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.1 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

DeepSeek V3.2 Exp 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 Exp ThinkingDeepSeekThis modelOpenAI o4-mini highOpenAIRemove
ProviderDeepSeekOpenAI
Discovery tierOpen weightsEfficient
AddedJan 1, 2024Dec 4, 2025
Limits
Context window163.84K200KBest
Max output65.54K100KBest
Average output917 tokens75 tokens
Pricing, USD per 1M tokens
Input$0.28Best$1.10
Output$0.42Best$4.40
Cache read—$0.55
Performance
Throughput12.8 tok/s—
Time to first token5.0 s—
Request success (24h)100.0%—
Benchmark indexes
Intelligence Index16.616.7Best
Math Index87.790.7Best
Capabilities
ReasoningYesYes
ToolsNoYes
Structured outputNoYes
Reasoning effort—low, medium, high

Public evaluations

Benchmarks

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

  • DeepSeek V3.2 Exp Thinking
  • OpenAI o4-mini high

Intelligence Index

  • DeepSeek V3.2 Exp Thinking16.6
  • OpenAI o4-mini high16.7

DeepSeek V3.2 Exp Thinking: Better than 43% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • DeepSeek V3.2 Exp Thinking: 87.7
    • OpenAI o4-mini high: 90.7Top

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • DeepSeek V3.2 Exp Thinking: 72.3%Top
    • OpenAI o4-mini high: 61.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • DeepSeek V3.2 Exp Thinking: 14.9%
    • OpenAI o4-mini high: 16.5%Top

  • GPQA Diamond

    Graduate-level science questions

    • DeepSeek V3.2 Exp Thinking: 79.7%Top
    • OpenAI o4-mini high: 78.4%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • DeepSeek V3.2 Exp Thinking: 85.0%Top
    • OpenAI o4-mini high: 83.2%

  • IFBench

    Following precise output instructions

    • DeepSeek V3.2 Exp Thinking: 54.1%
    • OpenAI o4-mini high: 68.7%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • DeepSeek V3.2 Exp Thinking: 78.9%
    • OpenAI o4-mini high: 85.9%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • DeepSeek V3.2 Exp Thinking: 87.7%
    • OpenAI o4-mini high: 90.7%Top

  • AIME

    Competition mathematics

    • DeepSeek V3.2 Exp Thinking: —
    • OpenAI o4-mini high: 94.0%

  • MATH-500

    Competition math problems

    • DeepSeek V3.2 Exp Thinking: —
    • OpenAI o4-mini high: 98.9%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • DeepSeek V3.2 Exp Thinking: 31.1%Top
    • OpenAI o4-mini high: 15.2%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • DeepSeek V3.2 Exp Thinking: 33.9%
    • OpenAI o4-mini high: 55.6%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • DeepSeek V3.2 Exp Thinking: 72.3%Top
    • OpenAI o4-mini high: 61.0%

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.

Throughput
12.8 tok/s
Faster than 2% of 259 models
Time to first token
5.0 s
Quicker than 33% of 259 models
Prompt cache hits
79.0%
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.