NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek V3.2 Thinking

Added Dec 1, 2025Open weights

Compare models

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

Loading models…

Use in the app

DeepSeek V3.2 (thinking/reasoner mode) — official successor to V3.2-Exp. Reasoning-first model built for agents with GPT-5 level performance. Balanced inference vs. output length. First DeepSeek model with thinking-in-tool-use capability. FP8.

  • Reasoning
  • Tools
  • Structured output
  • PDF input
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.21
Output
$0.31
Cache read
$0.0216

Reference prices as published by the model provider. API example

Specifications

Context window
163K
Max output
65.5K
Average output (7 days)
1.4K tokens
Longer than 85% of 465 models

Side by side

DeepSeek V3.2 Thinking 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…

DeepSeek V3.2 ThinkingDeepSeekThis modelDeepSeek V3.2DeepSeekRemove
ProviderDeepSeekDeepSeek
Discovery tierOpen weightsOpen weights
AddedDec 1, 2025Dec 1, 2025
Limits
Context window163K163K
Max output65.54K65.54K
Average output1.4K tokens408 tokens
Pricing, USD per 1M tokens
Input$0.21$0.21
Output$0.31$0.31
Cache read$0.0216$0.0216
Performance
Throughput41.1 tok/s50.2 tok/sBest
Time to first token1.7 sBest2.6 s
Request success (24h)99.9%Best99.6%
Benchmark indexes
Intelligence Index21.5Best16.0
Coding Index44.2—
Math Index92.0Best59.0
Capabilities
ReasoningYesNo
ToolsYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • DeepSeek V3.2 Thinking
  • DeepSeek V3.2

Intelligence Index

  • DeepSeek V3.2 Thinking21.5
  • DeepSeek V3.216.0

DeepSeek V3.2 Thinking: Better than 52% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • DeepSeek V3.2 Thinking: 44.2
    • DeepSeek V3.2: —

  • Math Index

    Composite of the math evaluations

    • DeepSeek V3.2 Thinking: 92.0Top
    • DeepSeek V3.2: 59.0

Agentic work

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • DeepSeek V3.2 Thinking: 691 Elo
    • DeepSeek V3.2: —

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • DeepSeek V3.2 Thinking: 73.3%Top
    • DeepSeek V3.2: 45.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • DeepSeek V3.2 Thinking: 24.6%Top
    • DeepSeek V3.2: 11.2%

  • GPQA Diamond

    Graduate-level science questions

    • DeepSeek V3.2 Thinking: 84.0%Top
    • DeepSeek V3.2: 75.1%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • DeepSeek V3.2 Thinking: 86.2%Top
    • DeepSeek V3.2: 83.7%

  • IFBench

    Following precise output instructions

    • DeepSeek V3.2 Thinking: 60.7%Top
    • DeepSeek V3.2: 49.0%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • DeepSeek V3.2 Thinking: 86.2%Top
    • DeepSeek V3.2: 59.3%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • DeepSeek V3.2 Thinking: 92.0%Top
    • DeepSeek V3.2: 59.0%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • DeepSeek V3.2 Thinking: 35.6%Top
    • DeepSeek V3.2: 32.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • DeepSeek V3.2 Thinking: 90.6%Top
    • DeepSeek V3.2: 78.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • DeepSeek V3.2 Thinking: 73.3%Top
    • DeepSeek V3.2: 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.

Throughput
41.1 tok/s
Faster than 31% of 250 models
Time to first token
1.7 s
Quicker than 86% of 250 models
Prompt cache hits
63.6%
About $0.0897 per 1M input tokens with caching
Request success (24h)
99.9%
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 98.8%
  • 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": "deepseek/deepseek-v3.2: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/deepseek-v3.2:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.