. It performs comparably to Qwen3‑235B‑A22B‑Instruct‑2507 and shows clear advantages on ultra‑long context tasks (up to 256K tokens).

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

Pricing

USD per 1M tokens
Input
$0.09
Output
$1.10

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
—

Side by side

Qwen3 Next 80B 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 Next 80B A3B (Instruct)QwenThis modelGemma 4 26B A4BGoogleRemove
ProviderQwenGoogle
Discovery tierOpen weightsOpen weights
AddedSep 11, 2025Apr 2, 2026
Limits
Context window262.14K262.14K
Max output—131.07K
Average output—131 tokens
Pricing, USD per 1M tokens
Input$0.09$0.09
Output$1.10$0.30Best
Cache read—$0.05
Performance
Throughput—86.0 tok/s
Time to first token—2.4 s
Request success (24h)98.8%100.0%Best
Benchmark indexes
Intelligence Index—16.7
Coding Index—39.3
Capabilities
ReasoningNoYes
ToolsYesYes
VisionNoYes
Structured outputYesYes
Video inputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Qwen3 Next 80B A3B (Instruct)
  • Gemma 4 26B A4B

Intelligence Index

  • Qwen3 Next 80B A3B (Instruct)—
  • Gemma 4 26B A4B16.7
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 39.3

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 1.9%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 0.2%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 315 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 565 Elo

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 65.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 19.3%

  • GPQA Diamond

    Graduate-level science questions

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 79.2%

  • IFBench

    Following precise output instructions

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 72.4%

Coding

  • SciCode

    Scientific computing in Python

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 40.0%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 13.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 43.6%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen3 Next 80B A3B (Instruct): —
    • Gemma 4 26B A4B: 65.7%

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
0.0%
Request success (24h)
98.8%
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 94.2%
  • 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-next-80b-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-next-80b-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.