NOUMENOpen app
NOUMEN

Qwen · Open weights

Qwen3.5 397B A17B TEE

Added Feb 28, 2026Open weights

Compare models

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

Loading models…

Use in the app

Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention. Running inside a TEE (Trusted Execution Environment), with provider attestation support.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.55
Output
$3.50

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
65.5K

Side by side

Qwen3.5 397B A17B TEE 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…

Qwen3.5 397B A17B TEEQwenThis modelMiMo V2.5 ThinkingxiaomiRemove
ProviderQwenxiaomi
Discovery tierOpen weightsOpen weights
AddedFeb 28, 2026Jun 3, 2026
Limits
Context window262.14K1.05MBest
Max output65.54K131.07KBest
Average output—1.1K tokens
Pricing, USD per 1M tokens
Input$0.55$0.14Best
Output$3.50$0.28Best
Cache read—$0.0028
Cache write—$0.00
Performance
Throughput—41.3 tok/s
Time to first token—7.2 s
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index21.421.8Best
Coding Index—56.8
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effort—none, high

Public evaluations

Benchmarks

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

  • Qwen3.5 397B A17B TEE
  • MiMo V2.5 Thinking

Intelligence Index

  • Qwen3.5 397B A17B TEE21.4
  • MiMo V2.5 Thinking21.8

Qwen3.5 397B A17B TEE: Better than 51% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Qwen3.5 397B A17B TEE: —
    • MiMo V2.5 Thinking: 56.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Qwen3.5 397B A17B TEE: —
    • MiMo V2.5 Thinking: 18.4%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Qwen3.5 397B A17B TEE: —
    • MiMo V2.5 Thinking: 3.3%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Qwen3.5 397B A17B TEE: —
    • MiMo V2.5 Thinking: 754 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Qwen3.5 397B A17B TEE: —
    • MiMo V2.5 Thinking: 996 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Qwen3.5 397B A17B TEE: —
    • MiMo V2.5 Thinking: 4.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen3.5 397B A17B TEE: 64.3%
    • MiMo V2.5 Thinking: 73.0%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen3.5 397B A17B TEE: 19.8%
    • MiMo V2.5 Thinking: 27.2%Top

  • GPQA Diamond

    Graduate-level science questions

    • Qwen3.5 397B A17B TEE: 86.1%Top
    • MiMo V2.5 Thinking: 84.9%

  • IFBench

    Following precise output instructions

    • Qwen3.5 397B A17B TEE: 51.6%
    • MiMo V2.5 Thinking: 67.1%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Qwen3.5 397B A17B TEE: —
    • MiMo V2.5 Thinking: 0.0%

  • SciCode

    Scientific computing in Python

    • Qwen3.5 397B A17B TEE: —
    • MiMo V2.5 Thinking: 43.9%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen3.5 397B A17B TEE: 35.6%
    • MiMo V2.5 Thinking: 41.7%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen3.5 397B A17B TEE: 83.9%
    • MiMo V2.5 Thinking: 90.6%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen3.5 397B A17B TEE: 64.3%
    • MiMo V2.5 Thinking: 73.0%Top

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": "TEE/qwen3.5-397b-a17b",
    "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="TEE/qwen3.5-397b-a17b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Qwen

Other Qwen models, starting with the same family.