DeepSeek R1 Distill Llama 70B
DeepSeek · 1 configuration
Intelligence7.9
Input / 1M$0.70
Output / 1M$1.10
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 thinking · Click a point to switch configuration
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
7.9 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
40.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
5.1 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
21.9 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
27.6 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
19.2 %Specifications from the catalog
Inputtext
Outputtext
Tool callingNo
Structured outputYes
SpeedNot available
First tokenNot available
Maximum output8.2K
Catalog listing date2025-01-27