DeepSeek V3.1
DeepSeek · 2 thinking configurations
Intelligence13.5
Input / 1M$0.58
Output / 1M$1.68
Context128K
Tariff: DeepSeek · Source: artificial-analysis · 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 cost2 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
13.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
77.9 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
14.3 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
37.4 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
41.5 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
29.0 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
SpeedNot available
First tokenNot available
Maximum output32.8K
Catalog listing date2025-08-21