Llama 3.1 8B
Meta · 1 configuration
Intelligence6.9
Input / 1M$0.02
Output / 1M$0.05
Context128K
Tariff: Meta · 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
Compact Llama instruction model for fast chat and local deployment
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
6.9 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
25.9 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
5.3 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
1.5 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
16.4 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
28.6 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
8.5 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputNot available
Speed140.4 tok/s
First token0.91 s
Maximum output131.1K
Catalog listing date2024-07-23