← All benchmarks

Llama 3.1 Nemotron Instruct 70B

NVIDIA · Released 2024-10-15 · Independent benchmark scores from Artificial Analysis

Intelligence Index
7.6
Output speed
78.6
tokens/sec
Blended price
$1.20
per 1M tokens
Time to first token
5.73s

Model metadata

Model ID7393c56a-ec31-48e9-b804-c04f2d2cb641
Slugllama-3-1-nemotron-instruct-70b
Release date2024-10-15
ProviderNVIDIA
Provider slugnvidia
Output speed78.6 tok/s
Time to first token5.73s
Time to first answer5.73s
Blended price ($/1M)$1.20
Input price ($/1M)$1.20
Output price ($/1M)$1.20

All evaluation scores (17)

aime24.7%
aime 2511.0%
artificial analysis coding index
artificial analysis intelligence index7.60
artificial analysis math index11.00
gpqa46.5%
hle4.6%
ifbench30.7%
lcr7.0%
livecodebench16.9%
math 50073.3%
mmlu pro69.0%
scicode23.3%
tau banking
tau223.1%
terminalbench hard4.5%
terminalbench v2 1

Source: artificialanalysis.ai/models/llama-3-1-nemotron-instruct-70b

Benchmark data from Artificial Analysis.