← All comparisons

DeepHermes 3 - Mistral 24B Preview (Non-reasoning) vs Claude 4.5 Sonnet (Non-reasoning)

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

DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Claude 4.5 Sonnet (Non-reasoning)
Intelligence Index10.937.1
Coding Index33.5
Math Index37.0
Output speed (tok/s)0.054.7
Blended price ($/1M)$0.00$6.56
Time to first token (s)0.00s1.08s
aime4.7%
aime 2537.0%
artificial analysis coding index33.50
artificial analysis intelligence index10.9037.10
artificial analysis math index37.00
gpqa38.2%72.7%
hle3.9%7.1%
ifbench42.7%
lcr51.3%
livecodebench19.5%59.0%
math 50059.5%
mmlu pro58.0%86.0%
scicode22.8%42.8%
tau270.5%
terminalbench hard28.8%

Benchmark data from Artificial Analysis.