← All comparisons

Llama Nemotron Super 49B v1.5 (Reasoning) vs Hermes 3 - Llama-3.1 70B

NVIDIA vs Nous Research — side-by-side benchmark comparison

Llama Nemotron Super 49B v1.5 (Reasoning)Hermes 3 - Llama-3.1 70B
Intelligence Index18.710.6
Coding Index15.1
Math Index76.7
Output speed (tok/s)48.133.2
Blended price ($/1M)$0.17$0.30
Time to first token (s)0.30s0.38s
aime86.0%2.3%
aime 2576.7%
artificial analysis coding index15.10
artificial analysis intelligence index18.7010.60
artificial analysis math index76.70
gpqa74.8%40.1%
hle6.8%4.1%
ifbench37.0%
lcr34.0%
livecodebench73.7%18.8%
math 50098.3%53.8%
mmlu pro81.4%57.1%
scicode34.8%23.1%
tau228.1%
terminalbench hard5.3%

Benchmark data from Artificial Analysis.