← All comparisons

Magistral Medium 1.2 vs Qwen3 32B (Reasoning)

Mistral vs Alibaba — side-by-side benchmark comparison

Magistral Medium 1.2Qwen3 32B (Reasoning)
Intelligence Index27.116.5
Coding Index21.713.8
Math Index82.073.0
Output speed (tok/s)39.493.4
Blended price ($/1M)$2.75$0.28
Time to first token (s)0.54s1.13s
aime80.7%
aime 2582.0%73.0%
artificial analysis coding index21.7013.80
artificial analysis intelligence index27.1016.50
artificial analysis math index82.0073.00
gpqa73.9%66.8%
hle9.6%8.3%
ifbench43.0%36.3%
lcr51.3%0.0%
livecodebench75.0%54.6%
math 50096.1%
mmlu pro81.5%79.8%
scicode39.2%35.4%
tau252.0%29.8%
terminalbench hard12.9%3.0%

Benchmark data from Artificial Analysis.