← All comparisons

Mistral Small 3.2 vs Qwen3 235B A22B 2507 (Reasoning)

Mistral vs Alibaba — side-by-side benchmark comparison

Mistral Small 3.2Qwen3 235B A22B 2507 (Reasoning)
Intelligence Index15.129.5
Coding Index13.323.2
Math Index27.091.0
Output speed (tok/s)133.062.5
Blended price ($/1M)$0.13$0.84
Time to first token (s)0.36s1.21s
aime32.3%94.0%
aime 2527.0%91.0%
artificial analysis coding index13.3023.20
artificial analysis intelligence index15.1029.50
artificial analysis math index27.0091.00
gpqa50.5%79.0%
hle4.3%15.0%
ifbench33.5%51.2%
lcr17.3%67.0%
livecodebench27.5%78.8%
math 50088.3%98.4%
mmlu pro68.1%84.3%
scicode26.4%42.4%
tau229.5%53.2%
terminalbench hard6.8%13.6%

Benchmark data from Artificial Analysis.