← All comparisons

Llama 3.1 Nemotron Instruct 70B vs Claude 3.5 Sonnet (June '24)

NVIDIA vs Anthropic — side-by-side benchmark comparison

Llama 3.1 Nemotron Instruct 70BClaude 3.5 Sonnet (June '24)
Intelligence Index13.414.2
Coding Index10.826.0
Math Index11.0
Output speed (tok/s)292.90.0
Blended price ($/1M)$1.20$6.56
Time to first token (s)0.24s0.00s
aime24.7%9.7%
aime 2511.0%
artificial analysis coding index10.8026.00
artificial analysis intelligence index13.4014.20
artificial analysis math index11.00
gpqa46.5%56.0%
hle4.6%3.7%
ifbench30.7%
lcr7.0%
livecodebench16.9%
math 50073.3%69.5%
mmlu pro69.0%75.1%
scicode23.3%31.6%
tau223.1%
terminalbench hard4.5%

Benchmark data from Artificial Analysis.