DeepSeek logo
DeepSeek
•

Open weights release

•

Released setembro de 2025

DeepSeek V3.2 Exp: Release Intelligence, Performance & Price

Available providers

DeepSeekDeepSeekNovitaNovita

Intelligence

DeepSeek V3.2 ExpDeepSeek V3.2 Exp
26
DeepSeek V3.2 ExpDeepSeek V3.2 Exp
22

Artificial Analysis Intelligence Index

Speed

DeepSeek V3.2 ExpDeepSeek V3.2 Exp
-
DeepSeek V3.2 ExpDeepSeek V3.2 Exp
-

Output speed

Cost

DeepSeek V3.2 ExpDeepSeek V3.2 Exp
-
DeepSeek V3.2 ExpDeepSeek V3.2 Exp
-

Per Intelligence Index Task

The DeepSeek V3.2 Exp release offers 2 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across the 2 models.

  • For intelligence, the top model of DeepSeek V3.2 Exp is DeepSeek V3.2 Exp (Reasoning) at 26.

Input modality

Supports: text

Output modality

Supports: text

Context window128k
~192 A4 pages of size 12 Arial font
Total parameters685B
Active parameters37B
Number of parameters active per token during inference
LicenseMIT
Model weightsHugging Face

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Speed & Latency

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Capability Scores

Capability Indices

Measures the performance of models on specific capabilities and industries
Agentic Index

Measures performance in agentic workflows, focusing on behaviors like tool use, planning, autonomy, and complex problem solving.

Finance & Accounting Index

Incorporates 5 evaluations: AA-Omniscience, GDPval-AA v2, Humanity's Last Exam, 𝜏³-Banking, AA-LCR · Higher is better

Strategy & Ops Index

Incorporates 4 evaluations: AA-Omniscience, GDPval-AA v2, 𝜏³-Banking, AA-LCR · Higher is better

Legal Index

Incorporates 5 evaluations: AA-Omniscience, GDPval-AA v2, AA-LCR, 𝜏³-Banking, Humanity's Last Exam · Higher is better

Healthcare & Medical Index

Incorporates 4 evaluations: AA-Omniscience, GDPval-AA v2, Humanity's Last Exam, 𝜏³-Banking · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, GPQA Diamond, CritPt, GDPval-AA v2, Terminal-Bench v2.1 · Higher is better

Economics Index

Incorporates 4 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-LCR · Higher is better

Reasoning models are indicated by a lightbulb icon

More from DeepSeek

Further details

Weights
Provider Benchmarks
DeepSeek V3.2 Exp (Reasoning)
DeepSeek logoDeepSeek
26
685B
37B active at inference time
128k
$0.1
-
🤗
NovitaDeepSeek
View
DeepSeek V3.2 Exp (Non-reasoning)
DeepSeek logoDeepSeek
22
685B
37B active at inference time
128k
$0.1
-
🤗
NovitaDeepSeek
View