← All comparisons

Magistral Small 1.2 vs Hermes 4 - Llama-3.1 70B (Reasoning)

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

Magistral Small 1.2Hermes 4 - Llama-3.1 70B (Reasoning)
Intelligence Index18.216.0
Coding Index14.814.4
Math Index80.368.7
Output speed (tok/s)111.192.8
Blended price ($/1M)$0.75$0.20
Time to first token (s)0.38s0.64s
aime
aime 2580.3%68.7%
artificial analysis coding index14.8014.40
artificial analysis intelligence index18.2016.00
artificial analysis math index80.3068.70
gpqa66.3%69.9%
hle6.1%7.9%
ifbench44.4%31.3%
lcr16.3%6.7%
livecodebench72.3%65.3%
math 500
mmlu pro76.8%81.1%
scicode35.2%34.1%
tau227.8%22.5%
terminalbench hard4.5%4.5%

Benchmark data from Artificial Analysis.