← All comparisons

Hermes 4 - Llama-3.1 405B (Reasoning) vs Claude 3.5 Sonnet (Oct '24)

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

Hermes 4 - Llama-3.1 405B (Reasoning)Claude 3.5 Sonnet (Oct '24)
Intelligence Index18.615.9
Coding Index16.030.2
Math Index69.7
Output speed (tok/s)38.60.0
Blended price ($/1M)$1.50$6.56
Time to first token (s)0.79s0.00s
aime15.7%
aime 2569.7%
artificial analysis coding index16.0030.20
artificial analysis intelligence index18.6015.90
artificial analysis math index69.70
gpqa72.7%59.9%
hle10.3%3.9%
ifbench32.7%
lcr20.7%
livecodebench68.6%38.1%
math 50077.1%
mmlu pro82.9%77.2%
scicode25.2%36.6%
tau222.2%
terminalbench hard11.4%

Benchmark data from Artificial Analysis.