NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek V3.2 Exp Thinking

Added Jan 1, 2024Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

DeepSeek V3.2 Exp Thinking is an experimental V3-series reasoning model with improved long-context efficiency compared with earlier V3 releases. FP8.

  • Reasoning
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.28
Output
$0.42

Reference prices as published by the model provider. API example

Specifications

Context window
163.8K
Max output
65.5K
Average output (7 days)
917 tokens
Longer than 68% of 468 models

Side by side

Compare models

Put DeepSeek V3.2 Exp Thinking next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryStep 3.5 FlashGemma 4 26B A4BOpenAI o4-mini highAll 3

Public evaluations

Benchmarks

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

Intelligence Index

16.6

Better than 43% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    87.7

    Composite of the math evaluations

    Better than 79% of 118 scored models

Document reasoning

  • AA-LCRv1.1

    72.3%

    Reasoning across long documents

    Better than 54% of 309 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    14.9%

    Expert-level questions across academic fields

    Better than 41% of 323 scored models

  • GPQA Diamond

    79.7%

    Graduate-level science questions

    Better than 47% of 291 scored models

  • MMLU-Pro

    85.0%

    Multi-subject knowledge and reasoning

    Better than 86% of 132 scored models

  • IFBench

    54.1%

    Following precise output instructions

    Better than 54% of 215 scored models

Coding

  • LiveCodeBench

    78.9%

    Recent competitive programming problems

    Better than 80% of 129 scored models

Math

  • AIME 2025

    87.7%

    Competition mathematics, 2025 problems

    Better than 79% of 118 scored models

Legacy evaluations

  • Terminal-Bench Hard

    31.1%

    Earlier terminal task suite

    Better than 57% of 212 scored models

  • τ²-Bench Telecom

    33.9%

    Tool use in a customer-support simulation

    Better than 26% of 214 scored models

  • AA-LCR (unversioned)

    72.3%

    Long-context reasoning, earlier grading

    Better than 54% of 309 scored models

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.

Throughput
11.0 tok/s
Faster than 0% of 254 models
Time to first token
6.1 s
Quicker than 27% of 254 models
Prompt cache hits
78.5%
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 98.0%
  • 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": "deepseek-ai/deepseek-v3.2-exp-thinking",
    "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="deepseek-ai/deepseek-v3.2-exp-thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.