DeepSeek V3 (Dec)
DeepSeek · 1 configuration
Intelligence8.5
Input / 1M$0.32
Output / 1M$0.89
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 cost1 measured configurations · 0 without both values
Selected: thinking default · Click a point to switch configuration
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
8.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
55.7 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
2.9 %SciCodeCode generation for scientific research problems.
35.8 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
16.9 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
22.8 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
34.8 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
25.4 %Specifications from the catalog
Inputtext
Outputtext
Tool callingNot available
Structured outputNot available
SpeedNot available
First tokenNot available
Maximum output—
Catalog listing dateNot available