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
Context Window
163.0K
Max Output
65.5K
Input Price (Auto)
$0.26/1M
Output Price (Auto)
$0.40/1M
Cache Read (Auto)
$0.026/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
41.7
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
36.7
GPQA Diamond
Graduate-level scientific reasoning
84.0%
Better than 89% of models compared
HLE
Humanity's Last Exam
22.2%
Better than 90% of models compared
IFBench
Instruction-following benchmark
60.7%
Better than 79% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
90.6%
Better than 88% of models compared
AA-LCR
Long context reasoning evaluation
65.0%
Better than 88% of models compared
SciCode
Python programming for scientific computing
38.9%
Better than 79% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
35.6%
Better than 88% of models compared
AIME 2025
American Invitational Mathematics Examination 2025
92.0%
Better than 94% of models compared
MMLU-Pro
Professional and academic subject knowledge
86.2%
Better than 95% of models compared
Last updated May 15, 2026
Artificial AnalysisLiveCodeBench
Contamination-free coding benchmark
86.2%
Better than 97% of models compared
