← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs Hermes 4 - Llama-3.1 405B (Non-reasoning)

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

Claude 4.5 Haiku (Non-reasoning)Hermes 4 - Llama-3.1 405B (Non-reasoning)
Intelligence Index31.017.6
Coding Index29.618.1
Math Index39.015.3
Output speed (tok/s)105.840.8
Blended price ($/1M)$2.19$1.50
Time to first token (s)0.65s0.73s
aime
aime 2539.0%15.3%
artificial analysis coding index29.6018.10
artificial analysis intelligence index31.0017.60
artificial analysis math index39.0015.30
gpqa64.6%53.6%
hle4.3%4.2%
ifbench42.0%34.8%
lcr43.7%20.0%
livecodebench51.1%54.6%
math 500
mmlu pro80.0%72.9%
scicode34.4%34.6%
tau232.5%26.6%
terminalbench hard27.3%9.8%

Benchmark data from Artificial Analysis.