DeepSeek
DeepSeek

DeepSeek V3.2

Model ID:deepseek/deepseek-v3.2
2025-12-01Open Model
API
OverallNo.14
PopularityNo.55

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

Knowledge Cutoff
Unknown

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory
164K

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words
$0.26IN$0.38OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

AI Performance Evaluation

Arena Overall Score
1424
±4
As of 2026-04-02
Overall Rank
No.55
39,412 Votes
Arena by Ability
Hard Prompts
1446±5No.54
Expert Knowledge
1446±13No.54
Instruction Following
1421±7No.44
Conversation Memory
1424±8No.57
Creative
1401±9No.49
Coding
1468±7No.55
Math
1429±12No.45
Arena by Occupation
Creative Writing
1410±7No.45
Social Sciences
1450±8No.49
Media
1394±8No.57
Business
1419±8No.55
Healthcare
1443±13No.63
Legal
1430±12No.59
Software
1454±6No.63
Mathematics
1442±15No.43
Reasoning Ability
AA Intelligence Index
42%↑3%
MMLU-Pro
86%↑4%
GPQA Diamond
84%↑2%
HLE
22%↑6%
Math
AA Math Index
92%↑18%
AIME 2025
92%↑18%
Coding Ability
AA Coding Index
37%↑0%
LiveCodeBench
86%↑21%
SciCode
39%↓3%
TerminalBench
36%↑2%
Instruction Following
IFBench
61%↑3%
Long Context
AA-LCR
65%↑1%
Agentic AI Ability
TAU2
91%↑19%
Speed
Standard Mode
47tok/sec↓31
First Output 1.26s
Artificial Analysis
Reasoning Mode
47tok/sec↓26
First Output 44.33s
Artificial Analysis