DeepSeek V3.2 Speciale
DeepSeek · 1 configuration
Intelligence14.5
Input / 1M$0.58
Output / 1M$1.68
Context128K
Tariff: Azure · Source: models-dev · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
DeepSeek chat model for instruction following, coding, and analysis
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
14.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
87.1 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
28.7 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
0.0 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
63.9 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
37.8 %Specifications from the catalog
Inputtext
Outputtext
Tool callingNo
Structured outputNot available
SpeedNot available
First tokenNot available
Maximum output128K
Catalog listing date2025-12-01