Llama 3.2 Instruct 3B
Creator
Meta AI (FAIR)
Released
2024-09-25
Intelligence
9.7
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$0.15
input tokens
Out $/1M
$0.15
output tokens
Blended $/1M
$0.15
3:1 blended
Speed
52
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
26
Humanity’s Last Exam
5
MMLU-Pro
35
SciCode
5
LiveCodeBench
8
MATH-500
49
AIME 2025
3
τ²-Bench (agentic)
21
Terminal-Bench Hard—
IFBench
26