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.
Added Dec 1, 2025
Model weightsContext Window
163.0K
Max Output
65.5K
Avg output tokens (7d)
1.4K tokens
Input Price (Auto)
$0.21/1M
Output Price (Auto)
$0.31/1M
Cache Read (Auto)
$0.022/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
21.5
Coding Index
44.2
Agentic work
T²-Bench Telecom (legacy)
Legacy fallback · Conversational AI agents in dual-control scenarios
90.6%
Better than 85% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
810 Elo
Better than 37% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
73.3%
Better than 73% of models compared
Reasoning
HLE
Humanity's Last Exam
24.6%
Better than 76% of models compared
IFBench
Instruction-following benchmark
60.7%
Better than 72% of models compared
CritPt
Research-level physics reasoning
2.9%
Coding
Terminal-Bench Hard (legacy)
Legacy fallback · Agentic coding and terminal use
35.6%
Better than 82% of models compared
LiveCodeBench
Contamination-free coding benchmark
86.2%
Better than 97% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
92.0%
Better than 94% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
86.2%
Better than 95% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
33.0%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
82.7%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
84.0%
Better than 74% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
73.3%
Better than 73% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
15.5%
Last updated Sep 13, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare DeepSeek V3.2 Thinking with similar models from the same provider or model family.
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flashDeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use.
DeepSeek V4.1 Flash Thinking
deepseek/deepseek-v4.1-flash:thinkingDeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use.
DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-expAn experimental vision-enabled DeepSeek V4 Flash model that adds image understanding while retaining the text, reasoning, coding, tool-calling, and agent capabilities of the base model.
DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813DeepSeek V4 Pro 0813 is the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.
DeepSeek V4 Pro 0813 Thinking
deepseek/deepseek-v4-pro-0813:thinkingDeepSeek V4 Pro 0813 Thinking enables reasoning by default on the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.
DeepSeek V4 Flash Latest
deepseek/deepseek-v4-flash-latestCompatibility alias that routes to the newest dated DeepSeek V4 Flash release.