← All comparisons

Magistral Medium 1.2 vs Hermes 4 - Llama-3.1 405B (Non-reasoning)

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

Magistral Medium 1.2Hermes 4 - Llama-3.1 405B (Non-reasoning)
Intelligence Index27.117.6
Coding Index21.718.1
Math Index82.015.3
Output speed (tok/s)39.440.8
Blended price ($/1M)$2.75$1.50
Time to first token (s)0.54s0.73s
aime
aime 2582.0%15.3%
artificial analysis coding index21.7018.10
artificial analysis intelligence index27.1017.60
artificial analysis math index82.0015.30
gpqa73.9%53.6%
hle9.6%4.2%
ifbench43.0%34.8%
lcr51.3%20.0%
livecodebench75.0%54.6%
math 500
mmlu pro81.5%72.9%
scicode39.2%34.6%
tau252.0%26.6%
terminalbench hard12.9%9.8%

Benchmark data from Artificial Analysis.