NOUMENOpen app
NOUMEN

Qwen · Open weights

Qwen3.6 35B A3B TEE

Added Jun 9, 2026Open weights

Compare models

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

Loading models…

Use in the app

Qwen3.6 35B A3B is an open-weight MoE model from Alibaba's Qwen team with 35B total parameters and 3B active parameters per token. 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
$0.20
Output
$1.27

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
262.1K
Average output (7 days)
3.9K tokens
Longer than 98% of 468 models

Side by side

Qwen3.6 35B A3B 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…

Qwen3.6 35B A3B TEEQwenThis modelKimi K2 0905MoonshotRemove
ProviderQwenMoonshot
Discovery tierOpen weightsOpen weights
AddedJun 9, 2026Sep 25, 2025
Limits
Context window262.14K262.14K
Max output262.14KBest100.35K
Average output3.9K tokens677 tokens
Pricing, USD per 1M tokens
Input$0.20Best$0.40
Output$1.27Best$1.80
Performance
Throughput—55.2 tok/s
Time to first token—3.2 s
Request success (24h)99.5%100.0%Best
Benchmark indexes
Intelligence Index15.215.3Best
Coding Index28.1—
Math Index—57.3
Capabilities
ToolsNoYes
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Qwen3.6 35B A3B TEE
  • Kimi K2 0905

Intelligence Index

  • Qwen3.6 35B A3B TEE15.2
  • Kimi K2 090515.3

Qwen3.6 35B A3B TEE: Better than 38% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Qwen3.6 35B A3B TEE: 28.1
    • Kimi K2 0905: —

  • Math Index

    Composite of the math evaluations

    • Qwen3.6 35B A3B TEE: —
    • Kimi K2 0905: 57.3

Agentic work

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Qwen3.6 35B A3B TEE: 847 Elo
    • Kimi K2 0905: —

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen3.6 35B A3B TEE: 64.3%Top
    • Kimi K2 0905: 53.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen3.6 35B A3B TEE: 13.9%Top
    • Kimi K2 0905: 6.4%

  • GPQA Diamond

    Graduate-level science questions

    • Qwen3.6 35B A3B TEE: 81.7%Top
    • Kimi K2 0905: 76.7%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Qwen3.6 35B A3B TEE: —
    • Kimi K2 0905: 81.9%

  • IFBench

    Following precise output instructions

    • Qwen3.6 35B A3B TEE: 36.2%
    • Kimi K2 0905: 41.7%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Qwen3.6 35B A3B TEE: —
    • Kimi K2 0905: 61.0%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Qwen3.6 35B A3B TEE: —
    • Kimi K2 0905: 57.3%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen3.6 35B A3B TEE: 25.8%Top
    • Kimi K2 0905: 23.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen3.6 35B A3B TEE: 85.1%Top
    • Kimi K2 0905: 73.4%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen3.6 35B A3B TEE: 64.3%Top
    • Kimi K2 0905: 53.0%

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
13.6%
Request success (24h)
99.5%
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 77.7%
  • 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": "TEE/qwen3.6-35b-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="TEE/qwen3.6-35b-a3b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Qwen

Other Qwen models, starting with the same family.