← All comparisons

Magistral Small 1.2 vs Llama Nemotron Super 49B v1.5 (Reasoning)

Mistral vs NVIDIA — side-by-side benchmark comparison

Magistral Small 1.2Llama Nemotron Super 49B v1.5 (Reasoning)
Intelligence Index18.218.7
Coding Index14.815.1
Math Index80.376.7
Output speed (tok/s)111.148.1
Blended price ($/1M)$0.75$0.17
Time to first token (s)0.38s0.30s
aime86.0%
aime 2580.3%76.7%
artificial analysis coding index14.8015.10
artificial analysis intelligence index18.2018.70
artificial analysis math index80.3076.70
gpqa66.3%74.8%
hle6.1%6.8%
ifbench44.4%37.0%
lcr16.3%34.0%
livecodebench72.3%73.7%
math 50098.3%
mmlu pro76.8%81.4%
scicode35.2%34.8%
tau227.8%28.1%
terminalbench hard4.5%5.3%

Benchmark data from Artificial Analysis.