Llama 3.1 Instruct 8B
Creator
Meta AI (FAIR)
Released
2024-07-23
Intelligence
7.6
Artificial Analysis Index
Coding
5.4
Artificial Analysis Index
In $/1M
$0.07
input tokens
Out $/1M
$0.09
output tokens
Blended $/1M
$0.08
3:1 blended
Speed
0
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
26
Humanity’s Last Exam
5
MMLU-Pro
48
SciCode
13
LiveCodeBench
12
MATH-500
52
AIME 2025
4
τ²-Bench (agentic)
16
Terminal-Bench Hard
1
IFBench
29