Llama 3.2 3B
Meta · 1 configuration
Intelligence5.7
Input / 1M$0.05
Output / 1M$0.34
Context128K
Tariff: Cloudflare Workers AI · 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 default · Click a point to switch configuration
Open Llama instruction model for multilingual chat, reasoning, and coding
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
5.7 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
25.5 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
5.3 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
21.1 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
26.2 %Specifications from the catalog
Inputtext
Outputtext
Tool callingNo
Structured outputNo
SpeedNot available
First tokenNot available
Maximum output80K
Catalog listing date2024-09-25