← All comparisons

Claude 3 Sonnet vs Hermes 3 - Llama-3.1 70B

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

Claude 3 SonnetHermes 3 - Llama-3.1 70B
Intelligence Index10.310.6
Coding Index
Math Index
Output speed (tok/s)0.033.2
Blended price ($/1M)$6.00$0.30
Time to first token (s)0.00s0.38s
aime4.7%2.3%
aime 25
artificial analysis coding index
artificial analysis intelligence index10.3010.60
artificial analysis math index
gpqa40.0%40.1%
hle3.8%4.1%
ifbench
lcr
livecodebench17.5%18.8%
math 50041.4%53.8%
mmlu pro57.9%57.1%
scicode22.9%23.1%
tau2
terminalbench hard

Benchmark data from Artificial Analysis.